This document discusses the use of wavelet transforms for medical image processing, specifically for hip arthroplasty. It provides background on wavelet transforms and how they can be used for tasks like de-noising and segmentation. The document then describes the key parameters measured in hip arthroplasty, including parameters from anterior-posterior and anterior-lateral x-rays both before and after prosthesis insertion. It also discusses using the DICOM standard to organize medical image data and extracting information from DICOM files.
Image guided surgery involves using preoperative scans like MRI or CT to create 3D reconstructions of the surgical area. This information can be used for surgical planning, simulation, and navigation during the procedure. For navigation, the 3D models are registered to the patient in the operating room using probes to locate anatomical landmarks. This allows the surgeon to view internal structures and track the position of surgical tools to aid precision. Key benefits are improved accuracy, reduced risks to vital structures, and assistance for complex cases where normal anatomy is distorted.
This document discusses image guided surgery, which uses computer technology and 3D imaging like CT and MRI scans to guide surgical interventions. Key aspects covered include:
- Image guidance allows surgeons to view a patient's anatomy during surgery to locate structures hidden from direct vision.
- Registration aligns the 3D imaging with the patient's actual anatomy using tracking devices and fiducial markers.
- Volume rendering and surface rendering techniques are used to visualize 3D models of the patient's anatomy overlaid during surgery.
- Accuracy depends on factors like registration error and tracking device precision. Image guidance is useful for locating small structures in complex areas like the skull base.
Lec1: Medical Image Computing - Introduction Ulaş Bağcı
2017 Spring, UCF Medical Image Computing Course
Basics of Radiological Image Modalities and their clinical use (MRI, PET, CT, fMRI, DTI, ...)
• Introduction to Medical Image Computing and Toolkits
• Image Filtering, Enhancement, Noise Reduction, and
Signal Processing
• MedicalImageRegistration
• MedicalImageSegmentation
• MedicalImageVisualization
• Machine Learning in Medical Imaging
• Shape Modeling/Analysis of Medical Images
Deep Learning in Radiology
Lumbar disk 3D modeling from limited number of MRI axial slices IJECEIAES
This paper studies the problem of clinical MRI analysis in the field of lumbar intervertebral disk herniation diagnosis. It discusses the possibility of assisting radiologists in reading the patient's MRI images by constructing a 3D model for the region of interest using simple computer vision methods. We use axial MRI slices of the lumbar area. The proposed framework works with a very small number of MRI slices and goes through three main stages. Namely, the region of interest extraction and enhancement, inter-slice interpolation, and 3D model construction. We use the Marching Cubes algorithm to construct the 3D model of the region of interest. The validation of our 3D models is based on a radiologist's analysis of the models. We tested the proposed 3D model construction on 83 cases and We have a 95% accuracy according to the radiologist evaluation. This study shows that 3D model construction can greatly ease the task of the radiologist which enhances the working experience. This leads eventually to a more accurate and easy diagnosis process.
Stereotaxy is a method used in neurosurgery to locate structures inside the brain using external reference points and coordinates. It involves fixing an animal's head in a stereotactic frame then using coordinates from a stereotactic atlas, along with microdrives on the frame, to target locations inside the brain. Verniers on the microdrives allow precise movement along 3 axes to reach targets. An example is given of determining the stereotactic coordinates to target the substantia nigra pars reticulata in a rat, taking into account the need to approach at an angle to avoid blood vessels.
This document describes a study that evaluated the accuracy of using computer-assisted virtual surgical planning and guides for reconstructing zygomatic bone defects with vascularized iliac crest bone grafts. CT scans of patients' faces and bone grafts were used to create 3D models and virtual surgical plans. Surgical guides were fabricated to transfer the plans intraoperatively. Postoperative CT scans found the mean difference in bone graft shape and position between actual and planned was 0.71mm and 3.53mm respectively, indicating good accuracy of the computer-assisted method.
Image guided surgery involves using preoperative scans like MRI or CT to create 3D reconstructions of the surgical area. This information can be used for surgical planning, simulation, and navigation during the procedure. For navigation, the 3D models are registered to the patient in the operating room using probes to locate anatomical landmarks. This allows the surgeon to view internal structures and track the position of surgical tools to aid precision. Key benefits are improved accuracy, reduced risks to vital structures, and assistance for complex cases where normal anatomy is distorted.
This document discusses image guided surgery, which uses computer technology and 3D imaging like CT and MRI scans to guide surgical interventions. Key aspects covered include:
- Image guidance allows surgeons to view a patient's anatomy during surgery to locate structures hidden from direct vision.
- Registration aligns the 3D imaging with the patient's actual anatomy using tracking devices and fiducial markers.
- Volume rendering and surface rendering techniques are used to visualize 3D models of the patient's anatomy overlaid during surgery.
- Accuracy depends on factors like registration error and tracking device precision. Image guidance is useful for locating small structures in complex areas like the skull base.
Lec1: Medical Image Computing - Introduction Ulaş Bağcı
2017 Spring, UCF Medical Image Computing Course
Basics of Radiological Image Modalities and their clinical use (MRI, PET, CT, fMRI, DTI, ...)
• Introduction to Medical Image Computing and Toolkits
• Image Filtering, Enhancement, Noise Reduction, and
Signal Processing
• MedicalImageRegistration
• MedicalImageSegmentation
• MedicalImageVisualization
• Machine Learning in Medical Imaging
• Shape Modeling/Analysis of Medical Images
Deep Learning in Radiology
Lumbar disk 3D modeling from limited number of MRI axial slices IJECEIAES
This paper studies the problem of clinical MRI analysis in the field of lumbar intervertebral disk herniation diagnosis. It discusses the possibility of assisting radiologists in reading the patient's MRI images by constructing a 3D model for the region of interest using simple computer vision methods. We use axial MRI slices of the lumbar area. The proposed framework works with a very small number of MRI slices and goes through three main stages. Namely, the region of interest extraction and enhancement, inter-slice interpolation, and 3D model construction. We use the Marching Cubes algorithm to construct the 3D model of the region of interest. The validation of our 3D models is based on a radiologist's analysis of the models. We tested the proposed 3D model construction on 83 cases and We have a 95% accuracy according to the radiologist evaluation. This study shows that 3D model construction can greatly ease the task of the radiologist which enhances the working experience. This leads eventually to a more accurate and easy diagnosis process.
Stereotaxy is a method used in neurosurgery to locate structures inside the brain using external reference points and coordinates. It involves fixing an animal's head in a stereotactic frame then using coordinates from a stereotactic atlas, along with microdrives on the frame, to target locations inside the brain. Verniers on the microdrives allow precise movement along 3 axes to reach targets. An example is given of determining the stereotactic coordinates to target the substantia nigra pars reticulata in a rat, taking into account the need to approach at an angle to avoid blood vessels.
This document describes a study that evaluated the accuracy of using computer-assisted virtual surgical planning and guides for reconstructing zygomatic bone defects with vascularized iliac crest bone grafts. CT scans of patients' faces and bone grafts were used to create 3D models and virtual surgical plans. Surgical guides were fabricated to transfer the plans intraoperatively. Postoperative CT scans found the mean difference in bone graft shape and position between actual and planned was 0.71mm and 3.53mm respectively, indicating good accuracy of the computer-assisted method.
An Automated Pelvic Bone Geometrical Feature Measurement Utilities on Ct Scan...IOSR Journals
This document discusses an automated system for measuring geometric features of the pelvic bone from CT scan images. The system uses patch statistical shape models and a multilevel measurement utility to determine pelvic orientation based on image calibration. It aims to help orthopedic surgeons locate damage areas and landmarks more accurately, especially for obese patients where manual palpation is difficult. The system involves experts to analyze statistical values generated from the measurements to inform treatment decisions.
Track 6. Technological innovations in biomedical training and practice
Authors: Jesús M Gonçalves, M J Sanchez-Ledesma, P Ruisoto, M Jaramillo, J J Jimenez and J A Juanes
Robotic Surgery In Orthopaedics - orthoapedic seminar-Dr Mukul Jain GMCH, U...MukulJain81
Robotic surgery is gaining popularity in orthopaedics for its ability to perform minimally invasive surgery with improved accuracy of implant placement. There are three main types of robotic systems - autonomous systems which operate independently, passive navigation systems which provide guidance to surgeons, and semi-autonomous systems which combine surgeon control with robotic guidance and restraint of surgical tools. While robotic surgery shows benefits of precision and alignment, it also faces limitations such as financial costs, difficulty with soft tissues, and a need for further validation of long-term clinical outcomes.
190330 AI & cloud based medical/dental SW (KIST 김영준)Youngjun Kim
1) The document discusses various AI and cloud-based dental and medical software developed by the Korea Institute of Science and Technology, including tools for 3D modeling, surgical planning, landmark detection, segmentation, and disease diagnosis using deep learning.
2) Key technologies described include Boolean operations on 3D models, mesh repairing, offset surfaces, automated landmark detection on cephalograms, mandible segmentation, and using deep learning to diagnose rotator cuff tears on MRI with over 93% accuracy.
3) The tools are being commercialized and many were developed through collaborations with dental and medical universities to improve patient treatments.
This document discusses medical image processing and its application to breast cancer detection. It provides an overview of digital image processing techniques used in medical imaging like X-rays, mammography, ultrasound, MRI and CT. Computer-aided diagnosis (CAD) helps in tasks like visualization, detection, localization, segmentation and classification of medical images. For breast cancer detection specifically, the document discusses mammography and challenges in detecting tumors in dense breast tissue. It also reviews several published methods for segmenting and analyzing lesions in mammograms and evaluates their performance based on parameters like true positives, false positives, etc.
Augmented Reality : Future of Orthopedic SurgeryPayelBanerjee17
I just wanted people to be aware of all the recent advancements occurring in surgeries, and in medicine. so here I'm uploading it in public. kindly look into it. also, you can check out my
https://thatindiangirl1.blogspot.com (blog)
The Indian Dental Academy is the Leader in continuing dental education , training dentists in all
aspects of dentistry and
offering a wide range of dental certified courses in different formats.for more details please visit
www.indiandentalacademy.com
An automated 3D cup planning in total hip arthroplasty from a standard X‑ray ...AutoImPlan team
This document describes a method for automated 3D cup planning in total hip arthroplasty using only a standard X-ray radiograph as input. Boundaries are extracted from the X-ray and used to reconstruct the 3D pelvis shape via an atlas-based 2D-3D method. Cup diameter and position are then automatically determined. The method was tested on 6 cases, achieving pelvis reconstruction errors of 1.8mm on average and cup planning errors similar to using 3D CT images. The method shows potential for automated preoperative planning without needing 3D CT scans.
The document discusses the objective of being a leader in producing replicas of osseous tissue and customized bone implants using CT, X-ray, or MRI images. It describes 3 action areas: 1) using models for surgical planning to improve outcomes, 2) producing customized implants to reduce additional surgeries and recovery time, and 3) developing new bioactive implant technologies. The document then outlines a 3-stage process for producing replicas, biocompatible implants, and biocompatible implants with bioactive components. Examples of use for maxillofacial surgery planning and reconstruction are provided.
Robotic systems are increasingly being used in orthopaedic surgery to improve accuracy and consistency when performing procedures like total hip replacements, unicompartmental knee replacements, and anterior lumbar interbody fusions. These systems can be autonomous, haptic/surgeon-guided, or passive, and preliminary results suggest robotic assistance may lead to short-term improvements in clinical and radiological outcomes compared to traditional techniques. The precision and accuracy afforded by robotic surgery is well-suited for operations on bones and may help achieve better long-term outcomes by more accurately placing implants and balancing tissues.
Basics of computational assessment for COPD: IWPFI 2017Namkug Kim
1) The document discusses computational assessment methods for chronic obstructive pulmonary disease (COPD) using medical imaging data. It covers topics like lung segmentation, lobe segmentation, airway measurement, vessel quantification, and texture-based emphysema quantification.
2) Various algorithms are presented for tasks like robust lung and lobe segmentation, left/right lung splitting, airway skeletonization and labeling, and classification of pulmonary arteries and veins.
3) Quantitative image analysis methods are discussed for measuring airway wall thickness, quantifying emphysema heterogeneity, and classifying COPD patterns based on texture and shape features.
1) The document discusses the use of artificial intelligence in orthodontics, including applications like automated cephalometric analysis, skeletal classification, predicting orthodontic treatment needs, and 3D tooth segmentation.
2) AI technologies like convolutional neural networks, artificial neural networks, and deep learning are being used in these orthodontic applications.
3) While AI is proving accurate and can help practitioners make decisions faster, limitations include cost, data protection concerns, and ensuring AI systems do not replace human clinicians for serious medical decisions.
Computer-assisted orthopaedic surgery uses computer and robotic technologies to provide precision and accuracy to orthopaedic procedures. This includes pre-operative planning tools, intraoperative navigation equipment, smart tools, and remote surgery technologies. The key benefits of computer-assisted orthopaedics are improved geometric precision, reproducibility, and reduced radiation exposure compared to conventional surgery. Navigation systems precisely guide surgical tools using tracking systems and registration of pre-operative images.
CrystalGuide flat fee surgical guide and triple scan - a new and effective pr...Michael Gross
CrystalGuide flat fee surgical guide and triple scan - a new and effective protocol for 3D planning and guided surgery of partially edentulous cases CrystalGuide - complete service for advanced 3D planning and guided surgery of dental implants
1) The document describes a study comparing computer-assisted mandibular reconstruction using vascularized iliac crest bone grafts to conventional reconstruction techniques.
2) With computer-assisted planning, a surgical guide was designed based on CT scans and used to precisely shape and position the bone graft. This method aimed to reduce operating time and bone removal compared to conventional techniques.
3) Results found that with computer-assisted planning, the bone graft fit perfectly into the mandibular defect with less adjustment needed. Operating time and bone removed were also reduced compared to conventional techniques. Patients reported higher satisfaction with their appearance.
Recent advances in diagnosis and treatment planning1 /certified fixed orthod...Indian dental academy
The Indian Dental Academy is the Leader in continuing dental education , training dentists in all aspects of dentistry and offering a wide range of dental certified courses in different formats.
Indian dental academy provides dental crown & Bridge,rotary endodontics,fixed orthodontics,
Dental implants courses.for details pls visit www.indiandentalacademy.com ,or call
0091-9248678078
This study evaluated the use of computer-assisted surgery using 3D planning and surgical guides compared to conventional surgery for reconstructing jaw defects with free vascularized fibular flaps. The computer-assisted approach significantly reduced shaping time and ischemic time compared to conventional surgery. It also eliminated discrepancies between the size of the fibula defect and transplant size. One flap failed in the conventional group, while all flaps were successful with the computer-assisted approach. The results suggest computer-assisted surgery may improve outcomes for fibular flap reconstruction of jaw defects.
This document provides an overview of how virtual reality is being applied in various areas of medicine, with a focus on surgery, neurosurgery, and mental and physical rehabilitation. It discusses how VR is used for surgical planning and simulation, particularly for minimally invasive endoscopic surgery. VR training simulators are also described as a way to practice new procedures safely. The document outlines some of the technical challenges in making VR simulations realistic and the transfer of skills from VR to real-world surgery. Pre-operative planning systems that use actual patient data are distinguished from training simulations. Telemedicine and collaborative applications are also mentioned.
1. The document discusses applying 3D printing to medical imaging by discussing medical image modeling.
2. It covers topics like virtual surgery modeling, 3D printers, image scanners, requirements for 3D printed medical models, and the medical imaging workflow from acquisition to 3D printing and post-processing.
3. Key aspects of medical image-based 3D printing discussed are image segmentation, surface modeling, and an in-house software for virtual simulated surgery.
The objective of this work is to propose an image
denoising technique and compare it with image denoising
using ridgelets. The proposed method uses slantlet transform
instead of wavelets in ridgelet transform. Experimental result
shows that the proposed method is more effective than ridgelets
in noise removal. The proposed method is effective in
compressing images while preserving edges.
Skeletal Bone Age Analysis Using Emroi TechniqueIOSR Journals
The document describes a system for skeletal bone age estimation using region extraction from X-ray images of the left hand and wrist. The system uses discrete wavelet transformation, energy-based segmentation, and the Jacobi method to extract features like the carpal region and epiphyseal/metaphysical region. These extracted features are classified using k-means clustering to determine the bone age. The system was tested on a sample of 24 X-ray images and results were discussed. Performance was compared to other existing bone age assessment methods.
An Automated Pelvic Bone Geometrical Feature Measurement Utilities on Ct Scan...IOSR Journals
This document discusses an automated system for measuring geometric features of the pelvic bone from CT scan images. The system uses patch statistical shape models and a multilevel measurement utility to determine pelvic orientation based on image calibration. It aims to help orthopedic surgeons locate damage areas and landmarks more accurately, especially for obese patients where manual palpation is difficult. The system involves experts to analyze statistical values generated from the measurements to inform treatment decisions.
Track 6. Technological innovations in biomedical training and practice
Authors: Jesús M Gonçalves, M J Sanchez-Ledesma, P Ruisoto, M Jaramillo, J J Jimenez and J A Juanes
Robotic Surgery In Orthopaedics - orthoapedic seminar-Dr Mukul Jain GMCH, U...MukulJain81
Robotic surgery is gaining popularity in orthopaedics for its ability to perform minimally invasive surgery with improved accuracy of implant placement. There are three main types of robotic systems - autonomous systems which operate independently, passive navigation systems which provide guidance to surgeons, and semi-autonomous systems which combine surgeon control with robotic guidance and restraint of surgical tools. While robotic surgery shows benefits of precision and alignment, it also faces limitations such as financial costs, difficulty with soft tissues, and a need for further validation of long-term clinical outcomes.
190330 AI & cloud based medical/dental SW (KIST 김영준)Youngjun Kim
1) The document discusses various AI and cloud-based dental and medical software developed by the Korea Institute of Science and Technology, including tools for 3D modeling, surgical planning, landmark detection, segmentation, and disease diagnosis using deep learning.
2) Key technologies described include Boolean operations on 3D models, mesh repairing, offset surfaces, automated landmark detection on cephalograms, mandible segmentation, and using deep learning to diagnose rotator cuff tears on MRI with over 93% accuracy.
3) The tools are being commercialized and many were developed through collaborations with dental and medical universities to improve patient treatments.
This document discusses medical image processing and its application to breast cancer detection. It provides an overview of digital image processing techniques used in medical imaging like X-rays, mammography, ultrasound, MRI and CT. Computer-aided diagnosis (CAD) helps in tasks like visualization, detection, localization, segmentation and classification of medical images. For breast cancer detection specifically, the document discusses mammography and challenges in detecting tumors in dense breast tissue. It also reviews several published methods for segmenting and analyzing lesions in mammograms and evaluates their performance based on parameters like true positives, false positives, etc.
Augmented Reality : Future of Orthopedic SurgeryPayelBanerjee17
I just wanted people to be aware of all the recent advancements occurring in surgeries, and in medicine. so here I'm uploading it in public. kindly look into it. also, you can check out my
https://thatindiangirl1.blogspot.com (blog)
The Indian Dental Academy is the Leader in continuing dental education , training dentists in all
aspects of dentistry and
offering a wide range of dental certified courses in different formats.for more details please visit
www.indiandentalacademy.com
An automated 3D cup planning in total hip arthroplasty from a standard X‑ray ...AutoImPlan team
This document describes a method for automated 3D cup planning in total hip arthroplasty using only a standard X-ray radiograph as input. Boundaries are extracted from the X-ray and used to reconstruct the 3D pelvis shape via an atlas-based 2D-3D method. Cup diameter and position are then automatically determined. The method was tested on 6 cases, achieving pelvis reconstruction errors of 1.8mm on average and cup planning errors similar to using 3D CT images. The method shows potential for automated preoperative planning without needing 3D CT scans.
The document discusses the objective of being a leader in producing replicas of osseous tissue and customized bone implants using CT, X-ray, or MRI images. It describes 3 action areas: 1) using models for surgical planning to improve outcomes, 2) producing customized implants to reduce additional surgeries and recovery time, and 3) developing new bioactive implant technologies. The document then outlines a 3-stage process for producing replicas, biocompatible implants, and biocompatible implants with bioactive components. Examples of use for maxillofacial surgery planning and reconstruction are provided.
Robotic systems are increasingly being used in orthopaedic surgery to improve accuracy and consistency when performing procedures like total hip replacements, unicompartmental knee replacements, and anterior lumbar interbody fusions. These systems can be autonomous, haptic/surgeon-guided, or passive, and preliminary results suggest robotic assistance may lead to short-term improvements in clinical and radiological outcomes compared to traditional techniques. The precision and accuracy afforded by robotic surgery is well-suited for operations on bones and may help achieve better long-term outcomes by more accurately placing implants and balancing tissues.
Basics of computational assessment for COPD: IWPFI 2017Namkug Kim
1) The document discusses computational assessment methods for chronic obstructive pulmonary disease (COPD) using medical imaging data. It covers topics like lung segmentation, lobe segmentation, airway measurement, vessel quantification, and texture-based emphysema quantification.
2) Various algorithms are presented for tasks like robust lung and lobe segmentation, left/right lung splitting, airway skeletonization and labeling, and classification of pulmonary arteries and veins.
3) Quantitative image analysis methods are discussed for measuring airway wall thickness, quantifying emphysema heterogeneity, and classifying COPD patterns based on texture and shape features.
1) The document discusses the use of artificial intelligence in orthodontics, including applications like automated cephalometric analysis, skeletal classification, predicting orthodontic treatment needs, and 3D tooth segmentation.
2) AI technologies like convolutional neural networks, artificial neural networks, and deep learning are being used in these orthodontic applications.
3) While AI is proving accurate and can help practitioners make decisions faster, limitations include cost, data protection concerns, and ensuring AI systems do not replace human clinicians for serious medical decisions.
Computer-assisted orthopaedic surgery uses computer and robotic technologies to provide precision and accuracy to orthopaedic procedures. This includes pre-operative planning tools, intraoperative navigation equipment, smart tools, and remote surgery technologies. The key benefits of computer-assisted orthopaedics are improved geometric precision, reproducibility, and reduced radiation exposure compared to conventional surgery. Navigation systems precisely guide surgical tools using tracking systems and registration of pre-operative images.
CrystalGuide flat fee surgical guide and triple scan - a new and effective pr...Michael Gross
CrystalGuide flat fee surgical guide and triple scan - a new and effective protocol for 3D planning and guided surgery of partially edentulous cases CrystalGuide - complete service for advanced 3D planning and guided surgery of dental implants
1) The document describes a study comparing computer-assisted mandibular reconstruction using vascularized iliac crest bone grafts to conventional reconstruction techniques.
2) With computer-assisted planning, a surgical guide was designed based on CT scans and used to precisely shape and position the bone graft. This method aimed to reduce operating time and bone removal compared to conventional techniques.
3) Results found that with computer-assisted planning, the bone graft fit perfectly into the mandibular defect with less adjustment needed. Operating time and bone removed were also reduced compared to conventional techniques. Patients reported higher satisfaction with their appearance.
Recent advances in diagnosis and treatment planning1 /certified fixed orthod...Indian dental academy
The Indian Dental Academy is the Leader in continuing dental education , training dentists in all aspects of dentistry and offering a wide range of dental certified courses in different formats.
Indian dental academy provides dental crown & Bridge,rotary endodontics,fixed orthodontics,
Dental implants courses.for details pls visit www.indiandentalacademy.com ,or call
0091-9248678078
This study evaluated the use of computer-assisted surgery using 3D planning and surgical guides compared to conventional surgery for reconstructing jaw defects with free vascularized fibular flaps. The computer-assisted approach significantly reduced shaping time and ischemic time compared to conventional surgery. It also eliminated discrepancies between the size of the fibula defect and transplant size. One flap failed in the conventional group, while all flaps were successful with the computer-assisted approach. The results suggest computer-assisted surgery may improve outcomes for fibular flap reconstruction of jaw defects.
This document provides an overview of how virtual reality is being applied in various areas of medicine, with a focus on surgery, neurosurgery, and mental and physical rehabilitation. It discusses how VR is used for surgical planning and simulation, particularly for minimally invasive endoscopic surgery. VR training simulators are also described as a way to practice new procedures safely. The document outlines some of the technical challenges in making VR simulations realistic and the transfer of skills from VR to real-world surgery. Pre-operative planning systems that use actual patient data are distinguished from training simulations. Telemedicine and collaborative applications are also mentioned.
1. The document discusses applying 3D printing to medical imaging by discussing medical image modeling.
2. It covers topics like virtual surgery modeling, 3D printers, image scanners, requirements for 3D printed medical models, and the medical imaging workflow from acquisition to 3D printing and post-processing.
3. Key aspects of medical image-based 3D printing discussed are image segmentation, surface modeling, and an in-house software for virtual simulated surgery.
The objective of this work is to propose an image
denoising technique and compare it with image denoising
using ridgelets. The proposed method uses slantlet transform
instead of wavelets in ridgelet transform. Experimental result
shows that the proposed method is more effective than ridgelets
in noise removal. The proposed method is effective in
compressing images while preserving edges.
Skeletal Bone Age Analysis Using Emroi TechniqueIOSR Journals
The document describes a system for skeletal bone age estimation using region extraction from X-ray images of the left hand and wrist. The system uses discrete wavelet transformation, energy-based segmentation, and the Jacobi method to extract features like the carpal region and epiphyseal/metaphysical region. These extracted features are classified using k-means clustering to determine the bone age. The system was tested on a sample of 24 X-ray images and results were discussed. Performance was compared to other existing bone age assessment methods.
image denoising technique using disctere wavelet transformalishapb
This document discusses image denoising techniques using discrete wavelet transforms. It begins with an introduction and lists the objectives, goals, and types of noise that affect images. It then describes several denoising techniques including spatial filtering methods like mean, wiener and median filters as well as frequency domain filtering and wavelet domain filtering. The document provides block diagrams of the wavelet denoising process and evaluates performance of various denoising algorithms using metrics like PSNR and SSIM. It was implemented in MATLAB and concluded that wavelet thresholding provides significant improvement in image quality while preserving useful information.
Curved Wavelet Transform For Image Denoising using MATLAB.Nikhil Kumar
This document summarizes a student project on image denoising using wavelet analysis. It introduces wavelet transforms as a method to denoise digital images corrupted by noise. The project uses MATLAB to apply a discrete wavelet transform with a Haar wavelet, thresholds wavelet coefficients at different levels to compress and denoise the image, and demonstrates the results on an example image.
This document discusses image denoising techniques. It begins by defining image denoising as removing unwanted noise from an image to restore the original signal. It then discusses several types of noise like additive Gaussian noise, impulse noise, uniform noise, and periodic noise. For denoising, it covers spatial domain techniques like linear filters (mean, weighted mean), non-linear filters (median filter), and frequency domain techniques that apply a low-pass filter to the Fourier transform of the noisy image. The document provides examples of denoising noisy images using mean and median filters to remove different types of noise.
The document discusses various image denoising algorithms. It defines image denoising as removing noise from an image. Common denoising algorithms discussed include spatial domain filters like Gaussian filtering, anisotropic filtering, and total variation minimization. Neighborhood filtering and non-local means (NL-means) are also summarized. Gaussian filtering blurs edges and textures while anisotropic filtering degrades flat and texture regions. Total variation minimization can oversmooth textures. Neighborhood filtering is not robust to noisy pixel values. In contrast, NL-means compares neighborhood configurations and is more robust than neighborhood filtering alone.
Image compression using discrete wavelet transformHarshal Ladhe
This document discusses image compression using the discrete wavelet transform (DWT) as outlined in the JPEG2000 standard. It presents the basic block diagram of image compression, including the encoder and decoder. It demonstrates color and gray-scale image compression across multiple levels of compression, showing the original and compressed images. It concludes that DWT provides high compression ratios while maintaining image quality and outperforms other traditional techniques. Future work is proposed to implement neural network-based compression.
This document provides information on fractures of the tibia. It begins with definitions of fractures and their various classifications. The causes of tibial fractures include direct forces, indirect forces, twisting, bending, and pathological fractures. Fracture patterns include transverse, oblique, spiral, impacted, comminuted, and compression fractures. Treatment options for tibial fractures depend on the fracture type and include casting, intramedullary nailing, plating, and external fixation. Complications can include nonunion, malunion, infection, and hardware failure. Open fractures require urgent debridement and antibiotics to prevent infection.
The document discusses image denoising techniques based on partial differential equations (PDEs). It begins by defining image noise and describing conventional denoising filters like averaging and median filters. It then focuses on diffusion-based denoising methods, particularly the influential 1987 work of Perona and Malik which introduced nonlinear anisotropic diffusion. Their approach uses an edge-stopping function to reduce diffusion near edges. The document outlines linear and nonlinear diffusion models, conditions for the diffusion coefficient function, and extensions of the Perona-Malik model. It summarizes a 2014 paper proposing a robust anisotropic diffusion scheme using novel variants of the edge-stopping function and diffusivity parameter computation.
Scaphoid fractures are the most common carpal bone fractures, often occurring in young adults from falls on an outstretched hand. The scaphoid has a tenuous blood supply and is prone to non-union, especially for proximal pole fractures. Treatment depends on fracture type and stability, ranging from casting to operative fixation with screws. Complications include malunion, delayed union, non-union and avascular necrosis, requiring further procedures like bone grafting or carpal fusion.
Shallow introduction for Deep Learning Retinal Image AnalysisPetteriTeikariPhD
This document provides an overview of various retinal imaging techniques and applications of deep learning to retinal image analysis. It discusses fundamentals of eye anatomy and image formation, as well as common retinal diseases. Imaging modalities covered include fundus photography, optical coherence tomography (OCT), and multispectral imaging. The document also explores nonlinear optical properties of the eye and applications of techniques like third harmonic generation microscopy. Finally, it touches on topics relevant to deep learning like data sources, annotation, data augmentation, network architectures, and hardware optimization. The goal is to introduce key concepts from different disciplines to facilitate communication across fields involved in retinal image analysis.
This document provides an introduction to wavelet transforms. It begins with an outline of topics to be covered, including an overview of wavelet transforms, the limitations of Fourier transforms, the historical development of wavelets, the principle of wavelet transforms, examples of applications, and references. It then discusses the stationarity of signals and how Fourier transforms cannot show when frequency components occur over time. Short-time Fourier analysis is introduced as a solution, but it is noted that wavelet transforms provide a more flexible approach by allowing the window size to vary. The document proceeds to define what a wavelet is, discuss the historical development of wavelet theory, provide examples of popular mother wavelets, and explain the steps to compute a continuous wave
fracture and dislocation ppt . Almas khan. khorfakkhan hospital dubaialmasmkm
This document discusses fractures and dislocations, including:
- Signs and symptoms of fractures like pain, deformity, and loss of function
- Types of fractures such as complete, incomplete, open, comminuted, spiral, and stress fractures
- Emergency care for fractures including splinting, immobilization, and controlling bleeding
- Diagnosis using x-rays, CT scans, or MRIs to identify fracture type and location
- Treatment options like casting, internal fixation surgery, traction, and exercise
- Factors that can delay or prevent fracture healing like infection, movement, and poor blood supply
- The role of the radiographer in obtaining quality images to aid in diagnosis and monitoring healing
This document defines trauma and fractures, and describes the types and features of fractures and dislocations. It discusses [1] the signs and symptoms of fractures, including pain, swelling, deformity and loss of movement or feeling; [2] the process of fracture healing through callus formation; and [3] factors that can affect healing like age, health, nutrition and circulation. It also provides examples and illustrations of different fracture patterns like transverse, spiral, comminuted, impacted and compression fractures.
- Mandibular fractures are common injuries that may be encountered by dental surgeons. They can be classified based on type, site, and cause of the fracture.
- Signs and symptoms depend on the specific site of the fracture and may include pain, swelling, limitation of mouth opening, and malocclusion. Radiographs are important for diagnosis.
- Management involves addressing the airway, hemorrhage, and pain. Definitive treatment consists of reduction to realign fragments followed by immobilization to allow bone healing, which depends on the stability and mobility at the fracture site. Teeth in the line of fracture may require extraction.
This document discusses different types of femoral bone fractures including neck, intertrochanteric, subtrochanteric, and shaft fractures. It provides details on femoral neck fractures, including causes such as falls in the elderly and high-energy injuries in younger patients. Treatment options are discussed including internal fixation with screws or pins for displaced fractures or prosthetic replacement in elderly patients. Complications of femoral fractures include nonunion, osteonecrosis, healing inhibition, and for shaft fractures, vascular injury, thromboembolism, infection, and malunion.
1. The document describes different types of fractures including complete, incomplete, impacted and comminuted fractures. It also discusses fracture classification systems and factors that influence bone healing.
2. Clinical signs of fractures include pain, swelling, deformity, loss of function. Examination involves inspection, palpation, and assessment of range of motion. Imaging plays a key role in diagnosis and fracture characterization.
3. Potential complications of fractures include vascular or nerve injury, visceral injury, infection, and malunion. Proper diagnosis and management can help prevent long-term disability.
This document summarizes a student project on implementing lossless discrete wavelet transform (DWT) and inverse discrete wavelet transform (IDWT). It provides an overview of the project, which includes introducing DWT, reviewing literature on lifting schemes for faster DWT computation, and simulating a 2D (5,3) DWT. The results show DWT blocks decomposing signals into high and low pass coefficients. Applications mentioned are in medical imaging, signal denoising, data compression and image processing. The conclusion discusses the need for lossless transforms in medical imaging. Future work could extend this to higher level transforms and applications like compression and watermarking.
Medical Image Processing in Nuclear Medicine and Bone ArthroplastyIOSR Journals
This document discusses medical image processing in nuclear medicine and bone arthroplasty. It provides background on nuclear medicine imaging techniques like planar imaging, SPECT, PET and hybrid SPECT/CT and PET/CT systems. It then discusses how MATLAB can be used for medical image processing tasks in nuclear medicine like organ contouring, interpolation, filtering, segmentation, background removal, registration and volume quantification. Specific examples of nuclear medicine examinations that can be analyzed using MATLAB algorithms are also mentioned.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
This document discusses 3D diagnostics in orofacial medicine using cone-beam computed tomography (CBCT). It begins by providing background on the development of 3D diagnostics and its limitations in dentistry due to high radiation exposure from traditional CT. The advent of CBCT enabled wider use of 3D diagnostics in dentistry by using a cone-shaped beam and lower radiation doses. CBCT provides high-resolution 3D images, allows for improved surgical planning, and greater understanding of procedures for patients. The document then describes the technical principles and components of CBCT scanning.
Implementation of Lower Leg Bone Fracture Detection from X Ray Imagesijtsrd
A methodology and various techniques are presented for development of fracture detection system using digital image processing. This paper presents an implementation of bone fracture detection using medical X ray image. The goal of this paper is to generate a quick and diagnosis can save time, effort and cost as well as reduce errors. The main objective of this research is to classify the lower leg bone fracture using X ray image because this type of bone are the most commonly occur in bone. This paper classifies the two types of fracture Non fracture and fracture or Transverse fracture by using SVM classifier. The proposed system has basically five steps, namely, image acquisition, image pre processing, image segmentation, feature extraction and image classification. San Myint | Khaing Thinzar "Implementation of Lower Leg Bone Fracture Detection from X-Ray Images" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-3 | Issue-5 , August 2019, URL: https://www.ijtsrd.com/papers/ijtsrd27957.pdfPaper URL: https://www.ijtsrd.com/engineering/electronics-and-communication-engineering/27957/implementation-of-lower-leg-bone-fracture-detection-from-x-ray-images/san-myint
Review on Medical Image Fusion using Shearlet TransformIRJET Journal
This document reviews medical image fusion using the shearlet transform. It discusses how medical image fusion combines information from multimodality images like CT, MRI, PET into a single image. The shearlet transform allows for more efficient encoding of anisotropic features compared to wavelets. The proposed algorithm involves decomposing registered input images using shearlet transforms, applying fusion rules to select coefficients, and reconstructing the fused image. Medical image fusion using shearlets can improve diagnosis by combining complementary anatomical and functional details from different imaging modalities.
This document provides an overview of CT simulation components and processes. It discusses the key elements of a CT simulator, including the CT scanner components like bore size and image quality, virtual simulation software features like contouring and image display, and other essentials like laser positioning and DICOM connectivity. CT simulation has advanced radiation therapy planning by providing detailed volumetric patient images to design customized treatment plans while reducing dose to healthy tissues.
Improving radiologists’ and orthopedists’ QoE in diagnosing lumbar disk herni...IJECEIAES
This document describes research on improving radiologists' and orthopedists' quality of experience (QoE) in diagnosing lumbar disk herniation using 3D modeling. The researchers built 3D models from MRI scans and developed an automated diagnosis framework. They evaluated the 3D models on 14 medical specialists and found it increased their QoE in 95% of cases. The automated framework was trained on 83 cases and tested on new cases, achieving 90% diagnosis accuracy.
This document presents a statistical path loss model for medical implant communication channels developed using an immersive 3D visualization environment. The environment allows simulation of radio frequency propagation from implantable antennas inside a virtual human body model. Simulations were performed for various near-surface and deep-tissue implant locations. A statistical path loss model was extracted from the simulation results to help optimize transceiver design for medical implants.
This document presents a statistical path loss model for radio frequency (RF) propagation from medical implants inside the human body. The authors used an immersive 3D visualization environment to simulate RF propagation from implant antennas in various locations within a 3D human body model. From the simulation data, they extracted statistical path loss models describing the relationship between received signal power and distance for deep tissue and near-surface implant scenarios. The models characterize implant-to-implant and implant-to-body surface propagation and can help optimize transceiver design for medical implant communication systems.
This document describes the process of creating a 3D CAD model of the human knee joint from CT scan data using reverse engineering and Mimics software. Key points:
- CT scan data of a 25-year-old male's knee was used to generate DICOM images, which were then imported into Mimics.
- Mimics software uses density segmentation to distinguish bone, soft tissues, and other structures based on pixel intensity in the images.
- Each bone segment was reconstructed separately through manual editing of density masks generated by Mimics.
- The final 3D model exported from Mimics in STL file format can be used for applications like surgical simulation and implant design where an accurate knee model is needed
Multimodality medical image fusion using improved contourlet transformationIAEME Publication
1. The document presents a technique for medical image fusion using an improved contourlet transformation with log Gabor filters.
2. It proposes decomposing images using a contourlet transformation with modified directional filter banks that incorporate log Gabor filters. This aims to provide high quality fused images while localizing features accurately and minimizing noise.
3. Experimental results on fusing medical images show that the proposed technique achieves higher quality measurements like PSNR compared to a basic contourlet transformation fusion approach.
This document discusses an integrated reverse engineering approach for dimensional and error analysis of a customized humerus bone implant. It begins with an overview of how reverse engineering and rapid prototyping can be used to create customized medical implants using CT scan data. It then describes a specific case study where a humerus bone implant was created for a patient using FDM printing. Dimensional and error analysis was performed on the printed implant using an optical measurement technique, finding a mean error of 0.1mm between the CAD model and printed implant. The study demonstrates the potential for reverse engineering and rapid prototyping to create accurate, customized bone implants but also highlights sources of error that must be considered.
Intelligent computing techniques on medical image segmentation and analysis a...eSAT Publishing House
IJRET : International Journal of Research in Engineering and Technology is an international peer reviewed, online journal published by eSAT Publishing House for the enhancement of research in various disciplines of Engineering and Technology. The aim and scope of the journal is to provide an academic medium and an important reference for the advancement and dissemination of research results that support high-level learning, teaching and research in the fields of Engineering and Technology. We bring together Scientists, Academician, Field Engineers, Scholars and Students of related fields of Engineering and Technology
CBCT has become an important tool in clinical orthodontics for providing 3D information. It was developed due to increasing demand for 3D data from conventional CT scans. This article discusses CBCT technology and its various uses in orthodontics such as detection of facial asymmetry, assessment of mandibular shape and growth, localization of impacted teeth, evaluation of root resorption and airway changes. CBCT allows more accurate diagnosis and treatment planning compared to 2D radiographs and has largely replaced conventional records in digital orthodontic records.
This document discusses cone-beam computed tomography (CBCT) and its applications in dental practice. CBCT provides sub-millimeter resolution images of the maxillofacial skeleton in a fraction of the time and radiation dose of conventional CT. It allows reconstruction of 3D volumetric data into multiplanar reformatted images. Specific applications discussed include implant planning, pathology assessment, temporomandibular joint imaging, and orthodontics. Advanced display modes like curved planar reformation and volume rendering provide familiar views useful for clinical evaluation and measurement.
View classification of medical x ray images using pnn classifier, decision tr...eSAT Journals
Abstract: In this era of electronic advancements in the field of medical image processing, the quantum of medical X-ray images so produced exorbitantly can be effectively addressed by means of automated indexing, comparing, analysing and annotating that will really be pivotal to the radiologists in interpreting and diagnosing the diseases. In order to envisage such an objective, it has been humbly endeavoured in this paper by proposing an efficient methodology that takes care of the view classification of the X-ray images for the automated annotation from their vast database, with which the decision making for the physicians and radiologists becomes simpler despite an immeasurable and ever-growing trends of the X-ray images. In this paper, X-ray images of six different classes namely chest, head, foot, palm, spine and neck have been collected. The framework proposed in this paper involves the following: The images are pre-processed using M3 filter and segmentation by Expectation Maximization (EM) algorithm, followed by feature extraction through Discrete Wavelet Transform. The orientation of X-ray images has been performed in this work by comparing among the Probabilistic Neural Network (PNN), Decision Tree algorithm and Support Vector Machine (SVM), while the PNN yields an accuracy of 75%, the Decision Tree with 92.77% and the SVM of 93.33%. Key Words: M3 filter, Expectation Maximaization, Discrete Wavelet Transformation, Probabilistic Neural Network, Decision Tree Algorithm and Support Vector Machine.
This document summarizes the growing use of engineering simulation in the biomedical industry for product development. Simulation is becoming integral to developing products ranging from prosthetics to surgical devices to medical equipment. Reasons for this include advancements in high-performance computing meeting demands of complex biomedical design, and the ability to import medical imaging scans into simulations. This enables virtual prototyping of devices to analyze issues like fluid flow and structural stresses prior to physical testing. The document provides examples of current applications of simulation in areas like aneurysm analysis, drug delivery, orthopedics, and cochlear implants. It predicts future use of simulation for personalized medicine through virtual surgery planning and automated design optimization.
IRJET - 3D Reconstruction and Modelling of a Brain MRI with TumourIRJET Journal
The document describes a process to 3D print a model of a brain with a tumour using MRI data. The key steps are:
1. Pre-processing the MRI data through filtering and enhancement to highlight the tumour region.
2. Reconstructing the pre-processed images into a 3D model and converting it to an .STL format for 3D printing.
3. 3D printing the model using stereolithography to create a physical replica of the patient's brain specifying the location, size and position of the tumour.
The goal is to create models for pre-surgery planning and simulation to help doctors choose the best surgical procedure.
This document discusses the various uses of computers in orthodontics. It begins with an introduction to computers and their advantages over manual work. It then describes several applications of computers in orthodontic practice, including administrative, clinical, and miscellaneous uses. Specific technologies discussed include computed tomography, digital radiography, 3D imaging, digital study models, computerized tooth width analysis, cephalometric analysis software, and programs for treatment planning and visualization like Invisalign. Overall, the document provides an overview of how computers are transforming various areas of orthodontic practice and care.
The document discusses the development of spatial mapping and referencing technologies for sub-surface imaging problems like retinal surgery. The goal is to create systems that can operate accurately in real-time to guide surgical tools and monitor procedures. A retinal testbed is being assembled to develop algorithms to mosaic curved retinal images, extract features for registration, and enable real-time spatial referencing between live surgery images and wide-area retinal maps. The methods being developed will then be generalized to other applications and a clinical prototype is planned within three years.
Similar to Wavelets in Medical Image Processing On Hip Arthroplasty and De-Noising, Segmentation (20)
This document provides a technical review of secure banking using RSA and AES encryption methodologies. It discusses how RSA and AES are commonly used encryption standards for secure data transmission between ATMs and bank servers. The document first provides background on ATM security measures and risks of attacks. It then reviews related work analyzing encryption techniques. The document proposes using a one-time password in addition to a PIN for ATM authentication. It concludes that implementing encryption standards like RSA and AES can make transactions more secure and build trust in online banking.
This document analyzes the performance of various modulation schemes for achieving energy efficient communication over fading channels in wireless sensor networks. It finds that for long transmission distances, low-order modulations like BPSK are optimal due to their lower SNR requirements. However, as transmission distance decreases, higher-order modulations like 16-QAM and 64-QAM become more optimal since they can transmit more bits per symbol, outweighing their higher SNR needs. Simulations show lifetime extensions up to 550% are possible in short-range networks by using higher-order modulations instead of just BPSK. The optimal modulation depends on transmission distance and balancing the energy used by electronic components versus power amplifiers.
This document provides a review of mobility management techniques in vehicular ad hoc networks (VANETs). It discusses three modes of communication in VANETs: vehicle-to-infrastructure (V2I), vehicle-to-vehicle (V2V), and hybrid vehicle (HV) communication. For each communication mode, different mobility management schemes are required due to their unique characteristics. The document also discusses mobility management challenges in VANETs and outlines some open research issues in improving mobility management for seamless communication in these dynamic networks.
This document provides a review of different techniques for segmenting brain MRI images to detect tumors. It compares the K-means and Fuzzy C-means clustering algorithms. K-means is an exclusive clustering algorithm that groups data points into distinct clusters, while Fuzzy C-means is an overlapping clustering algorithm that allows data points to belong to multiple clusters. The document finds that Fuzzy C-means requires more time for brain tumor detection compared to other methods like hierarchical clustering or K-means. It also reviews related work applying these clustering algorithms to segment brain MRI images.
1) The document simulates and compares the performance of AODV and DSDV routing protocols in a mobile ad hoc network under three conditions: when users are fixed, when users move towards the base station, and when users move away from the base station.
2) The results show that both protocols have higher packet delivery and lower packet loss when users are either fixed or moving towards the base station, since signal strength is better in those scenarios. Performance degrades when users move away from the base station due to weaker signals.
3) AODV generally has better performance than DSDV, with higher throughput and packet delivery rates observed across the different user mobility conditions.
This document describes the design and implementation of 4-bit QPSK and 256-bit QAM modulation techniques using MATLAB. It compares the two techniques based on SNR, BER, and efficiency. The key steps of implementing each technique in MATLAB are outlined, including generating random bits, modulation, adding noise, and measuring BER. Simulation results show scatter plots and eye diagrams of the modulated signals. A table compares the results, showing that 256-bit QAM provides better performance than 4-bit QPSK. The document concludes that QAM modulation is more effective for digital transmission systems.
The document proposes a hybrid technique using Anisotropic Scale Invariant Feature Transform (A-SIFT) and Robust Ensemble Support Vector Machine (RESVM) to accurately identify faces in images. A-SIFT improves upon traditional SIFT by applying anisotropic scaling to extract richer directional keypoints. Keypoints are processed with RESVM and hypothesis testing to increase accuracy above 95% by repeatedly reprocessing images until the threshold is met. The technique was tested on similar and different facial images and achieved better results than SIFT in retrieval time and reduced keypoints.
This document studies the effects of dielectric superstrate thickness on microstrip patch antenna parameters. Three types of probes-fed patch antennas (rectangular, circular, and square) were designed to operate at 2.4 GHz using Arlondiclad 880 substrate. The antennas were tested with and without an Arlondiclad 880 superstrate of varying thicknesses. It was found that adding a superstrate slightly degraded performance by lowering the resonant frequency and increasing return loss and VSWR, while decreasing bandwidth and gain. Specifically, increasing the superstrate thickness or dielectric constant resulted in greater changes to the antenna parameters.
This document describes a wireless environment monitoring system that utilizes soil energy as a sustainable power source for wireless sensors. The system uses a microbial fuel cell to generate electricity from the microbial activity in soil. Two microbial fuel cells were created using different soil types and various additives to produce different current and voltage outputs. An electronic circuit was designed on a printed circuit board with components like a microcontroller and ZigBee transceiver. Sensors for temperature and humidity were connected to the circuit to monitor the environment wirelessly. The system provides a low-cost way to power remote sensors without needing battery replacement and avoids the high costs of wiring a power source.
1) The document proposes a model for a frequency tunable inverted-F antenna that uses ferrite material.
2) The resonant frequency of the antenna can be significantly shifted from 2.41GHz to 3.15GHz, a 31% shift, by increasing the static magnetic field placed on the ferrite material.
3) Altering the permeability of the ferrite allows tuning of the antenna's resonant frequency without changing the physical dimensions, providing flexibility to operate over a wide frequency range.
This document summarizes a research paper that presents a speech enhancement method using stationary wavelet transform. The method first classifies speech into voiced, unvoiced, and silence regions based on short-time energy. It then applies different thresholding techniques to the wavelet coefficients of each region - modified hard thresholding for voiced speech, semi-soft thresholding for unvoiced speech, and setting coefficients to zero for silence. Experimental results using speech from the TIMIT database corrupted with white Gaussian noise at various SNR levels show improved performance over other popular denoising methods.
This document reviews the design of an energy-optimized wireless sensor node that encrypts data for transmission. It discusses how sensing schemes that group nodes into clusters and transmit aggregated data can reduce energy consumption compared to individual node transmissions. The proposed node design calculates the minimum transmission power needed based on received signal strength and uses a periodic sleep/wake cycle to optimize energy when not sensing or transmitting. It aims to encrypt data at both the node and network level to further optimize energy usage for wireless communication.
This document discusses group consumption modes. It analyzes factors that impact group consumption, including external environmental factors like technological developments enabling new forms of online and offline interactions, as well as internal motivational factors at both the group and individual level. The document then proposes that group consumption modes can be divided into four types based on two dimensions: vertical (group relationship intensity) and horizontal (consumption action period). These four types are instrument-oriented, information-oriented, enjoyment-oriented, and relationship-oriented consumption modes. Finally, the document notes that consumption modes are dynamic and can evolve over time.
The document summarizes a study of different microstrip patch antenna configurations with slotted ground planes. Three antenna designs were proposed and their performance evaluated through simulation: a conventional square patch, an elliptical patch, and a star-shaped patch. All antennas were mounted on an FR4 substrate. The effects of adding different slot patterns to the ground plane on resonance frequency, bandwidth, gain and efficiency were analyzed parametrically. Key findings were that reshaping the patch and adding slots increased bandwidth and shifted resonance frequency. The elliptical and star patches in particular performed better than the conventional design. Three antenna configurations were selected for fabrication and measurement based on the simulations: a conventional patch with a slot under the patch, an elliptical patch with slots
1) The document describes a study conducted to improve call drop rates in a GSM network through RF optimization.
2) Drive testing was performed before and after optimization using TEMS software to record network parameters like RxLevel, RxQuality, and events.
3) Analysis found call drops were occurring due to issues like handover failures between sectors, interference from adjacent channels, and overshooting due to antenna tilt.
4) Corrective actions taken included defining neighbors between sectors, adjusting frequencies to reduce interference, and lowering the mechanical tilt of an antenna.
5) Post-optimization drive testing showed improvements in RxLevel, RxQuality, and a reduction in dropped calls.
This document describes the design of an intelligent autonomous wheeled robot that uses RF transmission for communication. The robot has two modes - automatic mode where it can make its own decisions, and user control mode where a user can control it remotely. It is designed using a microcontroller and can perform tasks like object recognition using computer vision and color detection in MATLAB, as well as wall painting using pneumatic systems. The robot's movement is controlled by DC motors and it uses sensors like ultrasonic sensors and gas sensors to navigate autonomously. RF transmission allows communication between the robot and a remote control unit. The overall aim is to develop a low-cost robotic system for industrial applications like material handling.
This document reviews cryptography techniques to secure the Ad-hoc On-Demand Distance Vector (AODV) routing protocol in mobile ad-hoc networks. It discusses various types of attacks on AODV like impersonation, denial of service, eavesdropping, black hole attacks, wormhole attacks, and Sybil attacks. It then proposes using the RC6 cryptography algorithm to secure AODV by encrypting data packets and detecting and removing malicious nodes launching black hole attacks. Simulation results show that after applying RC6, the packet delivery ratio and throughput of AODV increase while delay decreases, improving the security and performance of the network under attack.
The document describes a proposed modification to the conventional Booth multiplier that aims to increase its speed by applying concepts from Vedic mathematics. Specifically, it utilizes the Urdhva Tiryakbhyam formula to generate all partial products concurrently rather than sequentially. The proposed 8x8 bit multiplier was coded in VHDL, simulated, and found to have a path delay 44.35% lower than a conventional Booth multiplier, demonstrating its potential for higher speed.
This document discusses image deblurring techniques. It begins by introducing image restoration and focusing on image deblurring. It then discusses challenges with image deblurring being an ill-posed problem. It reviews existing approaches to screen image deconvolution including estimating point spread functions and iteratively estimating blur kernels and sharp images. The document also discusses handling spatially variant blur and summarizes the relationship between the proposed method and previous work for different blur types. It proposes using color filters in the aperture to exploit parallax cues for segmentation and blur estimation. Finally, it proposes moving the image sensor circularly during exposure to prevent high frequency attenuation from motion blur.
This document describes modeling an adaptive controller for an aircraft roll control system using PID, fuzzy-PID, and genetic algorithm. It begins by introducing the aircraft roll control system and motivation for developing an adaptive controller to minimize errors from noisy analog sensor signals. It then provides the mathematical model of aircraft roll dynamics and describes modeling the real-time flight control system in MATLAB/Simulink. The document evaluates PID, fuzzy-PID, and PID-GA (genetic algorithm) controllers for aircraft roll control and finds that the PID-GA controller delivers the best performance.
Understanding Inductive Bias in Machine LearningSUTEJAS
This presentation explores the concept of inductive bias in machine learning. It explains how algorithms come with built-in assumptions and preferences that guide the learning process. You'll learn about the different types of inductive bias and how they can impact the performance and generalizability of machine learning models.
The presentation also covers the positive and negative aspects of inductive bias, along with strategies for mitigating potential drawbacks. We'll explore examples of how bias manifests in algorithms like neural networks and decision trees.
By understanding inductive bias, you can gain valuable insights into how machine learning models work and make informed decisions when building and deploying them.
DEEP LEARNING FOR SMART GRID INTRUSION DETECTION: A HYBRID CNN-LSTM-BASED MODELgerogepatton
As digital technology becomes more deeply embedded in power systems, protecting the communication
networks of Smart Grids (SG) has emerged as a critical concern. Distributed Network Protocol 3 (DNP3)
represents a multi-tiered application layer protocol extensively utilized in Supervisory Control and Data
Acquisition (SCADA)-based smart grids to facilitate real-time data gathering and control functionalities.
Robust Intrusion Detection Systems (IDS) are necessary for early threat detection and mitigation because
of the interconnection of these networks, which makes them vulnerable to a variety of cyberattacks. To
solve this issue, this paper develops a hybrid Deep Learning (DL) model specifically designed for intrusion
detection in smart grids. The proposed approach is a combination of the Convolutional Neural Network
(CNN) and the Long-Short-Term Memory algorithms (LSTM). We employed a recent intrusion detection
dataset (DNP3), which focuses on unauthorized commands and Denial of Service (DoS) cyberattacks, to
train and test our model. The results of our experiments show that our CNN-LSTM method is much better
at finding smart grid intrusions than other deep learning algorithms used for classification. In addition,
our proposed approach improves accuracy, precision, recall, and F1 score, achieving a high detection
accuracy rate of 99.50%.
Advanced control scheme of doubly fed induction generator for wind turbine us...IJECEIAES
This paper describes a speed control device for generating electrical energy on an electricity network based on the doubly fed induction generator (DFIG) used for wind power conversion systems. At first, a double-fed induction generator model was constructed. A control law is formulated to govern the flow of energy between the stator of a DFIG and the energy network using three types of controllers: proportional integral (PI), sliding mode controller (SMC) and second order sliding mode controller (SOSMC). Their different results in terms of power reference tracking, reaction to unexpected speed fluctuations, sensitivity to perturbations, and resilience against machine parameter alterations are compared. MATLAB/Simulink was used to conduct the simulations for the preceding study. Multiple simulations have shown very satisfying results, and the investigations demonstrate the efficacy and power-enhancing capabilities of the suggested control system.
We have compiled the most important slides from each speaker's presentation. This year’s compilation, available for free, captures the key insights and contributions shared during the DfMAy 2024 conference.
Using recycled concrete aggregates (RCA) for pavements is crucial to achieving sustainability. Implementing RCA for new pavement can minimize carbon footprint, conserve natural resources, reduce harmful emissions, and lower life cycle costs. Compared to natural aggregate (NA), RCA pavement has fewer comprehensive studies and sustainability assessments.
KuberTENes Birthday Bash Guadalajara - K8sGPT first impressionsVictor Morales
K8sGPT is a tool that analyzes and diagnoses Kubernetes clusters. This presentation was used to share the requirements and dependencies to deploy K8sGPT in a local environment.
ACEP Magazine edition 4th launched on 05.06.2024Rahul
This document provides information about the third edition of the magazine "Sthapatya" published by the Association of Civil Engineers (Practicing) Aurangabad. It includes messages from current and past presidents of ACEP, memories and photos from past ACEP events, information on life time achievement awards given by ACEP, and a technical article on concrete maintenance, repairs and strengthening. The document highlights activities of ACEP and provides a technical educational article for members.
Wavelets in Medical Image Processing On Hip Arthroplasty and De-Noising, Segmentation
1. IOSR Journal of Computer Engineering (IOSR-JCE)
e-ISSN: 2278-0661, p- ISSN: 2278-8727Volume 12, Issue 6 (Jul. - Aug. 2013), PP 20-31
www.iosrjournals.org
www.iosrjournals.org 20 | Page
Wavelets in Medical Image Processing On Hip Arthroplasty and
De-Noising, Segmentation
Himadri Nath Moulick1
, Moumita Ghosh2
1
CSE, Aryabhatta Institute of Engg & Management, Durgapur, PIN-713148, India
2
CSE,University Institute Of Technology,(The University Of Burdwan) Pin -712104,India
Abstract: Computers have become indispensable in all domains, and the medical segment does not represent
an exception. The need for accuracy and speed has led to a tight collaboration between machines and human
beings. Maybe the future will allow the existence of a world where the human intervention won’t be necessary,
but for now,the best approach in the medical field is to create semiautomatic applications, in order to help the
doctors with the diagnoses, with following the patients’ evolution and managing them and with other medical
activities. Our application is designed for automatic measurements of orthopedic parameters, and allows the
possibility of human intervention in case the parameters have not been detected properly. The segment of the
application is Hip Arthroplasty. And Wavelet transforms and other multi-scale analysis functions have been
used for compact signal and image representations in de-noising, compression and feature detection processing
problems for about twenty years. Numerous research works have proven that space-frequency and space-scale
expansions with this family of analysis functions provided a very efficient framework for signal or image data.
The wavelet transform itself offers great design flexibility. Basis selection, spatial-frequency tiling, and various
wavelet threshold strategies can be optimized for best adaptation to a processing application, data
characteristics and feature of interest. Fast implementation of wavelet transforms using a filter-bank framework
enable real time processing capability. Instead of trying to replace standard image processing techniques,
wavelet transforms offer an efficient representation of the signal, finely tuned to its intrinsic properties. By
combining such representations with simple processing techniques in the transform domain, multi-scale
analysis can accomplish remarkable performance and efficiency for many image processing problems. Multi-
scale analysis has been found particularly successful for image de-noising and enhancement problems given
that a suitable separation of signal and noise can be achieved in the transform domain (i.e. after projection of
an observation signal) based on their distinct localization and distribution in the spatial-frequency domain.
With better correlation of significant features, wavelets were also proven to be very useful for detection
{jin_Mallat_1992a} and matching applications {jin_Strickland_1995}.
Key-Words - Hip Arthroplasty, Canny Edge Detection, DICOM, Hough Transform, Radiographic Image
Processing De-noising, Segmentation
I. Introduction
Medical image processing is an area of increasing interest. It includes a wide range of methods and
techniques, starting with the acquisition of images using specialized devices (for example, CT devices), image
enhancement and analysis, to 3D model reconstruction from 2D images. Thus, the research in this field
represents a point of interest for both doctors and engineers, in their attempt to improve medical techniques,
with computer assistance, in order to obtain more accurate results in treating the patients. Among many research
projects in this area of interest some of the most relevant are: The SCANIP [11] image processing software that
provides a broad range of image visualization, processing and segmentation tools for medical purposes. This
software has been created by Simpleware in Great Britain. The SCANIP programs ensure the conversion of 3D
medical images into quality meshes. These meshes can be used in future processing in analysis programs, in
fluid dynamics, CAD and the creation of Rapid Prototyping models. The sources for these programs come from
MRIs, CTs or MicroCTs. The 3D-DOCTOR Project [12] that comes with an advanced 3d modeling software,
with strong processing and measurement functions for MRI-s, CT-s, PET-s, and other types of medical images.
The possible applications of this software are in the scientific and medical domain, but also in the image
processing industrial field. The functioning principle of this software is based on edge detection techniques
using 3D image segmentation functions and on the construction of 3D surfaces and volumes, that are afterwards
visualized and measured for the purpose of a quantitative and qualitative analysis. - The Hip-OpCT software
[13] that allows importing CT images in DICOM format. Once imported, the CT dataset is visualized through
several modalities from which the doctors can plan the size and the position of the prosthesis. Wavelets have
been widely used in signal and image processing for the past 20 years. Although a milestone paper by
Grossmann and Morlet {jin_Grossman_1984} was considered as the beginning point of modern wavelet
analysis, similar ideas and theoretical bases can be found back in early 20
th
century {jin_Haar_1910}. Following
2. Wavelets in Medical Image Processing On Hip Arthroplasty and De-Noising, Segmentation
www.iosrjournals.org 21 | Page
two important papers in late 1980s by S. Mallat {jin_Mallat_1989} and I. Daubechies {jin_Daubechies_1988},
more than 9,000 journal papers and 200 books related to wavelets have been published {jin_Unser_2003a}.
Wavelets were first introduced to medical imaging research in 1991 in a journal paper describing the
application of wavelet transforms for noise reduction in MRI images. {jin_Weaver_1991}. Ever since, wavelet
transforms have been successfully applied to many topics including tomographic reconstruction, image
compression, noised reduction, image enhancement, texture analysis/segmentation and multi-scale registration.
Two review papers in 1996 {jin_Unser_1996} and 2000 {jin_Laine_2000} provide a summary and overview of
research works related to wavelets in medical image processing from the past few years. Many related works
can also be found in the book edited by A. Aldroubi and M. Unser {jin_Aldroubi_1996}. More currently, a
special issue of IEEE Transactions on Medical Imaging {jin_Unser_2003a} provides a large collection of most
recent research works using wavelets in medical image processing. The purpose of this chapter is to summarize
the usefulness of wavelets in various problems of medical imaging. The chapter is organized as follows. Section
2 overviews the theoretical fundamentals of wavelet theory and related multi-scale representations. As an
example, the implementation of an over-complete dyadic wavelet transform will be illustrated. Section 3
includes a general introduction of image de-noising and enhancement techniques using wavelet analysis. Section
4 and 5 will summarize the basic principles and research works in literature for wavelet analysis applied to
image segmentation and registration.
II. Arthroplasty- General Presentation
Arthroplasty [10] represents a surgical procedure in which the arthritic or dysfunctional joint surface is
replaced with prosthesis or by remodeling or realigning the joint. The important joint for this article is the one
located at hip area. This is the reason why the article details the parameters that belong to the thigh-bone and the
pelvis. Fig.1 presents the most important parameters in Hip Arthroplasty, extracted from an anterior-posterior
radiography. Fig.2 presents the parameters extracted from an anterior-lateral radiography representing the hip
after the insertion of the prosthesis. For the scope of this article, three areas of the thighboneare analyzed: the
femoral head (the nearest part to the pelvis), the femoral neck, and the femoral shaft or body (the longest part of
the thigh-bone).
Fig.1. Parameters important in Hip Replacement, extracted from an anterior-posterior radiography
The parameters of interest for the Hip Replacement [7] are listed below:
1) the superior margin of the acetabulum (the superior point in which the thigh-bone meetsthe pelvis). 2) the
inferior margin of the acetabulum (the inferior point in which the thigh-bone (thefemoral head) meets the
pelvis).3) the femoral head axis or the acetabulum axis (the line determined by the two points that represent
the superior margin and the inferior margin of the acetabulum). 4) the angle created by the acetabulum axis
with the vertical line. This angle has to be the same for both of the femoral bones. 5) the lesser trochanter
(located in the upper left part of the femoral body). 6) the greater trochanter (located in the upper right part
of the femoral body). 7) the tangent to the superior cortical of the femoral neck 8) the tangent to the inferior
cortical of the femoral neck 9) the femoral neck axis (the axis of the cylinder determined by the tangents 7
and 8) 10) the femoral body axis or the diaphyseal axis (the axis of the cylinder that approximates the
femoral body) 11) the most important parameter, extracted from the x-ray before the surgical intervention is
represented by the cervicodiaphyseal angle (the angle determined by the neck axis and the diaphyseal axis).
Depending on the value of this angle, it can be determined whether the patient needs or not a prosthesis. If
the angle has values between 125 and 135 degrees, the thigh-bone is considered to be in normal ranges. 12)
the right ischiadic tuberosity (the lowest right part of the pelvic bone). 13) the left ischiadic tuberosity (the
lowest left part of the pelvic bone).14) the ischiadic line or the horizontal reference line (the line determined
by the two ischiadic tuberosities). 15) the vertical reference line, that is perpendicular on the ischiadic line,
3. Wavelets in Medical Image Processing On Hip Arthroplasty and De-Noising, Segmentation
www.iosrjournals.org 22 | Page
in its middle. 16) the line starting from the center of the lesser left trochanter, parallel to the ischiadic line
17) the line starting from the center of the right lesser trochanter, parallel to the ischiadic line; the distance
between lines 16 and 17 represents the vertical distance between the two thigh-bones. If this distance is
greater than a chosen threshold, there is an indication of a difference between the lengths of the two femoral
bones that has to be resolved surgically (in most cases). After inserting the prosthesis, some new parameters
must be taken into consideration: 18) the diaphyseal axis of the femoral bone (the same as parameter 10).
19) the diaphyseal axis of the prosthesis or the axis of the prosthesis‟ body (the axis of the cylinder that
approximates the prosthesis‟ body). 20) The deviation of the prosthesis (the angle determined by lines 18
and 19). This parameter will be computed in several radiographic images, following the evolution of the
same patient. The important parameters extracted from an anteriorlateral radiography, after inserting the
prosthesis, are shown in Fig.2:
Fig.2. Parameters important in Hip Replacement, extracted from an anterior-lateral radiography, after the
insertion of the prosthesis
21) The axis of the prosthesis‟ neck 22) The axis of the prosthesis‟ body 23) The anteversion angle (the
angle determined by the axes 21 and 22). If this angle has its value situated between 5 and 10 degrees, it‟s
considered to be in normal ranges.
1.The DICOM Standard
In order to manage and interpret the x-rays data in a simple and organized manner, a standard for the x-
ray files is needed. This is the reason why the most popular standard for medical images was chosen: DICOM
[14]. The Digital Imaging and Communications in Medicine (DICOM) standard is a detailed specification of the
coding and transfer of medical images and their associated information.
2. Representing Data in the DICOM Format
The clinical data are represented in a variety of formats: the distances are measured in millimeters, the
time in seconds, etc. The PS 3.5 part of the standard, entitled Data Structure and Their Encoding, defines 27
types of standard data, known as “value representations” (VR), that include all types of data that can appear in
the medical domain. Any information encoded in a DICOM file has to belong to one of these predefined types.
Some of the most important standard data are: Person Name (PN), Date Time (DT), and Age String
(AS). A DICOM file has the following structure: - A preamble of 128 bytes - A prefix (4 bytes) for retaining the
letters „D‟, „I‟, „C‟, „M‟ (the signature of a DICOM file) - A data set that contains information like: patient‟s
name, image type, image dimension, etc. - Pixels that form the image (or the images) contained in the file.
3. Extracting Data from DICOM Files
Extracting data from a DICOM file can be made using the tags defined in the DICOM dictionary.
Every tag is searched in the file, and, if found, is interpreted. The steps in extracting the information are: -
Checking the existence of the characters „D‟, „I‟, „C‟, „M‟ - Determining of the VR type - Setting the order of
the bytes (Big Endian or Little Endian) - Searching for a tag in the DICOM file, corresponding to the order of
bytes and the VR type - Extracting the values corresponding to that tag Some characteristics of the DICOM
files, important when extracting data, are: - the number of images contained in the DICOM file - the number of
bits per pixel: 8, 12, 16, 24 - the compression - the photometric interpretation: shades of gray or color images In
case of images without compression, the extraction of the images is made pixel by pixel, according to the
number of bits per pixel. For images with compression, a decompression step should be previously performed.
4. Wavelets in Medical Image Processing On Hip Arthroplasty and De-Noising, Segmentation
www.iosrjournals.org 23 | Page
4. The Structure of the CR DICOM files
Computer radiographic images (CR) stored in DICOM files are accompanied by general identification
elements and some specific information. For example, the Patient module contains: the name of the patient, the
patient‟s ID, the patient‟s date of birth, etc. Another module, specific for CR, CR Series, contains information
about the examined body part, the view position, etc. Our application extracts from every module the important
elements for managing and interpreting the patient‟s data.
III. Wavelet Transform And Multi-Scale Analysis
One of the most fundamental problems in signal processing is to find a suitable representation of the
data that will facilitate an analysis procedure. One way to achieve this goal is to use transformation, or
decomposition of the signal on a set of basis functions prior to processing in the transform domain. Transform
theory has played a key role in image processing for a number of years, and it continues to be a topic of interest
in theoretical as well as applied work in this field. Image transforms are used widely in many image processing
fields, including image enhancement, restoration, encoding, and description {jin_Jain_1989}. Historically, the
Fourier transform has dominated linear time-invariant signal processing. The associated basis functions are
complex sinusoidal waves that correspond to the eigenvectors of a linear time-invariant operator. A
signal defined in the temporal domain and its Fourier transform defined in the frequency
domain, have the following relationships {jin_Jain_1989; jin_Papoulis_1987}:
(1)
(2)
Fourier transform characterizes a signal via its frequency components. Since the support of the bases
function covers the whole temporal domain (i.e infinite support), depends on the values of
for all times. This makes the Fourier transform a global transform that cannot analyze local or transient
properties of the original signal In order to capture frequency evolution of a non-static signal, the basis
functions should have compact support in both time and frequency domain. To achieve this goal, a windowed
Fourier transform (WFT) was first introduced with the use of a window function w(t) into the Fourier transform
{jin_Mallat_1998}:
(3)
The energy of the basis function is concentrated in the neighborhood of time
over an interval of size measured by the standard deviation of Its Fourier transform is
with energy in frequency domain localized around
over an interval of size In a time-frequency plane the energy spread of what is called the
atom is represented by the Heisenberg rectangle with time width and frequency width
The
uncertainty principle states that the energy spread of a function and its Fourier transform cannot be
simultaneously arbitrarily small, verifying:
(4)
Shape and size of Heisenberg rectangles of a windowed Fourier transform therefore determine the spatial and
frequency resolution offered by such transform. Examples of spatial-frequency tiling with Heisenberg rectangles
are shown in Fig 3. Notice that for a windowed Fourier transform, the shape of the time-frequency boxes are
5. Wavelets in Medical Image Processing On Hip Arthroplasty and De-Noising, Segmentation
www.iosrjournals.org 24 | Page
identical across the whole time-frequency plane, which means that the analysis resolution of a windowed
Fourier transform remains the same across all frequency and spatial locations.
Fig .3. Example of spatial-frequency tiling of various transformations. x-axis: spatial resolution. y-axis:
frequency resolution. (a) discrete sampling (no frequency localization ). (b) Fourier transform (no temporal
localization). (c) windowed Fourier transform (constant Heisenberg boxes). (d) wavelet transform (variable
Heisenberg boxes).
To analyze transient signal structures of various supports and amplitudes in time, it is necessary to use
time-frequency atoms with different support sizes for different temporal locations. For example, in the case of
high frequency structures, which vary rapidly in time, we need higher temporal resolution to accurately trace the
trajectory of the changes; on the other hand, for lower frequency, we will need a relatively higher absolute
frequency resolution to give a better measurement on the value of frequency. We will show in the next section
that wavelet transform provide a natural representation which satisfies these requirements, as illustrated in Fig. 3
(d).
1. Noise Reduction and Image Enhancement Using Wavelet Transforms
De-noising can be viewed as an estimation problem trying to recover a true signal component X from
an observation Y where the signal component has been degraded by a noise component N:
(5)
The estimation is computed with a thresholding estimator in an orthonormal basis as
{jin_Donoho_1994b}:
(6)
where is a thresholding function that aims at eliminating noise components (via attenuating of
decreasing some coefficient sets) in the transform domain while preserving the true signal coefficients. If the
function is modified to rather preserve or increase coefficient values in the transform domain, it is
possible to enhance some features of interest in the true signal component with the framework of Equation (6).
Fig. 4 illustrates a multi-scale enhancement and de-noising framework using wavelet transforms. An over-
complete dyadic wavelet transform using bi-orthogonal basis is used. Notice that since the DC-cap contains the
overall energy distribution, it is usually kept untouched during the procedure. As shown in this figure,
thresholding and enhancement functions can be implemented independently from the wavelet filters and easily
incorporated into the filter bank framework.
Fig .4. A Multi-scale framework of de-noising and enhancement using discrete dyadic wavelet transform. A
three level decomposition was shown.
2.Thresholding operators for de-noising
As a general rule, wavelet coefficients with larger magnitude are correlated with salient features in the
image data. In that context, de-noising can be achieved by applying a thresholding operator to the wavelet
6. Wavelets in Medical Image Processing On Hip Arthroplasty and De-Noising, Segmentation
www.iosrjournals.org 25 | Page
coefficients (in the transform domain) followed by reconstruction of the signal to the original image (spatial)
domain.
Typical threshold operators for de-noising include hard thresholding
(7)
soft thresholding (wavelet shrinkage) {jin_Donoho_1995b}:
(8)
and affine(firm) thresholding{jin_Gao_1997}:
(9)
The shapes of these thresholding operators are illustrated in Fig 5.
Fig .5. Example of thresholding functions, assuming that the input data was normalized to the range of [-1,1]. (a)
Hard thresholding. (b) Soft thresholding. (c) Affine thresholding. The threshold level was set to T=0.5;
3.Image Segmentation Using Wavelets
3.1 Multi-scale Texture Classification and Segmentation
Texture is an important characteristic for analyzing many types of images, including natural scenes and
medical images. With the unique property of spatial-frequency localization, wavelet functions provide an ideal
representation for texture analysis. Experimental evidence on human and mammalian vision support the notion
of spatial-frequency analysis that maximizes a simultaneous localization of energy in both spatial and frequency
domain {jin_Beck_1987; jin_Julez_1981; jin_Watson_1983}. These psychophysical and physiological findings
lead to several research works on texture-based segmentation methods based on multi-scale analysis. Gabor
transform, as suggested by the uncertainty principle, provides an optimal joint resolution in the space-frequency
domain. Many early works utilized Gabor transforms for texture characteristics. In {jin_Daugman_1988} an
example is given on the use of Gabor coefficient spectral signatures {jin_Daugman_1985} to separate distinct
textural regions characterized by different orientations and predominant anisotropic texture moments. Porat and
Zeevi proposed in {jin_Porat_1989} six features derived from Gabor coefficients to characterize a local texture
component in an image: the dominant localized frequency; the second moment (variance) of the localized
frequency; center of gravity; variance of local orientation; local mean intensity; and variance of the intensity
level. A simple minimum-distance classifier was used to classify individual textured regions within a single
image using these features. Many wavelet-based texture segmentation methods had been investigated thereafter.
Most of these methods follow a three-step procedure: multi-scale expansion, feature characterization, and
classification. As such, they are usually different from each other from these aspects. Various multi-scale
representations have been used for texture analysis. Unser {jin_Unser_1995a} used a redundant wavelet frame.
Laine and Fan {jin_Laine_1993} investigated a wavelet packets representation and extended their
research to a redundant wavelet packets frame with Lemarié-Battle filters in {jin_Laine_1996a}. Modulated
wavelets were used in {jin_Hsin_1998} for better orientation adaptivity. To further extend the flexibility of the
spatial-frequency analysis, a multi-wavelet packets, combining multiple wavelet basis functions at different
expansion levels was used in {jin_Wang_2002}. An M-band wavelet expansion, which differs from a dyadic
wavelet transform in the fact that each expansion level contains M channels of analysis was used in
{jin_Acharyya_2002} to improve orientation selectivity. Quality and accuracy of segmentation ultimately
depends on the selection of the characterizing features. A simple feature selection can use the amplitude of the
wavelet coefficients {jin_Hsin_1998}. Many multi-scale texture segmentation methods construct the feature
7. Wavelets in Medical Image Processing On Hip Arthroplasty and De-Noising, Segmentation
www.iosrjournals.org 26 | Page
vector from various local statistics of the wavelet coefficients, such as its local variance {jin_Unser_1995a;
jin_Wang_2001}, moments {jin_Etemad_1997} or energy signature {jin_Acharyya_2002; jin_Laine_1993;
jin_Porter_1996}. Wavelet extrema density (WED), defined as the number of extrema of wavelet coefficients
per unit area, was used in {jin_Wang_2002}. In {jin_Laine_1996a}, a 1-D envelope detection was first applied
to the wavelet packets coefficients according to their orientation, and a feature vector was constructed as the
collection of envelope values for each spatial-frequency component. More sophisticated statistical analysis
involving Bayesian analysis and Markov random fields were also used to estimate local and long-range
correlations {jin_Choi_2001; jin_Zhang_1998}. For other examples of multi-scale textural features, test
and histogram testing were used in {jin_Li_2000}, “Roughness” based on fractal dimension measurement was
used in {jin_Charalampidis_2002}. Texture-based segmentation is usually achieved by texture classification.
Classic classifiers such as the minimum distance classifier {jin_Porat_1989}, are easier to implement when the
dimension of the feature vector is small and the groups of samples are well segregated. The most popular
classification procedures reported in the literature are the K-mean classifier {jin_Acharyya_2002;
jin_Charalampidis_2002; jin_Hsin_1998; jin_Laine_1996a; jin_Porter_1996; jin_Unser_1995a;
jin_Wang_2001} and the neural networks classifiers {jin_Daugman_1988; jin_Etemad_1997; jin_Laine_1993;
jin_Zhang_1998}.
Fig .6. Sample results using multi-scale texture segmentation. (a) Synthetic texture image. (b): segmentation
result for image (a) with a 2-class labeling. (c) MRI T1 image of a human brain. (d) segmentation result for
image (c) with a 4-class labeling.
As an example, we illustrate in Fig. 6 a texture-based segmentation method on both a synthetic texture
image and a medical image from a brain MRI data set. The algorithm used for this example from
{jin_Laine_1996a} uses the combination of wavelet packets frame with Lemarié-Battle filters, multi-scale
envelope features, and a K-mean classifier.
4. Wavelet Edge Detection and Segmentation
Edge detection plays important role in image segmentation. In many cases, boundary delineation is the
ultimate goal for an image segmentation and a good edge detector itself can then fulfill the requirement of
segmentation. On the other hand, many segmentation techniques require an estimation of object edges for their
intialization. For example, with standard gradient-based deformable models, an edge map is used to determine
where the deforming interface must stop. In this case, the final result of the segmentation method depends
heavily on the accuracy and completeness of the initial edge map. Although many research works have made
some efforts to eliminate this type of inter-dependency by introducing non-edge constraints {jin_Chan_2001;
jin_Yezzi_1999}, it is necessary and equally important to improve the edge estimation process itself. As
pointed out by the pioneer work of Mallat and Zhong {jin_Mallat_1992b}, first or second derivative based
wavelet functions can be used for multi-scale edge detection. Most multi-scale edge detectors smooth the input
signal at various scales and detect sharp variation locations (edges) from their first or second derivatives. Edge
locations are related to the extrema of the first derivative of the signal and the zero crossings of the second
derivative of the signal. In {jin_Mallat_1992b}, it was also pointed out that first derivative wavelet functions are
more appropriate for edge detection since the magnitude of wavelet modulus represents the relative “strength”
of the edges, and therefore enable to differentiate meaningful edges from small fluctuations caused by noise.
Using the first derivative of a smooth function as the mother wavelet of a multi scale
expansion results in a representation where the two components of wavelet coefficients at a certain scale s are
8. Wavelets in Medical Image Processing On Hip Arthroplasty and De-Noising, Segmentation
www.iosrjournals.org 27 | Page
related to the gradient vector of the input image smoothed by a dilated version of at
scale s.
(10)
The direction of the gradient vector at a point (x,y) indicates the direction in the image plane along
which the directional derivative of f(x,y) has the largest absolute value. Edge points (local maxima) can be
detected as points 00(,)xysuch that the modulus of the gradient vector is maximum in the direction towards
which the gradient vector points in the image plane. Such computation is closely related to a Canny edge
detector {jin_Canny_1986}. Extension to higher dimension is quite straightforward. Fig. 7 provides an example
of a multi-scale edge detection method based on a first derivative wavelet function. To further improve the
robustness of such multi-scale edge detector, Mallat and Zhong {jin_Mallat_1992b} also investigated the
relations between singularity (Lipschitz regularity) and the propagation of multi-scale edges across wavelet
scales. In {jin_Aydin_1996}, the dyadic expansion was extended to an M-band expansion to increase directional
selectivity. Also, continuous scale representation was used for better adaptation to object sizes
{jin_Laine_1997}. Continuity constraints were applied to fully recover a reliable boundary delineation from 2D
and 3D cardiac ultrasound in {jin_Laine_1996b} and {jin_Koren_1994}. In {jin_Dima_2002}, both cross-scale
edge correlations and spatial continuity were investigated to improve the edge detection in the presence of noise.
Wilson et al. in {jin_Wilson_1992} also suggested that a multi-resolution Markov model can be used
to track boundary curves of objects from a multi-scale expansion using a generalized wavelet transform.
Fig.7. Example of a multi-scale edge detection method finding local maxima of wavelet modulus, with a first-
derivative wavelet function. (a) Input image, (b)~(e): Multi-scale edge map at expansion scale 1 to 4.
Given their robustness and natural representation as boundary information within a multi-resolution
representation, multi-scale edges have been used in deformable model methods to provide a more reliable
constraint on the model deformation {jin_de Rivaz_2000; jin_Sun_2003; jin_Wu_2000; jin_Yoshida_1997}, as
an alternative to traditional gradient based edge map. In {jin_Neves_2003}, it was used as a pre-segmentation
step in order to find the markers that are used by watershed transform.
IV. Radiographic Image Processing
As in any image analysis application, the first step is a preprocessing step, needed to improve the image
by noise removal, contrast improvement, edge enhancement and others [4]. In our application, this step is
followed by a contour extraction step, which helps in the arthroplasty parameters‟ extraction.
1. Image Enhancement
One reason why the automatic interpretation of radiographic images doesn‟t give accurate results is the
fact that the radiographic images are blurred. This is why enhancing images before applying contour detection
algorithms is a step that should not be omitted. In the case of our application, the radiographic images are
enhanced by noise removal, edge enhancement and contrast improvement. We will detail each method in the
following subsections.
9. Wavelets in Medical Image Processing On Hip Arthroplasty and De-Noising, Segmentation
www.iosrjournals.org 28 | Page
2. Noise Removal
A series of methods have been tested in order to choose the best way for noise removal.The first
approach was that of using Gaussian filtering, that led to good results. Another interesting approach would be
Impulsive Noise removal [15]. The classic linear unsharp masking is an important scheme in feature based
image enhancement category, in which a high pass filter scaled version of the original image is added to itself,
in order to give more emphasis on the high frequency components. There is a very big possibility that the noise
will be amplified along with the detail features of the image. Thus, the main objective of this approach is to
separate the noisy and the noise-free images based on a certain threshold. The creators of the method propose
the use of a CV (coefficient of variance) based adaptive threshold technique for impulsive noise detection. The
main idea is to train a functional link artificial neural network (FLANN) [16] with a single statistical parameter
CV as input. The third approach meant for image enhancement is Image Noise removal using Graph Theory
Concepts [17]. This method first creates an image graph, based on the original image. There are many possible
mappings, but the most intuitive approach is to map each pixel in the image onto a vertex of the graph. This
graph will be four-way connected, so that each vertex corresponds to a pixel, and each edge has an associated
weight that corresponds to the distance between the color levels of the adjacent vertices. This technique has
been tested for impulse noise and for random noise, leading to the conclusion that the proposed method displays
good edge and detail preservation, while suppressing impulse and random noise. The chosen method for noise
removal was Gaussian Filtering, because of the need for speed in this preprocessing phase.
3.Edge Enhancement
The first method used for edge enhancement was Adaptive Smoothing. This represents a filter that
enhances edges, being applied like a matrix filter. The main difference between adaptive smoothing and matrix
filter is the fact that the first does not apply weights over the pixel‟s neighborhood in order to compute its new
intensity or color, but uses a gradient. The output obtained by using this gradient consists of both positive and
negative intensities, but also emphasized high frequency details. Another method for edge enhancement was the
curvelet transform [18]. Curvelet coefficient can be modified in order to enhance edges in an image by y(x)
(Velde function). We have chosen the first method because it was faster.
4. Contrast Improvement
The method tried for contrast improvement was histogram equalization that usually increases the global
contrast of images, especially when the usable data of images is represented by close contrast values. Peaks in
the image histogram (that indicate commonly used grey levels) are widened, while valleys are compressed.
5. Contour Extraction
Most of the contour extraction algorithms which are based on edge detection follow these steps:
- detecting the edge pixels (pixels where the intensity changes abruptly) - eliminating the edge pixels which are
not also contour pixels - connecting the contour pixels using local methods (based on the pixels‟ relations to
their neighbor pixels) or global methods (based on global information, for example the shape of a bone, in a
computer radiography). After trying a series of methods, the Canny algorithm [5] has been chosen in order to
extract the contour lines, because this produced the best results. The Canny algorithm will be briefly described
in the following lines. The Canny edge detection algorithm is a very well known algorithm and is considered by
many the optimal edge detector. The algorithm is structured into 6 steps: 1) filter out any noise in the original
image with the Gaussian filter 2) apply the Sobel operator on the resulting image, estimating the gradient in the
horizontal direction (Gx) and in the vertical direction (Gy). The magnitude, or the edge strength is approximated
by the sum between Gx and Gy
3) find the edge direction , as the arctangent of Gy/Gx. 4) Once the direction is known, relate the edge
direction to a discretized direction (all the angles between 67.5 and 112.5 will be considered to be of 90 degrees,
all angles between 112.5 and 157.5 are set to 135 degrees, etc). Fig.8 shows the possible discretized edge
directions, previously determined in step 3.
10. Wavelets in Medical Image Processing On Hip Arthroplasty and De-Noising, Segmentation
www.iosrjournals.org 29 | Page
Fig. 8. Gradient direction
5) Non-maximum suppression (trace along the edge in the edge direction and suppress any pixel that is
not considered to be an edge - that is not a local maximum) 6) Hysteresis for eliminating streaking, using two
thresholds, T1 (high) and T2 (low). Any pixel with a value greater than T1 is considered to be an edge pixel.
After applying the first threshold, any pixels connected to the edge pixels that have a value greater than
T2 will also be selected as edge pixels. Usually T1=2*T2. The result of applying the Canny detector is a binary
image (Fig. 9), where white pixels represent contour pixels. Having the contour lines of the bones, the next step
in our application is the extraction of the important parameters in hip arthroplasty (automatic and semiautomatic
extraction). We can observe in Fig. 4 that the contour is disconnected in some parts of the radiography, and that
it cannot be reconstructed with accuracy. That is why we propose to search for some salient parameters (for
example the lines representing the contour of the femoral body) that can be identified without the previous
reconstruction of the entire pelvic and femoral contour. In the following section we will present the methods
used after preprocessing the image (with noise removal, edge enhancement, contrast improvement and Canny
edge detection), in order to extract the parameters important in arthroplasty.
Fig.9. The image after applying the Canny Edge Detector
V. Conclusions
The research in the field of medical image analysis is a continuous challenge. The need to discover new
image analysis algorithms and new automatic learning techniques that would help in computer assisted
diagnosis is and will be a topic of interest for researchers.The results of our research, presented in this
paper,prove that solutions do exist. Although not all the arthroplasty parameters determined automatically were
100% accurate, the application proved to be very useful to doctors.The fact that the application allows patient‟s
data saving management, during a long period of time after the hip replacement procedure is another plus.This
application can be used for a single hospital, or for an entire national/international network of
hospitals,integrating other applications of diagnosis or of assisting doctors in planning certain surgeries and
following the patients‟ evolution after the surgeries.
The versatility of these multi-scale transforms make them a suitable tool for several applications in
signal and image processing that can benefit from the following advantages: 1. A wavelet transform
decomposes a signal to a hierarchy of sub-bands with sequential decrease in resolution. Such expansions are
especially useful when a multi-resolution representation is needed. Some image segmentation and registration
techniques can benefit from a “coarse to fine” paradigm based on a multi-resolution framework. 2. A signal can
be analyzed with a multi-resolution framework into a spatial-frequency representation. By carefully selecting
the wavelet function and the space-frequency plane tiling of the transform, distinct components from a noisy
observation signal can be easily separated based on their spatial-frequency characteristics. 3. Many important
features from an image data can be characterized more efficiently in the spatial-frequency domain. Such feature
11. Wavelets in Medical Image Processing On Hip Arthroplasty and De-Noising, Segmentation
www.iosrjournals.org 30 | Page
characterization was shown to be extremely useful in many applications including registration and data
compression. We summarized in this chapter some important applications in medical image processing using
wavelet transforms. Noise reduction and enhancement can be easily implemented by combining some very
simple linear thresholding techniques with wavelet expansion. Efficient de-noising and enhancement improve
image quality for further analysis including segmentation and registration. Feature characteristics in wavelet
domain were proven to be potentially more efficient and reliable when compared to spatial analysis only, and
therefore provided more effective segmentation and registration algorithms. We point out that many other
important applications of multi-resolution wavelet transforms, that were beyond the scope of this book, have not
been covered in this chapter, especially image compression, which is considered as one of the greatest
achievement of wavelet transform in recent years {jin_Unser_2003b}. Other important applications include
tomographic image reconstruction, analysis of functional MRI images (fMRI), and data encoding for MRI
acquisition. Despite the great success of multi-resolutions wavelet transform in medical imaging applications
for the past twenty years, it continues to be a very active area of research. We list a few resources below that are
of interest to readers willing to get more knowledgeable in research and applications in this area.
References
[1] Image Analysis by local 2-D Spectral Signatures., Journal of Optical Society of American, A, Vol. 2, pp. 74, 1985.
bibitem{jin_Daugman_1988} Daugman.
[2] Adapting to Unknown Smoothness via Wavelet Shrinkage., Journal of American Statistics Association, Vol. 90, No. 432, pp. 1200-
1224, 1995c.
[3] Bankman I, Handbook of Medical Image Processing and Analysis, Academic Press, 2000.
[4] Feng D D, Biomedical Information Technology, Elsevier, 2008.
[5] Chen Y, Ee X, Leow K W, Howe T S, Automatic Extraction of Femur Contours from Hip X rayimages, 2000.
[6] Gonzales R C, Woods R E, Digital Image Processing, Prentice-Hall, 2002.
[7] Canny J F, A Computational Approach to Edge Detection, IEEE Trans. Pattern Analysis and Machine Intelligence, 1986.
[8] Campilho A, Kamel M, Image Analysis and Recognition, Springer. Raj K Sinha, Hip Replacement.
[10] Kennon R, Hip and Knee Surgery: A Patient's Guide to Hip Replacement, Hip Resurfacing, Knee Replacement, and Knee
Arthroscopy Book Description.
[11] Botez P, Ortopedie, Bit Publishing House (Iasi), 2001.
[12] Morrey B F, Joint Replacement Arthtoplasty. SCANIP: Available http://www.simpleware.com/software/scanip/iptechd ata.php in
10.10.2009.
[14] 3D-DOCTOR: Available at http://www.ablesw.com/3d-doctor/index.html in 10.10.2009.
[15] Hip-OpCT: Available at http://www.hipop.it/hipopct.html in 20.10.2009.
[16] The official page of the DICOM standard. Availableat http://dicom.nema.org in 20.05.2009.
[ 17] Mohapatra S, Kumar Sa P, Majhi B, ImpulsiveNoise Removal Image Enhancement Technique, 6th
WSEAS International
Conference on CIRCUITS, SYSTEMS, ELECTRONICS, CONTROL & SIGNAL PROCESSING, Cairo, Egypt, 2007.
[18] Chen T, Wu HR, Adaptive impulse detection using center weighted median filters, IEEE Signal Process Lett, 2001.
[19] Georgakopoulos S, Andreadis A, Image Noise Removal Using Graph Theory Concepts, WSEAS Multiconference: Signal, Speech
and Image Processing, Rethymno, Greece, 2003.
[20] Mohammad F, Al-Otum H M, Oraiqat M T, A Comparison of Image Enhancement using Curvelet Transform with Multiscale
Gradient and Retinex Operators, WSEAS Multiconference: Signal, Speech and Image Processing, Izmir, Turkey, 2004.
[21] Djekoune O, Achour K, Halimi M, Kahlouche S, Incremental Hough Transform: An Improvement Algorithm for Digital Devices
Implementatio.
[22] WSEAS Int. Conference on Electronics, Control & Signal Processing and E-Activities, Singapore, 200
bibitem{jin_Acharyya_2002} Acharyya, M. and Kundu, M.
[23] Document Image Segmentation Using Wavelet Scale-Space Features., IEEE Trans. Circuits and Systems for Video Technology,
Vol. 12, No. 12, pp. 1117-1127, 2002. bibitem{jin_Aldroubi_1996} Aldroubi, A. and Unser, M.
[24] Wavelets in Medicine and Biology. Boca Raton, FL: CRC, 1996. bibitem{jin_Allen_1993} Allen, R., Kamangar, F., and Stokely,
E.
[25] Laplacian and Orthogonal Wavelet Pyramid Decompositions in Coarse-to-Fine Registration.,
IEEE Trans. Signal Processing, Vol. 41, No. 12, pp. 3536-3541, 1993. bibitem{jin_Angelini_2001} Angelini, E., Laine, A.,
Takuma, S., Holmes, J., and Homma, S.
[26] LV volume quantification via spatio-temporal analysis of real-time 3D echocardiography, IEEE Transactions on Medical
Imaging, Vol. 20, pp. 457-469, 2001. bibitem{jin_Antoniadis_2001} Antoniadis, A. and Fan, J.
[27] Regularization of Wavelet Approximations., Journal of American Statistics Association, Vol. 96, No. 455, pp. 939-967, 2001.
bibitem{jin_Aydin_1996} Aydin, T., Yemez, Y., Anarim, E., and Sankur, B.
[28] Multi-directional and Multi-scale Edge Detection via M-Band Wavelet Transform., IEEE Trans. Image Processing, Vol. 5, No. 9,
pp. 1370-1377, 1996. bibitem{jin_Babaud_1986} Babaud, J., Witkin, A., Baudin, M., and Duba, R.
[29] Uniqueness of the Gaussian Kernel for Scale-space Filtering., IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 8, pp.
26-33, 1986. bibitem{jin_Bastiaans_1981} Bastiaans, M.
[30] A Sampling Theorem for the Complex Spectrogram and Gabor's Expansion of a Signal in Gaussian Elementary Signals., Optical
Engineering, Vol. 20, No. 4, pp. 594-598, 1981. bibitem{jin_Beck_1987} Beck, J., Sutter, A., and Ivry, r.
[31] Spatial Freuqncy Channels and Perceptual Grouping in Texture Segregation., Computer Vision, Graphics, and Image Processing,
Vol. 37, pp. 299-325, 1987. bibitem{jin_Bello_1994} Bello, M.
[32] A Combined Markov Random Field and Wave-Packet Transform-Based Approach for Image Segmentation., IEEE Trans. Image
Processing, Vol. 3, No. 6, pp. 834-846, 1994.bibitem{jin_Candes_1999a} Candes, E. and Donoho, D.
[33] Curvelets - A Surprisingly Effective Nonadaptive Representation for Objects with Edges. in Curve and Surface Fitting: Saint-Malo
1999, Cohen, A., Rabut, C., and Schumaker, L., Eds. Nashville TN: Vanderbilt University Press, 1999a.
bibitem{jin_Candes_1999b} Candes, E. and Donoho, D.
12. Wavelets in Medical Image Processing On Hip Arthroplasty and De-Noising, Segmentation
www.iosrjournals.org 31 | Page
[34] Ridgelets: The Key to Higher-dimensional Intermittency?, Phil. Trans. R. Soc. Lond. A., Vol. 357, pp. 2495-2509, 1999b.
bibitem{jin_Canny_1986} Canny, J.
[35] A computational approach to edge detection, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 8, No. 6, pp.
679-698, 1986. bibitem{jin_Chan_2001} Chan, T. F. and Vese, L. A.
[36] Active Controus Without Edges, IEEE Transactions on Image Processing, Vol. 10, No. 2, pp. 266-277, 2001.
bibitem{jin_Chang_2000} Chang, S., Yu, B., and Vetterli, M.
[37] Spatially adaptive wavelet thresholding with context modeling for image denoising, IEEE Transactions on Image Processing, Vol.
9, No. 9, pp. 1522-1531, 2000. bibitem{jin_Charalampidis_2002} Charalampidis, D. and Kasparis, T.
[38] Wavelet-based Rotational Invariant Roughness Features for Texture Classification and Segmentation., IEEE Trans. Image
Processing, Vol. 11, No. 8, pp. 825-837, 2002. bibitem{jin_Choi_2001} Choi, H. and Baraniuk, R.
[39] Multiscale Image Segmentation Using Wavelet-Domain Hidden Markov Models., IEEE Trans. Image Processing, Vol. 10, No. 9,
pp. 1309-1321, 2001. bibitem{jin_Coifman_1995a} Coifman, R. and Donoho, D.
[40] Translation-invariant De-noising. in Wavelets and Statistics, Antoniadis, A. and Oppenheim, G., Eds. New York NY: Springer-
Verlag, 1995a. bibitem{jin_Coifman_1992} Coifman, R. R., Meyer, Y., and Wickerhauser, M. V.
[41] Wavelet Analysis and signal processing in Wavelets and their applications, Ruskai, B., Ed. Boston: Jones and Barlett, pp. 153-178,
1992. bibitem{jin_Coifman_1995b} Coifman, R. R. and Woog, L. J.
[42] Adapted waveform analysis, wavelet packets, and local cosine libraries as a tool for image processing, Investigative and trial image
processing, San Diego, California, Vol. 2567, 1995b. bibitem{jin_Daubechies_1988} Daubechies, I.
[43] Orthonormal bases of compactly supported wavelets, Communications on Pure and Applied Mathematics, Vol. 41, No. 7, pp. 909-
996, 1988. bibitem{jin_Daubechies_1992}
Daubechies, I., Ten Lectures on Wavelets. Philadelphia, PA: Siam, 1992. bibitem{jin_Daugman_1985} Daugman, J.
[44] Complete Discrete 2-D Gabor Transforms by Neural Networks for Image Analysis and Compression.,
IEEE Trans. Acoustics, Speech, and Signal Processing, bibitem{jin_de Rivaz_2000} de Rivaz, P. and Kingsbury, N.
[45] Fast Segmentation Using Level Set Curves of Complex Wavelet Surfaces., IEEE International Conference on Image Processing,
Vol. 3, pp. 29-32, 2000. bibitem{jin_Dima_2002} Dima, A., Scholz, M., and Obermayer, K.
[46] Automatic Segmentation and Skeletonization of Neurons From Confocal Microscopy Images Based on the 3-D Wavelet
Transform., IEEE Trans. Image Processing, Vol. 11, No. 7, pp. 790-801, 2002. bibitem{jin_Dinov_2002} Dinov, I., Mega, M.,
Thompson, P., Woods, R., Sumners, D., Sowell, E., and Toga, A.
[47] Quantitative Comparison and Analysis of Brain Image Registration Using Frequency-Adaptive Wavelet Shrinkage IEEE Trans.
Information Technology in Biomedicine, Vol. 6, No. 1, pp. 73-85, 2002. bibitem{jin_Donoho_1994a} Donoho, D. and
Johnstone, I.
[48] Ideal Spatial Adaptation via Wavelet Shrinkage., Biometrika, Vol. 81, pp. 425-455, 1994a. bibitem{jin_Donoho_1995a}
Donoho, D.
[49] Nonlinear solution of linear inverse problems by wavelet-vaguelette decompositions, Journal of Applied and Computational
Harmonic Analysis, Vol. 2, No. 2, pp. 101-126, 1995a. bibitem{jin_Donoho_1995b} Donoho, D.
[50] De-noising by Soft-thresholding., IEEE Trans. Information Theory, Vol. 41, No. 3, pp. 613-627, 1995b.
bibitem{jin_Donoho_1995c} Donoho, D. and Johnstone, I.