This document provides a summary of a PhD presentation on automated kidney segmentation in 3D ultrasound imagery and its application in computer-assisted trauma diagnosis. The key points are:
1) Rapid diagnosis of abdominal trauma is critical for survival but ultrasound exams can be improved with computer assistance. The presentation focuses on automatically detecting and segmenting the kidney in ultrasound images of the right upper quadrant view, which is most relevant for diagnosing bleeding.
2) A complex-valued implicit shape model (CVISM) is used to mathematically represent the multi-regional structure of the kidney. This shape prior aids in detecting the kidney alignment within ultrasound volumes.
3) For segmentation, a complex-valued regional level-set method with
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.
Optic Disc and Macula Localization from Retinal Optical Coherence Tomography ...IJECEIAES
This research used images from Optical Coherence Tomography (OCT) examination as well as fundus images to localize the optical disc and macular layer of retina. The researchers utilized the OCT and fundus image to interpret the distance between macular center and optic disc in the image. The distance will express the area of macula that can be employed for further research. This distance could recognize the thickness of macula parameters diameter that will be used in localizing process of optic disc and macula. The parameters are the circle radius, the size of window’s filter, the constant value and the size of optic disc element structure as well as the size of macula. The results of this study are expected to improve the accuracy of macula detection that experience the edema.
Multi-atlas based segmentation is an approach that requires little or no interaction from the user. It has been evaluated with high accuracy and consistent reproducibility in different anatomical structures. In this method, multiple atlases identify the location of one or more structures in the patient volume. The label volumes of the atlases are transformed taking the coordinate transformation obtained from image registration of each atlas to the target volume. A stochastic gradient descent optimisation is performed for the desired metric during the process. Since multiple structures are segmentation targets in the VISCERAL benchmark, a hierarchical selection of the registrations improves the segmentations of all the structures. A global affine registration is followed by individual affine registrations using a local binary mask to enforce the spatial correlation of each anatomical structure separately. These masks are obtained from the morphological dilation of the output labels of the different atlases registered in the previous step. The method is repeated for the non-rigid registration. The registrations of the bigger structures are used as a starting point for the closely related smaller structures, which are harder to segment. Most of the registrations of the initial
bigger structures (liver, lungs, urinary bladder) will be reused in the method which makes it faster than segmenting each structure individually from the start. Also the creation of regions-of-interest with the local masks speeds up the image registrations and improves the output estimations. The labels from the different atlases are fused using a per-voxel majority voting threshold in a single label volume that provides a final estimate location of the structures in the target volume. The images are downsampled in all but the final step to increase even more the speed of the algorithm. The method was tested with contrast-enhanced computed tomography images and 10 different anatomical structures: liver, spleen, kidneys, lungs, urinary bladder, trachea, lumbar vertebra and gallbladder. It can be then applied to any modality and any anatomical structure using a relatively small training set.
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.
Efficient Diabetic Retinopathy Space Subjective Fuzzy Clustering In Digital F...IOSR Journals
The document describes a new technique called Space Subjective Fuzzy Clustering Method (SSFC) for extracting retinal vessels from digital fundus images to detect diabetic retinopathy at an early stage. The SSFC method involves smoothing and enhancing the fundus image using mathematical morphology operations to suppress background information and highlight retinal vessels. It then applies a Space Subjective Fuzzy Clustering algorithm to segment the retinal vessels, followed by a refinement process. Experimental results show the SSFC method achieves better segmentation accuracy and clustering efficiency compared to existing methods for detecting signs of diabetic retinopathy.
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.
Diagnosis of Diabetic Retinopathy by Detection of Microneurysm And ExudatesIRJET Journal
This document proposes an automated method for detecting diabetic retinopathy by extracting features from fundus images using image processing techniques in MATLAB. It involves pre-processing fundus images, extracting blood vessels using edge detection and morphology, segmenting exudates using morphological operations, detecting the optic nerve and microaneurysms which appear as red lesions, and combining the results to determine if a patient is normal or abnormal. The proposed method could help enable large-scale screening of diabetic patients in a cost-effective manner.
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
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.
Optic Disc and Macula Localization from Retinal Optical Coherence Tomography ...IJECEIAES
This research used images from Optical Coherence Tomography (OCT) examination as well as fundus images to localize the optical disc and macular layer of retina. The researchers utilized the OCT and fundus image to interpret the distance between macular center and optic disc in the image. The distance will express the area of macula that can be employed for further research. This distance could recognize the thickness of macula parameters diameter that will be used in localizing process of optic disc and macula. The parameters are the circle radius, the size of window’s filter, the constant value and the size of optic disc element structure as well as the size of macula. The results of this study are expected to improve the accuracy of macula detection that experience the edema.
Multi-atlas based segmentation is an approach that requires little or no interaction from the user. It has been evaluated with high accuracy and consistent reproducibility in different anatomical structures. In this method, multiple atlases identify the location of one or more structures in the patient volume. The label volumes of the atlases are transformed taking the coordinate transformation obtained from image registration of each atlas to the target volume. A stochastic gradient descent optimisation is performed for the desired metric during the process. Since multiple structures are segmentation targets in the VISCERAL benchmark, a hierarchical selection of the registrations improves the segmentations of all the structures. A global affine registration is followed by individual affine registrations using a local binary mask to enforce the spatial correlation of each anatomical structure separately. These masks are obtained from the morphological dilation of the output labels of the different atlases registered in the previous step. The method is repeated for the non-rigid registration. The registrations of the bigger structures are used as a starting point for the closely related smaller structures, which are harder to segment. Most of the registrations of the initial
bigger structures (liver, lungs, urinary bladder) will be reused in the method which makes it faster than segmenting each structure individually from the start. Also the creation of regions-of-interest with the local masks speeds up the image registrations and improves the output estimations. The labels from the different atlases are fused using a per-voxel majority voting threshold in a single label volume that provides a final estimate location of the structures in the target volume. The images are downsampled in all but the final step to increase even more the speed of the algorithm. The method was tested with contrast-enhanced computed tomography images and 10 different anatomical structures: liver, spleen, kidneys, lungs, urinary bladder, trachea, lumbar vertebra and gallbladder. It can be then applied to any modality and any anatomical structure using a relatively small training set.
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.
Efficient Diabetic Retinopathy Space Subjective Fuzzy Clustering In Digital F...IOSR Journals
The document describes a new technique called Space Subjective Fuzzy Clustering Method (SSFC) for extracting retinal vessels from digital fundus images to detect diabetic retinopathy at an early stage. The SSFC method involves smoothing and enhancing the fundus image using mathematical morphology operations to suppress background information and highlight retinal vessels. It then applies a Space Subjective Fuzzy Clustering algorithm to segment the retinal vessels, followed by a refinement process. Experimental results show the SSFC method achieves better segmentation accuracy and clustering efficiency compared to existing methods for detecting signs of diabetic retinopathy.
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.
Diagnosis of Diabetic Retinopathy by Detection of Microneurysm And ExudatesIRJET Journal
This document proposes an automated method for detecting diabetic retinopathy by extracting features from fundus images using image processing techniques in MATLAB. It involves pre-processing fundus images, extracting blood vessels using edge detection and morphology, segmenting exudates using morphological operations, detecting the optic nerve and microaneurysms which appear as red lesions, and combining the results to determine if a patient is normal or abnormal. The proposed method could help enable large-scale screening of diabetic patients in a cost-effective manner.
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
Xoran's xCAT - high resolution low dose head CTBritaMed Inc.
Introduction of the xCAT: Xoran's most powerful CT Scanner to date, offering sub-millimeter resolution for superior geometrical accuracy.
The xCAT radiation dose is a small fraction of conventional head CT, while the entire scanner is compact and portable using a 4 wheels design.
Automated histopathological image analysis: a review on ROI extractioniosrjce
IOSR Journal of Computer Engineering (IOSR-JCE) is a double blind peer reviewed International Journal that provides rapid publication (within a month) of articles in all areas of computer engineering and its applications. The journal welcomes publications of high quality papers on theoretical developments and practical applications in computer technology. Original research papers, state-of-the-art reviews, and high quality technical notes are invited for publications.
This study evaluated the long-term safety and efficacy of Ferrara intrastromal corneal ring segments for keratoconus treatment. The records of 36 eyes of 30 patients who received ICRS from 1996-2002 were reviewed. At the 5-year follow-up, uncorrected and corrected visual acuity significantly improved, and keratometry and corneal thickness values significantly decreased. At the 10-year follow-up, these improvements were maintained without significant changes, demonstrating the long-term effectiveness and stability of ICRS for keratoconus. This is the longest reported follow-up of ICRS for keratoconus correction.
The Advantages of Two Dimensional Techniques (2D) in Pituitary Adenoma TreatmentIOSR Journals
The purpose of the study is to evaluate the two dimensional dose distribution techniques in pituitary adenoma patient treatment in order to provide 2D dose coverage to the target volume while sparing organs at risk (OARs). The CT simulator was used to radiograph 300 patients of pituitary adenomas to conform 2D dose distribution planning inside the tumour bed , and its structures were delineated; including gross target volume (GTV), clinical target volume (CTV), and planning target volume (PTV)], as well as organs at risks (OARs) . Dose distribution analysis was edited to provide 2D dose coverage to the target while sparing organs at risk. The main results of the study were, 2D dose distribution plans increases the unnecessary dose to the critical organs according to their geographical location from the pituitary adenoma site, and the present study , concludes that when the tumour dose increases from 45 to 55 Gy there is a linear proportional increment of dose to the organs at risks, and when the dose is about 60 Gy in 2D, the increment of unnecessary dose to temporal lobe is 0.31 Gy, and to eye is0.34Gy, and to optic chiasm is 0.42 Gy respectively .New techniques, which will lessen the unnecessary dose to OARs, needed to be developed .
A Novel Advanced Approach Using Morphological Image Processing Technique for ...CSCJournals
This document presents a novel approach for early detection of diabetic retinopathy using morphological image processing techniques. The proposed approach uses Contrast Limited Adaptive Histogram Equalization (CLAHE) for retinal optic disk detection and removal. Microaneurysms are then detected using morphological operations. Evaluation on real-world databases shows the approach achieves 99.7% accuracy, 81% sensitivity, and 90% specificity for microaneurysm detection, outperforming existing methods. The detection of microaneurysms at different levels can help identify the stage of diabetic retinopathy and enable early diagnosis.
Segmentation of the Blood Vessel and Optic Disc in Retinal Images Using EM Al...iosrjce
IOSR Journal of Computer Engineering (IOSR-JCE) is a double blind peer reviewed International Journal that provides rapid publication (within a month) of articles in all areas of computer engineering and its applications. The journal welcomes publications of high quality papers on theoretical developments and practical applications in computer technology. Original research papers, state-of-the-art reviews, and high quality technical notes are invited for publications.
WORLD’S LATEST 3D DIGITAL MAMMOGRAPHY SYSTEMMIOT Hospitals
The state-of-the-art 3D Digital Mammography System from GE Healthcare, installed at MIOT International is available in very few hospitals in India has been designed primarily to give you a painfree experience. Built on an upgradeable platform, which can move from basic screening to advanced diagnostic procedures in a matter of minutes, the system is ideal for first time & repeat screeners as well as those seeking a conclusive diagnoses.
Abstract— The division is the urgent stage in iris acknowledgment. We have utilized the worldwide limit an incentive for division. In the above calculation we have not considered the eyelid and eyelashes relics, which corrupt the execution of iris acknowledgment framework. The framework gives sufficient execution likewise the outcomes are attractive. Assist advancement of this technique is under way and the outcomes will be accounted for sooner rather than later. Based on the reasonable peculiarity of the iris designs we can anticipate that iris acknowledgment framework will turn into the main innovation in personality verification.In this paper, iris acknowledgment calculation is depicted. As innovation advances and data and scholarly properties are needed by numerous unapproved work force. Therefore numerous associations have being scanning routes for more secure confirmation strategies for the client get to. The framework steps are catching iris designs; deciding the area of iris limits; changing over the iris limit to the binarized picture; The framework has been actualized and tried utilizing dataset of number of tests of iris information with various complexity quality.
Keywords— GAC, Iris Recognition, Iris Segmentation, Snakes.
Detection of Macular Edema by using Various Techniques of Feature Extraction ...IRJET Journal
This document presents a review of techniques for automatically detecting diabetic retinopathy by analyzing color fundus images. Diabetic retinopathy occurs when blood vessels in the retina are damaged from diabetes, and can lead to vision loss if left untreated. The document discusses existing work on feature extraction and classification methods for detecting signs of diabetic retinopathy like exudates and macular edema. It proposes a new method that focuses on extracting texture features from the region around the macula in order to accurately detect high-risk macular edema cases.
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.
Automated Detection of Microaneurysm, Hard Exudates, and Cotton Wool Spots in...iosrjce
The The automatic identification of Image processing techniques for abnormalities in retinal images.
Its very importance in diabetic retinopathy screening. Manual annotations of retinal images are rare and
exclusive to obtain. The ophthalmoscope used direct analysis is a small and portable apparatus contained of a
light source and a set of lenses view the retina. The existence of diabetic retinopathy detected can be examining
the retina for its individual features. The first presence of diabetic retinopathy is the form of Microaneurysms.
This paper describes different works needed to the automatic identification of hard exudates and cotton wool
spots in retinal images for diabetic retinopathy detection and support vector machine (SVM) for classifying
images. This system is evaluated on a large dataset containing 130 retinal images. The proposed method Results
show that exudates were detected from a database with 96.9% sensitivity, specificity 96.1% and
97.38%accuracy
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
Three-dimensional (3D) computer-assisted surgical simulation and navigation can improve the accuracy of orthognathic surgery planning and execution over traditional 2D techniques. The document reviews literature on 3D modeling techniques including cone beam CT imaging, virtual surgical planning, and methods for transferring virtual plans to surgery using splints, guides or navigation. Key benefits of 3D methods include more accurate simulation of bone movements, simplified intraoperative positioning, elimination of human errors, and improved aesthetic outcomes.
Diabetic retinopathy is a leading cause of blindness that can be detected through automated analysis of fundus images. The document proposes using support vector machines to build a model that can robustly detect four key features of diabetic retinopathy - hard exudates, soft exudates, microaneurysms, and hemorrhages. The model is trained on a standardized set of fundus images and achieves over 95% accuracy on classification, providing an affordable solution to diagnose a disease affecting many people.
The document compares dose plans for cranio-spinal irradiation using helical tomotherapy versus traditional linear accelerators. Simulation results found that tomotherapy plans provided better sparing of organs-at-risk like the lungs, heart, and kidneys compared to previous techniques. However, integral doses need to be carefully analyzed for pediatric patients. Overall, tomotherapy allows for faster treatment times and improved target coverage and dose uniformity, but unexpected machine issues could impact treatment if backup is not available.
This document discusses the history and types of endoscopes used in urology. It describes rigid endoscopes which use a series of lenses to transmit images and how the rod lens system improved image quality. Flexible endoscopes transmit images using fiber optic bundles and have the advantage of being able to flex and access different areas. Newer digital endoscopes replace lenses with CCD chips to provide superior quality images electronically. The document outlines the benefits of different endoscope technologies and future trends including 3D imaging and wireless capabilities.
This document summarizes a research paper that proposes a method for detecting and classifying stages of non-proliferative diabetic retinopathy (NPDR) in retinal images. The method uses morphological operations to detect three retinal features - blood vessels, microaneurysms, and hard exudates. These features are extracted and the distribution in four retinal quadrants is used as input to an SVM classifier to classify images as normal, mild NPDR, moderate NPDR, or severe NPDR. The method was tested on 337 retinal images and achieved an average accuracy of 95%, sensitivity of 96.08% and specificity of 97.92% for classification. The results demonstrate the method can successfully classify NPDR stages, though classification
This thesis investigates using finite element analysis (FEA) to model magnetic resonance elastography (MRE) and its potential application to abdominal aortic aneurysms (AAAs). MRE is an MRI technique that measures tissue mechanical properties by imaging shear wave propagation under an applied force. The thesis develops an FEA method to simulate MRE and uses it to study how modeling parameters and geometry impact MRE measurements. Simulations of MRE on idealized AAA geometries show AAA size, thrombus viscosity, and AAA wall stiffness all influence measurement accuracy in the thrombus. However, initial MRE scans of real AAA patients were dominated by noise, and wave propagation was not visualized. This suggests the current MRE setup is
Anatomical segmentation is fundamental for further image analysis and Computer-Aided Diagnosis. Manual annotation and visual inspection is time consuming for radiologists. Accurate large scale data analysis techniques are needed.
This document provides guidance on ultrasound evaluation of the gallbladder and bile ducts. It discusses techniques for imaging the gallbladder and adjacent structures. Proper fasting is important for optimal visualization of the gallbladder. Anatomic variants like folds and septations are reviewed. Relationship of the bile ducts to surrounding vessels is described. Pitfalls in identifying the bile ducts versus other tubular structures are addressed.
Xoran's xCAT - high resolution low dose head CTBritaMed Inc.
Introduction of the xCAT: Xoran's most powerful CT Scanner to date, offering sub-millimeter resolution for superior geometrical accuracy.
The xCAT radiation dose is a small fraction of conventional head CT, while the entire scanner is compact and portable using a 4 wheels design.
Automated histopathological image analysis: a review on ROI extractioniosrjce
IOSR Journal of Computer Engineering (IOSR-JCE) is a double blind peer reviewed International Journal that provides rapid publication (within a month) of articles in all areas of computer engineering and its applications. The journal welcomes publications of high quality papers on theoretical developments and practical applications in computer technology. Original research papers, state-of-the-art reviews, and high quality technical notes are invited for publications.
This study evaluated the long-term safety and efficacy of Ferrara intrastromal corneal ring segments for keratoconus treatment. The records of 36 eyes of 30 patients who received ICRS from 1996-2002 were reviewed. At the 5-year follow-up, uncorrected and corrected visual acuity significantly improved, and keratometry and corneal thickness values significantly decreased. At the 10-year follow-up, these improvements were maintained without significant changes, demonstrating the long-term effectiveness and stability of ICRS for keratoconus. This is the longest reported follow-up of ICRS for keratoconus correction.
The Advantages of Two Dimensional Techniques (2D) in Pituitary Adenoma TreatmentIOSR Journals
The purpose of the study is to evaluate the two dimensional dose distribution techniques in pituitary adenoma patient treatment in order to provide 2D dose coverage to the target volume while sparing organs at risk (OARs). The CT simulator was used to radiograph 300 patients of pituitary adenomas to conform 2D dose distribution planning inside the tumour bed , and its structures were delineated; including gross target volume (GTV), clinical target volume (CTV), and planning target volume (PTV)], as well as organs at risks (OARs) . Dose distribution analysis was edited to provide 2D dose coverage to the target while sparing organs at risk. The main results of the study were, 2D dose distribution plans increases the unnecessary dose to the critical organs according to their geographical location from the pituitary adenoma site, and the present study , concludes that when the tumour dose increases from 45 to 55 Gy there is a linear proportional increment of dose to the organs at risks, and when the dose is about 60 Gy in 2D, the increment of unnecessary dose to temporal lobe is 0.31 Gy, and to eye is0.34Gy, and to optic chiasm is 0.42 Gy respectively .New techniques, which will lessen the unnecessary dose to OARs, needed to be developed .
A Novel Advanced Approach Using Morphological Image Processing Technique for ...CSCJournals
This document presents a novel approach for early detection of diabetic retinopathy using morphological image processing techniques. The proposed approach uses Contrast Limited Adaptive Histogram Equalization (CLAHE) for retinal optic disk detection and removal. Microaneurysms are then detected using morphological operations. Evaluation on real-world databases shows the approach achieves 99.7% accuracy, 81% sensitivity, and 90% specificity for microaneurysm detection, outperforming existing methods. The detection of microaneurysms at different levels can help identify the stage of diabetic retinopathy and enable early diagnosis.
Segmentation of the Blood Vessel and Optic Disc in Retinal Images Using EM Al...iosrjce
IOSR Journal of Computer Engineering (IOSR-JCE) is a double blind peer reviewed International Journal that provides rapid publication (within a month) of articles in all areas of computer engineering and its applications. The journal welcomes publications of high quality papers on theoretical developments and practical applications in computer technology. Original research papers, state-of-the-art reviews, and high quality technical notes are invited for publications.
WORLD’S LATEST 3D DIGITAL MAMMOGRAPHY SYSTEMMIOT Hospitals
The state-of-the-art 3D Digital Mammography System from GE Healthcare, installed at MIOT International is available in very few hospitals in India has been designed primarily to give you a painfree experience. Built on an upgradeable platform, which can move from basic screening to advanced diagnostic procedures in a matter of minutes, the system is ideal for first time & repeat screeners as well as those seeking a conclusive diagnoses.
Abstract— The division is the urgent stage in iris acknowledgment. We have utilized the worldwide limit an incentive for division. In the above calculation we have not considered the eyelid and eyelashes relics, which corrupt the execution of iris acknowledgment framework. The framework gives sufficient execution likewise the outcomes are attractive. Assist advancement of this technique is under way and the outcomes will be accounted for sooner rather than later. Based on the reasonable peculiarity of the iris designs we can anticipate that iris acknowledgment framework will turn into the main innovation in personality verification.In this paper, iris acknowledgment calculation is depicted. As innovation advances and data and scholarly properties are needed by numerous unapproved work force. Therefore numerous associations have being scanning routes for more secure confirmation strategies for the client get to. The framework steps are catching iris designs; deciding the area of iris limits; changing over the iris limit to the binarized picture; The framework has been actualized and tried utilizing dataset of number of tests of iris information with various complexity quality.
Keywords— GAC, Iris Recognition, Iris Segmentation, Snakes.
Detection of Macular Edema by using Various Techniques of Feature Extraction ...IRJET Journal
This document presents a review of techniques for automatically detecting diabetic retinopathy by analyzing color fundus images. Diabetic retinopathy occurs when blood vessels in the retina are damaged from diabetes, and can lead to vision loss if left untreated. The document discusses existing work on feature extraction and classification methods for detecting signs of diabetic retinopathy like exudates and macular edema. It proposes a new method that focuses on extracting texture features from the region around the macula in order to accurately detect high-risk macular edema cases.
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.
Automated Detection of Microaneurysm, Hard Exudates, and Cotton Wool Spots in...iosrjce
The The automatic identification of Image processing techniques for abnormalities in retinal images.
Its very importance in diabetic retinopathy screening. Manual annotations of retinal images are rare and
exclusive to obtain. The ophthalmoscope used direct analysis is a small and portable apparatus contained of a
light source and a set of lenses view the retina. The existence of diabetic retinopathy detected can be examining
the retina for its individual features. The first presence of diabetic retinopathy is the form of Microaneurysms.
This paper describes different works needed to the automatic identification of hard exudates and cotton wool
spots in retinal images for diabetic retinopathy detection and support vector machine (SVM) for classifying
images. This system is evaluated on a large dataset containing 130 retinal images. The proposed method Results
show that exudates were detected from a database with 96.9% sensitivity, specificity 96.1% and
97.38%accuracy
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
Three-dimensional (3D) computer-assisted surgical simulation and navigation can improve the accuracy of orthognathic surgery planning and execution over traditional 2D techniques. The document reviews literature on 3D modeling techniques including cone beam CT imaging, virtual surgical planning, and methods for transferring virtual plans to surgery using splints, guides or navigation. Key benefits of 3D methods include more accurate simulation of bone movements, simplified intraoperative positioning, elimination of human errors, and improved aesthetic outcomes.
Diabetic retinopathy is a leading cause of blindness that can be detected through automated analysis of fundus images. The document proposes using support vector machines to build a model that can robustly detect four key features of diabetic retinopathy - hard exudates, soft exudates, microaneurysms, and hemorrhages. The model is trained on a standardized set of fundus images and achieves over 95% accuracy on classification, providing an affordable solution to diagnose a disease affecting many people.
The document compares dose plans for cranio-spinal irradiation using helical tomotherapy versus traditional linear accelerators. Simulation results found that tomotherapy plans provided better sparing of organs-at-risk like the lungs, heart, and kidneys compared to previous techniques. However, integral doses need to be carefully analyzed for pediatric patients. Overall, tomotherapy allows for faster treatment times and improved target coverage and dose uniformity, but unexpected machine issues could impact treatment if backup is not available.
This document discusses the history and types of endoscopes used in urology. It describes rigid endoscopes which use a series of lenses to transmit images and how the rod lens system improved image quality. Flexible endoscopes transmit images using fiber optic bundles and have the advantage of being able to flex and access different areas. Newer digital endoscopes replace lenses with CCD chips to provide superior quality images electronically. The document outlines the benefits of different endoscope technologies and future trends including 3D imaging and wireless capabilities.
This document summarizes a research paper that proposes a method for detecting and classifying stages of non-proliferative diabetic retinopathy (NPDR) in retinal images. The method uses morphological operations to detect three retinal features - blood vessels, microaneurysms, and hard exudates. These features are extracted and the distribution in four retinal quadrants is used as input to an SVM classifier to classify images as normal, mild NPDR, moderate NPDR, or severe NPDR. The method was tested on 337 retinal images and achieved an average accuracy of 95%, sensitivity of 96.08% and specificity of 97.92% for classification. The results demonstrate the method can successfully classify NPDR stages, though classification
This thesis investigates using finite element analysis (FEA) to model magnetic resonance elastography (MRE) and its potential application to abdominal aortic aneurysms (AAAs). MRE is an MRI technique that measures tissue mechanical properties by imaging shear wave propagation under an applied force. The thesis develops an FEA method to simulate MRE and uses it to study how modeling parameters and geometry impact MRE measurements. Simulations of MRE on idealized AAA geometries show AAA size, thrombus viscosity, and AAA wall stiffness all influence measurement accuracy in the thrombus. However, initial MRE scans of real AAA patients were dominated by noise, and wave propagation was not visualized. This suggests the current MRE setup is
Anatomical segmentation is fundamental for further image analysis and Computer-Aided Diagnosis. Manual annotation and visual inspection is time consuming for radiologists. Accurate large scale data analysis techniques are needed.
This document provides guidance on ultrasound evaluation of the gallbladder and bile ducts. It discusses techniques for imaging the gallbladder and adjacent structures. Proper fasting is important for optimal visualization of the gallbladder. Anatomic variants like folds and septations are reviewed. Relationship of the bile ducts to surrounding vessels is described. Pitfalls in identifying the bile ducts versus other tubular structures are addressed.
This document provides an overview of ultrasonography in hepatobiliary diseases. It begins with basic knowledge about ultrasound waves and transducers. It then discusses how to evaluate the liver, including size, focal lesions, diffuse diseases, vasculature, and biliary radicles. Specific conditions like portal hypertension and bile duct obstruction are also addressed. The aim is to provide tips and tricks for ultrasonography of the liver and biliary system.
abdominal ultrasound
hope I helped you guys
comment if there is something wrong with what I made or if its good or not and if you want me to make next..thanks :)
The digestive system breaks down food through a multi-step process. The mouth and teeth chew food while saliva makes it slippery, then the esophagus transports chewed food to the stomach using peristalsis. In the stomach, gastric acids turn food into a liquid called chyme over 6-8 hours. The small intestine further breaks down nutrients with help from the liver, gallbladder and pancreas. The large intestine removes remaining water and minerals to form solid waste for excretion.
Presentation1.pptx, ultrasound examination of the liver and gall bladder.Abdellah Nazeer
This document provides an ultrasound protocol and guidelines for examining the liver and gallbladder. It begins with an overview of the role and technique of ultrasound for the liver, including scanning positions and images to capture. Common liver pathologies such as fatty liver, cirrhosis, cysts, hemangiomas, abscesses, and metastases are described. Guidelines are provided for gallbladder ultrasound including patient preparation, technique, and anatomy. Normal findings and pathologies like stones, acute cholecystitis, and emphysematous cholecystitis are outlined. The document concludes with potential vascular disorders of the liver involving blood flow.
Presentation1.pptx, ultrasound examination of the adrenal glands and kidneys.Abdellah Nazeer
This document discusses the ultrasound imaging of the adrenal glands and kidneys. It provides details on the anatomy and sonographic appearance of normal and pathological adrenal glands. The adrenal glands are located anteromedially to the kidneys. Common pathological conditions that can be identified with ultrasound include adrenal adenomas, myelolipomas, hemorrhages, abscesses, hyperplasia, cysts and metastases. Malignant tumors like metastases are often irregular with complex internal echoes. Ultrasound is useful to characterize adrenal lesions but CT may be needed for definitive diagnosis.
Marker Controlled Segmentation Technique for Medical applicationRushin Shah
Medical image segmentation is a very important field for the medical science. In medical images, edge detection is an important work for object recognition of the human organs such as brain, heart or kidney etc. and it is an essential pre-processing step in medical image segmentation.
Medical images such as CT, MRI or X-Ray visualizes the various information’s of internal organs which is very important for doctors diagnoses as well as medical teaching, learning and research.
It is a tough job to locate the internal organs if images contains noise or rough structure of human body organs.
Ultrasound of the urinary tract - Renal cystsSamir Haffar
This document discusses ultrasound findings of renal cysts and cystic renal lesions. It provides details on:
1) The Bosniak classification system used to characterize renal cysts and cystic masses as benign (Classes I and II) or malignant (Classes III and IV).
2) Characteristics of simple renal cysts, complex cysts, cystic renal cell carcinomas, and other cystic lesions.
3) Cystic manifestations of conditions like polycystic kidney disease, von Hippel-Lindau disease, and tuberous sclerosis.
Cystic liver lesions - An ultrasound perspectiveSamir Haffar
This document summarizes the diagnosis and imaging findings of various cystic hepatic lesions. It describes simple hepatic cysts, hydatid cysts, and congenital fibrocystic liver diseases including biliary hamartomas, peribiliary cysts, choledochal cysts, and polycystic liver disease. Imaging findings on ultrasound, CT, MRI, and MRCP are provided for each condition to aid diagnosis. Differential features between lesion types are emphasized, along with WHO classification of hydatid cyst appearance and post-operative evaluation of hydatid cyst treatment.
This document summarizes the radiographic manifestations of renal tuberculosis. It describes how tuberculosis can involve the renal parenchyma and collecting system, causing pyelonephritis or pseudotumoral lesions on imaging. Imaging findings vary depending on disease stage but can include papillary necrosis, strictures, hydronephrosis, mural thickening and calcifications. Plain films may demonstrate triangular calcifications in papillary necrosis or amorphous dystrophic calcifications in end-stage disease. Intravenous urography is sensitive for detecting lesions and complications like reflux or fistulas. Ultrasound, CT and MRI are also used to characterize lesions and assess extent of involvement.
Cystic kidney diseases in children can be genetic or non-genetic in origin. Genetic causes include autosomal recessive polycystic kidney disease (ARPKD), autosomal dominant polycystic kidney disease (ADPKD), juvenile nephronophthisis, and glomerulocystic kidney disease. Non-genetic causes include simple cysts, multicystic dysplastic kidney, acquired cysts, and caliceal cysts. Ultrasound is the primary imaging modality used for diagnosis. ARPKD is the most severe genetic cause, occurring in 1 in 50,000, and is characterized by cystic dilatation of the collecting tubules affecting both kidneys
PPT on BRAIN TUMOR detection in MRI images based on IMAGE SEGMENTATION khanam22
The document presents three methods for tumor detection in MRI images: 1) K-means clustering with watershed algorithm, 2) Optimized K-means using genetic algorithm, and 3) Optimized C-means using genetic algorithm. It evaluates each method, finding that C-means clustering with genetic algorithm most accurately detects tumors by assigning data points to multiple clusters and finding the optimal solution in less time. The proposed approach successfully detects tumors with high accuracy, identifies the tumor area and internal structure, and provides a colorized output image.
The document summarizes the main parts and processes of the human digestive system. It describes the six major processes of digestion - ingestion, propulsion, mechanical and chemical digestion, absorption, and defecation. It then explains the functions and roles of the main digestive organs - mouth, esophagus, stomach, small intestine, and large intestine. Finally, it discusses the accessory organs - liver, pancreas, gallbladder, and salivary glands - and how they aid the digestion process.
Ultrasound of acute & chronic cholecystitisSamir Haffar
This document discusses ultrasound findings related to cholecystitis. It describes the ultrasound appearance of acute cholecystitis, including signs like gallbladder wall thickening, pericholecystic fluid, and hyperemia on Doppler. Complications of acute cholecystitis are also reviewed, such as emphysematous cholecystitis where gas is visible in the gallbladder wall. Chronic cholecystitis is also summarized, noting findings like gallstones, wall thickening, and occasionally calcification or nodules indicative of xanthogranulomatous cholecystitis.
The document provides information on performing and interpreting an ultrasound of the liver. It discusses normal liver anatomy and Doppler assessments of the hepatic vessels. Key findings of a normal liver ultrasound include evaluating the size, shape, echogenicity and echotexture of the liver. Doppler ultrasound can assess blood flow in the hepatic arteries, portal veins and hepatic veins which branch throughout the liver and should demonstrate continuous flow in the expected directions. Spectral analysis of waveforms can help identify abnormalities associated with conditions like portal hypertension.
This document summarizes ultrasound findings related to the gallbladder. It begins by describing normal gallbladder anatomy and ultrasound appearance. It then discusses various congenital gallbladder abnormalities that can be seen on ultrasound. Finally, it details gallbladder pathologies that can be identified ultrasonographically such as gallstones, sludge, acute and chronic cholecystitis, polyps and carcinoma. For each finding, it provides ultrasound images and descriptions of characteristic ultrasound features.
This document discusses Doppler ultrasound of the kidneys. It begins with the normal anatomy of the kidneys and renal vasculature. It then describes how to perform grayscale and Doppler ultrasound of the kidneys, including imaging planes and settings. Normal Doppler waveforms of renal arteries are presented. Key measurements like resistive index, acceleration time, and peak systolic velocity of renal arteries are discussed. Variants of renal and renal vein anatomy are also reviewed.
BATCH NORMALIZED CONVOLUTION NEURAL NETWORK FOR LIVER SEGMENTATIONsipij
With the huge innovative improvement in all lifestyles, it has been important to build up the clinical fields, remembering the finding for which treatment is done; where the fruitful treatment relies upon the preoperative. Models for the preoperative, for example, planning to understand the complex internal structure of the liver and precisely localize the liver surface and its tumors; there are various algorithms proposed to do the automatic liver segmentation. In this paper, we propose a Batch Normalization After All - Convolutional Neural Network (BATA-Convnet) model to segment the liver CT images using Deep Learning Technique. The proposed liver segmentation model consists of four main steps: pre-processing, training the BATA-Convnet, liver segmentation, and the postprocessing step to maximize the result efficiency. Medical Image Computing and Computer Assisted Intervention (MICCAI) dataset and 3DImage Reconstruction for Comparison of Algorithm Database (3D-RCAD) were used in the experimentation and the average results using MICCAI are 0.91% for Dice, 13.44% for VOE, 0.23% for RVD, 0.29mm for ASD, 1.35mm for RMSSD and 0.36mm for MaxASD. The average results using 3DIRCAD dataset are 0.84% for Dice, 13.24% for VOE, 0.16% for RVD, 0.32mm for ASD, 1.17mm for RMSSD and 0.33mm for MaxASD.
Batch Normalized Convolution Neural Network for Liver Segmentationsipij
With the huge innovative improvement in all lifestyles, it has been important to build up the clinical fields, remembering the finding for which treatment is done; where the fruitful treatment relies upon the
preoperative. Models for the preoperative, for example, planning to understand the complex internal structure of the liver and precisely localize the liver surface and its tumors; there are various algorithms proposed to do the automatic liver segmentation. In this paper, we propose a Batch Normalization After All - Convolutional Neural Network (BATA-Convnet) model to segment the liver CT images using Deep
Learning Technique. The proposed liver segmentation model consists of four main steps: pre-processing, training the BATA-Convnet, liver segmentation, and the postprocessing step to maximize the result
efficiency. Medical Image Computing and Computer Assisted Intervention (MICCAI) dataset and 3DImage Reconstruction for Comparison of Algorithm Database (3D-IRCAD) were used in the experimentation and the average results using MICCAI are 0.91% for Dice, 13.44% for VOE, 0.23% for RVD, 0.29mm for ASD, 1.35mm for RMSSD and 0.36mm for MaxASD. The average results using 3DIRCAD dataset are 0.84% for Dice, 13.24% for VOE, 0.16% for RVD, 0.32mm for ASD, 1.17mm for
RMSSD and 0.33mm for MaxASD.
PERFORMANCE EVALUATION OF TUMOR DETECTION TECHNIQUES ijcsa
Automatic segmentation of tumor plays a vital role in diagnosis and surgical planning. This paper deals
with techniques which providing solution for detecting hepatic tumor in Computed Tomography (CT)
images. The main aim of this work is to analyze performance of tumor detection techniques like Knowledge
Based Constraints, Graph Cut Method and Gradient Vector Flow active contour. These three techniques
are computed using sensitivity, specificity and accuracy. From the evaluated result, knowledge based
constraints method is better than other graph cut method and gradient vector flow active contour.
PERFORMANCE EVALUATION OF TUMOR DETECTION TECHNIQUES ijcsa
Automatic segmentation of tumor plays a vital role in diagnosis and surgical planning. This paper deals
with techniques which providing solution for detecting hepatic tumor in Computed Tomography (CT)
images. The main aim of this work is to analyze performance of tumor detection techniques like Knowledge
Based Constraints, Graph Cut Method and Gradient Vector Flow active contour. These three techniquesare computed using sensitivity, specificity and accuracy. From the evaluated result, knowledge based constraints method is better than other graph cut method and gradient vector flow active contour.
3D Position Tracking System for Flexible CystoscopyCSCJournals
Flexible cystoscopy is an examination that allows physicians to look inside the bladder. In flexible cystoscopy, beginner physicians tend to lose track of the observation due to complex handling patterns of a flexible cystoscope and poor characteristics of the bladder. In this paper, as a diagnostic support tool for beginner physicians in flexible cystoscopy, we propose a system for tracking the observation using cystoscopic images. Our system discriminates three handling patterns of a flexible cystoscope, namely bending, rotation, or insertion. To discriminate the handling patterns accurately, we propose to use the degree of bending, rotation, or insertion as features for the discrimination as well as ZNCC-based optical flows. These features are learned by a Random Forest classifier. The classifier discriminates sequential handling patterns of the cystoscope by a time-series analysis. Experimental results on ten videos obtained in flexible cystoscopy show that each of the three handling patterns were correctly discriminated over 90% in average. In addition, we reproduced the observation in a virtual bladder we propose.
Terrain generation finds many applications such as
in CGI movies, animations and video games. This
paper describes a new and simple-to-implement terra
in generator called the Uplift Model. It is based o
n
the theory of crustal deformations by uplifts in Ge
ology. When a number of uplifts are made on the Ear
th’s
surface, the final net effect is an average of the
influence of each uplift at each point on the terra
in. The
result of applying this model from Nature is a very
realistic looking effect in the generated terrains
. The
model uses 6 parameters which allow for a great var
iety in landscape types produced. Comparisons are
made with other existing terrain generation algorit
hms. Averaging causes erosion of the surface wherea
s
fractal surfaces tend to be very jagged and more su
ited to alien worlds.
Segmentation of cysts in kidney and 3 d volume calculation from ct imagesbioejjournal
Statistics based optimization, Plackett–Burman design (PBD) and response surface methodology
(RSM) were employed to screen and optimize the media components for the production of
clavulanic acid from Streptomyces clavuligerus MTCC 1142, using solid state fermentation. jackfruit
seed powder was used as both the solid support and carbon source for the growth of Streptomyces
clavuligerus MTCC 1142. Based on the positive influence of the Pareto chart obtained from PBD on
clavulanic acid production, five media components – yeast extract, beef extract, sucrose, malt extract
and ferric chloride were screened. Central composite design (CCD) was employed using these five
media components- yeast extract 2.5%, beef extract 0.5%, sucrose 2.5%, malt extract 0.25% and ferric
chloride nutritional factors at three levels, for further optimization, and the second order polynomial
equation was derived, based on the experimental data. Response surface methodology showed that
the concentrations of yeast extract 2.5%, beef extract 0.5%, sucrose 2.5%, malt extract 0.25% and ferric
chloride 2.5% were the optimal levels for maximal clavulanic acid production (19.37 mg /gds) which were validated through experiments.
Segmentation of cysts in kidney and 3 d volume calculation from ct images ijcga
This paper proposes a segmentation method and a three-dimensional (3-D) volume calculation method of
cysts in kidney from a number of computer tomography (CT) slice images. The input CT slice images
contain both sides of kidneys. There are two segmentation steps used in the proposed method: kidney
segmentation and cyst segmentation. For kidney segmentation, kidney regions are segmented from CT slice
images by using a graph-cut method that is applied to the middle slice of input CT slice images. Then, the
same method is used for the remaining CT slice images. In cyst segmentation, cyst regions are segmented
from the kidney regions by using fuzzy C-means clustering and level-set methods that can reduce noise of
non-cyst regions. For 3-D volume calculation, cyst volume calculation and 3-D volume visualization are
used. In cyst volume calculation, the area of cyst in each CT slice image equals to the number of pixels in
the cyst regions multiplied by spatial density of CT slice images, and then the volume of cysts is calculated
by multiplying the cyst area and thickness (interval) of CT slice images. In 3-D volume visualization, a 3-D
visualization technique is used to show the distribution of cysts in kidneys by using the result of cyst volume
calculation. The total 3-D volume is the sum of the calculated cyst volume in each CT slice image.
Experimental results show a good performance of 3-D volume calculation. The proposed cyst segmentation
and 3-D volume calculation methods can provide practical supports to surgery options and medical
practice to medical students
Application of 3D Modeling for Preoperative Planning and Intra Operative Navigation during Procedures on the Organs of Retroperitoneal Space by Alexey A Rozhentsov in Experimental Techniques in Urology & Nephrology
CT scans use X-rays and computer calculations to produce detailed cross-sectional images of the body's internal structures. A CT scan of the urinary system can detect tumors, masses, stones, or cysts. The test is performed in a radiology department where the patient lies on a table that slides into a CT scanner. Dye may be injected into the patient's vein to enhance image quality. CT scans can distinguish between solid and liquid tissues and provide valuable information for examining kidney tumors and other abnormalities of the urinary tract. Risks of CT scanning are generally low but may include minor reactions to dye in rare cases more severe complications.
MEDICAL IMAGE PROCESSING METHODOLOGY FOR LIVER TUMOUR DIAGNOSISijsc
Apply the Image processing techniques to analyse the medical images may assist medical professionals as well as patients, especially in this research apply the algorithms to diagnose the liver tumours from the abdominal CT image. This research proposes a software solution to illustrate the automated liver
segmentation and tumour detection using artificial intelligent techniques. Evaluate the results of the liver segmentation and tumour detection, in-cooperation with the radiologists by using the prototype of the proposed system. This research overcomes the challenges in medical image processing. The 100 samples
collected from ten patients and received 90% accuracy rate.
Medical Image Processing Methodology for Liver Tumour Diagnosis ijsc
Apply the Image processing techniques to analyse the medical images may assist medical professionals as well as patients, especially in this research apply the algorithms to diagnose the liver tumours from the abdominal CT image. This research proposes a software solution to illustrate the automated liver segmentation and tumour detection using artificial intelligent techniques. Evaluate the results of the liver segmentation and tumour detection, in-cooperation with the radiologists by using the prototype of the proposed system. This research overcomes the challenges in medical image processing. The 100 samples collected from ten patients and received 90% accuracy rate.
The International Journal of Engineering & Science is aimed at providing a platform for researchers, engineers, scientists, or educators to publish their original research results, to exchange new ideas, to disseminate information in innovative designs, engineering experiences and technological skills. It is also the Journal's objective to promote engineering and technology education. All papers submitted to the Journal will be blind peer-reviewed. Only original articles will be published.
Individually Optimized Contrast-Enhanced 4D-CT for Radiotherapy Simulation in...Wookjin Choi
Purpose/Objectives: To develop an individually optimized contrast-enhanced (CE) 4D-CT for radiotherapy simulation in pancreatic adenocarcinoma (PDA).
Materials/Methods: Ten PDA patients were enrolled and underwent three CT scans: a 4D-CT immediately following a CE 3D-CT, and an individually optimized CE 4D-CT using a test injection to estimate the peak contrast enhancement time and to optimize the delay time. Three physicians contoured the tumor and pancreatic tissues. We compared image quality scores, tumor volume, motion, image noise, tumor-to-pancreas contrast, and contrast-to- noise ratio (CNR) in the three CTs. We also evaluated inter-observer variations in contouring the tumor using simultaneous truth and performance level estimation (STAPLE).
Results: The average image quality scores for CE 3D-CT and CE 4D-CT were comparable (4.0 and 3.8, p=0.47), and both were significantly better than that for 4D-CT (2.6, p<0.001). The tumor-to- pancreas contrast in CE 3D-CT and CE 4D-CT were comparable (15.5 and 16.7 HU, p=0.71), and the later was significantly higher than that in 4D-CT (9.2 HU, p=0.03). Image noise in CE 3D-CT (12.5 HU) was significantly lower than that in CE 4D-CT (22.1 HU, p<0.001) and 4D-CT (19.4 HU, p=0.005). The CNR in CE 3D-CT and CE 4D-CT were comparable (1.4 and 0.8, p=0.23), and the former was significantly better than that in 4D-CT (0.6, p=0.04). The average tumor volume was smaller in CE 3D-CT (29.8 cm 3 ) and CE 4D-CT (22.8 cm 3 ) than in 4D-CT (42.0 cm 3 ), though the differences were not statistically significant. The tumor motion was comparable in 4D-CT and CE 4D-CT (7.2 and 6.2 mm, p=0.23). The inter-observer variations were comparable in CE 3D-CT and CE 4D-CT (Jaccard index 66.0% and 61.9%), and the former was significantly smaller than that of 4D-CT (55.6%, p=0.047).
Conclusions: The CE 4D-CT demonstrated largely comparable characteristics to the CE 3D-CT. It has high potential for simultaneously delineating the tumor and quantifying the tumor motion with a single scan.
A Survey on Disease Prediction from Retinal Colour Fundus Images using Image ...ijcnes
The aim of this survey is to list the various disease predictions from retinal funds images and various methods used to detect the disease. This paper gives a detailed description about the various diseases predicted in retina by comparing retinal funds image structure. Till now, the prediction of various diseases such as diabetic retinopathy, cardiovascular disease and other eye problems had been predicted by using retinal funds images. Next, a comparative study of the various methods followed using image processing to find out the diseases from retinal funds images, is provided. The basic matrices observed to predict the diseases are optic disc,nerve cup and rim. To find the differences in the basic matrices, image processing techniques such as mask generation, colour normalization, edge detection, contrast enhancement are used. The datasets that are used for retinal image inputs are STARE, DRIVE, ONHSD, ARIA, IMAGERET. The survey at the end, discusses the future work for the possibilities of predicting gastreointestinal problems via retinal funds images.
Performance analysis of retinal image blood vessel segmentationacijjournal
The retinal image diagnosis
is an important methodology for diabetic retinopathy detection and analysis. in
this paper, the morphological operations and svm classifier are used to detect and segment the blood
vessels from the retinal image. the proposed system consists of three stage
s
-
first is preprocessing of retinal
image to separate the green channel and second stage is retinal image enhancement and third stage is
blood vessel segmentation using morphological operations and svm classifier. the performance of the
proposed system is
analyzed using publicly available dataset
Similar to MahdiMarsousi_PhD_FOE_PresentationSlides (20)
Performance analysis of retinal image blood vessel segmentation
MahdiMarsousi_PhD_FOE_PresentationSlides
1. Automated Kidney Segmentation In 3D Ultrasound Imagery,
and its Application in Computer-assisted Trauma Diagnosis
Final PhD Oral Examination - Presentation Slides
September 1st , 2016
Mahdi Marsousi
Supervisor: Prof. Konstantinos N. Plataniotis
2. Introduction
Abdominal trauma: injuries to abdomen, either blunt or penetrating, resulting
in severe blood loss.
Importance: massive internal bleeding quickly threats patient’s life.
Cure: rapid diagnosis and surgery
[1]
[1] http://www.radiologyassistant.nl/en/p466181ff61073/acute-abdomen-role-of-ct-in-trauma.html
[2] http://www.wikidoc.org/index.php/Abdominal_trauma
[2]
Slide #1
3. Diagnosis by 3D ultrasound (3DUS)
Ultrasound imagery is the preferred imaging modality for diagnosing
hemodynamically unstable patients, because it is portable.
It is also called: focused assessment with sonography for trauma “FAST”.
2D ultrasound is the popular diagnostic tool.
3DUS imagery is key to design computer-assisted diagnosis, because:
a) detecting and localizing internal organs in 3D space is possible by 3DUS;
b) 3DUS facilitates measuring the volume of internal bleeding.
Slide #2
4. :Focus of this presentation
FAST exam
FAST exam: rapid bedside ultrasound scan to find free fluids, as
indication of internal bleeding, around abdominal organs [1].
Six major abdominal views associated with FAST exam.
Right Upper Quadrant view (2), also called the Morison’s pouch
view, is the most relevant one, because:
It is the most sensitive view to abdominal bleeding
It entirely shows the right kidney, and a portion of liver and diaphragm[1].
Abdominal bleeding usually places between the right kidney and liver [1].
Therefore, detecting and segmenting the kidney shape is the key
for computer-assisted trauma diagnosis.
[1] Heller et al. Ultrasound use in trauma: the fast exam. Academic Emergency Medicine, 14(6):525–525, 2007.
[2] Ingeman et al. Emergency physician use of ultrasonography in blunt abdominal trauma. Academic Emergency
Medicine, 3(10):931–937, 1996.
Slide #3
5. Motivation, problem definition, & challenges
Motivation:
• In emergency, only paramedics provide medical service for trauma patients.
• Usually paramedics are not capable to do FAST exam.
• Thus, computer-assisted solution can help paramedics to conduct trauma diagnosis.
Problem definition:
Slide #4
6. 3DUS dataset
Slide #5
Training set: 6 with-kidney and 6 without-kidney images.
Evaluation set: 15 with-kidney and 15 without-kidney from healthy volunteers,
and 8 with-kidney images from abnormal patients.
Images of abnormal patients represent morphological changes to the kidney shape.
With-kidney image:
taken from Morison’s pouch view
Without-kidney image:
taken from other views.
9. Overview on kidney detection
Definition: searching within 3D image domain to find kidney shape to answer:
• whether kidney shape exists in a 3DUS image?
• if yes, what is its alignment?
State-of-the-art:
Proposed solutions:
Name Methodology Advantage Disadvantage
Noll et al.
[1]
- applies volume enhancement
- uses redial rays to find kidney shape mass-center
robust against speckle &
low-contrast intensity
may wrongly detect other
structures instead of kidney
[1] Noll et al. Automated kidney detection and segmentation in 3d ultrasound, in Clinical Image-Based
Proc. Translational Research in Medical Imag. Springer, 2014, pp. 83–90.
Slide #7
10. Definition: mathematical representation of kidney shape to add shape prior in kidney detection
Proposed shape modeling: complex-valued implicit shape model (CVISM)
Ψ 𝑋 = 𝜓 𝑃𝑆 𝑋 + 𝜓 𝐾𝐶 𝑋 − 𝑖 ⋅ 𝜓 𝑅𝑀 𝑋 ,
𝜓 𝑝𝑠, 𝜓 𝐾𝐶, and 𝜓 𝑅𝑀 are real-positive functions, defining voxel’s membership to Pyelocalyceal System,
Kidney Capsule, and Renal Medulla, respectively.
Generating regions: using ground truth data of training set of with-kidney images.
Kidney shape model
Slide #8
Kidney
Capsule
Renal
Medulla
Pyelocalyceal
System
Real values are used to
model bright regions:
𝐾𝐶: Kidney Capsule
𝑃𝑆: Pyelocalyceal System
Imaginary values are used
to model dark region:
𝑅𝑀: Renal Medulla
11. Objective: registering kidney CVISM on 3DUS images, to detect kidney shape and
estimate its alignment.
Challenges:
• Partial occlusion of kidney shape
• Non-kidney structures with similar appearance to the kidney shape
Components:
• Global deformation based on similarity transformation,
• Similarity metric,
• optimization algorithm.
Global deformation: similarity transformation (shape-preserving)
𝑌 = 𝑆𝑇 𝑝𝑠𝑡,1
𝑋 + 𝑝𝑠𝑡,2
Shape-to-volume registration
Slide #9
Orientations & scaling
𝑝𝑠𝑡,1 = 𝜃𝑥,𝜃𝑦,𝜃𝑧,𝑠
𝑇
Translations
𝑝𝑠𝑡,2 = 𝑡𝑥,𝑡𝑦,𝑡𝑧
𝑇
CVISM domain Image domain
12. Definition: quantifies similarity of deformed kidney CVISM and image data.
Proposed similarity metric: Regularized complex normalized cross-correlation (RCNCC)
Formulation:
Γ 𝑝𝑠𝑡,1, 𝑝𝑠𝑡,2
∗
= max
𝑝𝑠𝑡,2
∗ ∈ΩV
𝑠𝑢𝑏
1
Λ 𝑝𝑠𝑡,1, 𝑝𝑠𝑡,2
⋅
max 0,ℜ Σ𝐼 𝑝𝑠𝑡,1, 𝑝𝑠𝑡,2
Σ𝐼𝐼
ℜ
𝑝𝑠𝑡,1
⋅
max 0,ℑ Σ𝐼 𝑝, 𝑋, 𝑉
Σ𝐼𝐼
ℑ
𝑝𝑠𝑡,1
Λ 𝑝𝑠𝑡,1, 𝑝𝑠𝑡,2 increases as kidney CVISM aligns out of the ultrasound field of view.
RCNCC similarity metric
Regularization
Term
Checking similarity of image data
with Kidney Capsule and
Pyelocalyceal System
Checking similarity of image
data with Renal Medulla
Robustness against
Partial kidney shape occlusion
Considering multi-regional structure of the kidney shape,
max 𝑎, 𝑏 : selects maximum of 𝑎 and 𝑏.
“max”s are used to avoid multiplication of two negative values in RCNCC.
ℜ{𝑎} and ℑ{𝑏} extract real part of 𝑎 and imaginary part of 𝑏.
Slide #10
13. Registration problem
Objective: Finding 𝑝𝑠𝑡,1
∗
and 𝑝𝑠𝑡,2
∗
which provides a maximum RCNCC for input image.
Optimization problem:
Γ∗, 𝑝𝑠𝑡,1
∗
, 𝑝𝑠𝑡,2
∗
= max
𝑝𝑠𝑡,1
Γ 𝑝𝑠𝑡,1, 𝑝𝑠𝑡,2
∗
Optimization algorithm:
• initialization: searching for best seed point from a
set of seed points to initialize registration.
• iterative improvement: iteratively updating
registration parameters using Gradient Descent.
Figure shows RCNCC metric versus 𝜃 𝑥 and 𝜃𝑧.
Yellow regions correspond to desirable registration solutions.
The gray stars are seed point.
Red star is selected seed point.
Black arrows show iterations of Gradient descent.
Slide #11
14. Processing pipeline of kidney detection
• Γ 𝑡ℎ is threshold on similarity metric to decide whether the kidney shape exists or not.
• It is obtained using training set, as Γ 𝑡ℎ = 3.5.
Slide #12
15. Experimentation
Objective: to evaluate shape-based and atlas-based kidney detection, compared to Noll et al. [1].
Dataset:
• 15 with-kidney and 15 without-kidney images of healthy volunteers
• 8 with-kidney images abnormal patients
• 3DUS image simulator of Morison’s pouch
Comparison metrics:
• accuracy: 𝐴𝑐𝑐 𝐾𝐷 = 100% ⋅
𝑁 𝑇𝑃+𝑁 𝑇𝑁
𝑁 𝑇𝑃+𝑁 𝐹𝑁+𝑁 𝑇𝑁+𝑁 𝐹𝑃
,
• sensitivity: 𝑆𝑒𝑛𝑠 𝐾𝐷 =
NTP
𝑁 𝑇𝑃+𝑁 𝐹𝑁
,
• specificity: 𝑆𝑝𝑒𝑐 𝐾𝐷 =
𝑁 𝑇𝑁
𝑁 𝑇𝑁+𝑁 𝐹𝑃
.
𝑁 𝑇𝑃, 𝑁 𝑇𝑁, 𝑁𝐹𝑃, and 𝑁𝐹𝑁 are numbers of true positive, true negative, false positive, false negative detections.
[1] Noll et al. Automated kidney detection and segmentation in 3d ultrasound, in Clinical Image-Based
Proc. Translational Research in Medical Imag. Springer, 2014, pp. 83–90.
Slide #13
16. Visibility portion: 100 100 100 100 100 100 100 100 100 50 70 95 100 100 100 95 70 45 55 75 90 100 100 100 95 75 55
Sensitivity analysis
Ultrasound volume simulator is used to analyze sensitivity to kidney shape’s deformation and occlusion.
Both methods provides high robustness toward kidney shape translation.
Atlas-based method provides more accurate estimation of deformation (except for Δ𝜃 𝑥)
Slide #14
40 70 95 100 100 100 85 65 45 50 60 85 100 100 100 90 60 4560 80 95 100 100 100 95 85 65Visibility portion:
17. Kidney detection accuracy
Using with-kidney and without-kidney images of healthy volunteers:
• Shape-based and atlas-based provide higher accuracy, compared to Noll et al., because:
1) higher specificity: involving multi-structural regions of kidney shape,
2) higher sensitivity: regularization factor provides robustness against kidney shape’s occlusion.
• Atlas-based shows higher accuracy than shape-based because of using texture information.
Using actual ultrasound volumes of abnormal patients:
Accuracy is reduced, because:
different device settings from healthy volunteers,
Morphological changes of RUQ view in abnormal patients.
Method 𝑵 𝑻𝑷 𝑵 𝑻𝑵 𝑵 𝑭𝑷 𝑵 𝑭𝑵 Accuracy (%) Sensitivity Specificity
Noll et al. 9 11 4 6 66.67 0.60 0.73
Shape-based kidney detection 14 12 3 1 86.67 0.93 0.80
Atlas-based kidney detection 15 13 2 0 93.33 1 0.87
Slide #15
Method 𝑵 𝑻𝑷 𝑵 𝑭𝑵 Accuracy (%)
Noll et al. [1] 5 3 62.5
Shape-based 5 3 62.5
Atlas-based 6 2 75.0
18. Examples of kidney detection
Blue region: Renal Medulla
Red region: Kidney Capsule/Pyelocalyceal System
Slide #16
20. Overview on automated kidney segmentation
Problem definition: automatically segmenting the kidney shape in 3DUS images.
State-of-the-art:
Proposed method: complex-valued regional level-set with shape prior (CVRLS-SP)
• Complex-valued structure is used to add multi-regional structure into segmentation.
• Adding multi-regional structure is important because it improves segmentation specificity.
Name Methodology Advantage Disadvantage
Noll
et al. [1]
Radial ray trace + fast
marching + edge-based level-
set
- Robust against speckle and low-contrast
intensity profile
- Automated initialization
- Not robust against kidney deformation
- High-computational cost
MRF-AC
[2]
2D active contour + Markov
random field (MRF) + 3D
reconstruction
- Low computational cost - Manual initialization
- Discontinuity along z-axis
[1] Noll et al. Automated kidney detection and segmentation in 3d ultrasound, in Clinical Image-Based Proc.
Translational Research in Medical Imag. Springer, 2014, pp. 83–90.
[2] Martn-Fernndez et al., An approach for contour detection of human kidneys from ultrasound images
using markov random fields and active contours, Med. Image Anal., 1–23, 2005.
Slide #17
21. CVRLS-SP representation
Mathematical representation of regions in CVRLS-SP:
𝑏𝑟 : 𝑋 ∈ 𝑝𝑦𝑒𝑙𝑜𝑐𝑎𝑙𝑦𝑐𝑒𝑎𝑙 𝑠𝑦𝑠𝑡𝑒𝑚 𝑜𝑟 𝑘𝑖𝑑𝑛𝑒𝑦 𝑐𝑎𝑝𝑠𝑢𝑙𝑒, 𝑖𝑓 ℜ 𝜙 𝑋 > 0,
𝑑𝑟 : 𝑋 ∈ 𝑟𝑒𝑛𝑎𝑙 𝑚𝑒𝑑𝑢𝑙𝑙𝑎, 𝑖𝑓 ℑ 𝜙 𝑋 > 0,
𝑏𝑔 : 𝑋 ∈ 𝑏𝑎𝑐𝑘𝑔𝑟𝑜𝑢𝑛𝑑, 𝑜𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒.
where 𝜙 is level-set function.
Prior shape: (𝜙𝑠) is generated by aligning CVISM on detected kidney shape:
𝜙𝑠 𝑋 = 2 Ψ 𝑆𝑇 𝑝 𝑠𝑡,1
∗ 𝑋 + 𝑝𝑠𝑡,2
∗
> 0 − 1 + 𝑖 , ∀𝑋 ∈ Ω 𝑉
where 𝑆𝑇 𝑝 𝑠𝑡,1
∗ 𝑋 + 𝑝𝑠𝑡,2
∗
places kidney CVISM, Ψ, on detected kidney shape.
level-set function, 𝜙, is initialized by prior shape: 𝜙 𝑋; 𝑡 = 0 = 𝜙𝑠 𝑋 , 𝑡 is iteration.
Slide #18
22. CVRLS-SP evolution
[1] Chan and Zhu. Level set based shape prior segmentation. IEEE CVPR, vol 2, pp 1164–1170, 2005..
Slide #19
Conventional regional level-set with shape prior defines energy function as [1],
𝐹 𝑐, 𝜙, 𝜙𝑠 𝐴𝑇 𝑝 𝑎𝑓
, 𝑉 = 𝜆 ⋅ 𝐹𝑆𝑃 𝜙, 𝜙𝑠 𝐴𝑇 𝑝 𝑎𝑓
+ 𝜇 ⋅ 𝐹𝑖𝑛𝑡 𝜙 + 𝛾 ⋅ 𝐹𝑒𝑥𝑡(𝑐, 𝜙, 𝑉)
𝐹𝑆𝑃 𝜙, 𝜙𝑠 𝐴𝑇 𝑝 𝑎𝑓
: shape prior energy,
𝐹𝑖𝑛𝑡 𝜙 : internal energy, controlling smoothness.
𝐹𝑒𝑥𝑡(𝑐, 𝜙, 𝑉): external energy, pushing level-set toward region of interest.
𝑐: average intensity level of region of interest, 𝐴𝑇 𝑝 𝑎𝑓
: affine transformation.
𝜆, 𝜇, 𝛾: Lagrange multipliers
Contribution: CVRLS-SP’s energy functional is defined as follows,
𝐹 𝑐 𝑏𝑟, 𝑐 𝑑𝑟, 𝜙, 𝜙𝑠 𝐴𝑇 𝑝 𝑎𝑓
, 𝑉 = 𝜆 ⋅ 𝐹𝑆𝑃
𝑏𝑟
ℜ{𝜙}, ℜ{𝜙𝑠 𝐴𝑇 𝑝 𝑎𝑓
} + 𝜆 ⋅ 𝐹𝑆𝑃
𝑑𝑟
ℑ{𝜙}, ℑ{𝜙𝑠 𝐴𝑇 𝑝 𝑎𝑓
}
+𝜇 ⋅ 𝐹𝑖𝑛𝑡 𝜙 + 𝛾 ⋅ 𝐹𝑒𝑥𝑡
𝑏𝑟
(𝑐 𝑏𝑟, ℜ{𝜙}, 𝑉) + 𝛾 ⋅ 𝐹𝑒𝑥𝑡
𝑑𝑟
(𝑐 𝑑𝑟, ℑ{𝜙}, 𝑉)
• Multi-regional segmentation is added By dividing both FSP and Fext into br and dr terms.
24. Experimentation
Objective: to evaluate proposed kidney segmentation compared to Noll et al. [1] and MRF-AC. [2]
Dataset: evaluation set of actual ultrasound volumes
Comparison metrics:
• Dice’s similarity coefficient (DSC)=
2𝑇𝑃
2𝑇𝑃+𝐹𝑁+𝐹𝑃
,
• Accuracy metric (ACC)=
𝑇𝑃+𝑇𝑁
𝑇𝑃+𝑇𝑁+𝐹𝑃+𝐹𝑁
× 100% ,
• Sensitivity measure (SENS)=
𝑇𝑃
𝑇𝑃+𝐹𝑁
,
• Specificity measure (SPEC)=
𝑇𝑁
𝑇𝑁+𝐹𝑃
.
Parameter setting:
[1] Noll et al. Automated kidney detection and segmentation in 3d ultrasound, in Clinical Image-Based
Proc. Translational Research in Medical Imaging, Springer, 2014, pp. 83–90.
[2] Martin-Fernandez et al., An approach for contour detection of human kidneys from ultrasound images
using Markov random fields and active contours, Medical Image Analysis, 1–23, 2005.
Slide #21
Name 𝜆 𝜇 𝛾 𝑁𝑖𝑡𝑟 𝑡 𝑚𝑎𝑥 𝜖
Value 1 0.1 0.05 5 50 10
25. Specificity of CVRLS-SP is higher because:
• capability of segmenting multi-regional structure,
• using shape prior.
Box-plot: shows statistical variation of DSC of the methods:
minimum accuracy of CVRLS-SP is higher that maximum accuracy of both MRF-AC and Noll et al.
Kidney segmentation accuracy
Method
𝑫𝑺𝑪 𝑨𝑪𝑪 𝑺𝑬𝑵𝑺 𝑺𝑷𝑬𝑪
𝜇 𝜎 𝜇 𝜎 𝜇 𝜎 𝜇 𝜎
CVRLS-SP 0.8143 0.0408 97.48 0.72 0.7863 0.0814 0.9890 0.0060
Noll et al. 0.4207 0.0795 85.48 2.77 0.7024 0.0912 0.8678 0.0326
MRF-AC 0.5921 0.1457 93.10 2.74 0.6947 0.2132 0.9490 0.0246
𝜇: mean, 𝜎:standard deviation
Slide #22
CVRLS-SP MRFAC Noll et al.
0.3
0.4
0.5
0.6
0.7
0.8
0.9
Dice'sCoefficient(DSC)
26. Examples of kidney segmentation
Fourth column:
Yellow, red, and green colors are TP, FP, and FN regions. Slide #23
Original image Detected kidney Segmented
kidney regions
Comparing
automated segmentation
vs. ground-truth
3D view
Second and third columns:
Blue and red regions indicate Renal Medulla and
Pyelocalyceal System/Kidney Capsule, respectively.
27. Conclusions & Future Work
In this presentation, importance of computer-assisted solution for diagnosing
trauma patients by paramedics in emergency situation was discussed.
Shape-based and atlas-based kidney detection methods were introduced.
Automated kidney segmentation was introduced, which used kidney detection
module to automatically initialize segmentation process.
Kidney detection and segmentation accuracies of proposed methods were compared
to state-of-the-art, and evaluations and analysis confirmed improved accuracy using
proposed methods.
Future work:
Using the automated kidney segmentation to automatically detect free fluids.
Slide #24
28. Publications
Journal Papers:
[1] M. Marsousi, K. Plataniotis, and S. Stergiopoulos, “An Automated Approach for Kidney Segmentation in Three-Dimensional Ultrasound Images”,
IEEE Journal of Biomedical and Health Informatics, DOI: 10.1109/JBHI.2016.2580040, (Date of publication: June 13th 2016)
[2] M. Marsousi, K. Plataniotis, and S. Stergiopoulos, “Computer-Assisted 3D Ultrasound Probe Placement for Emergency Healthcare Applications”,
IEEE Transactions on Industrial Informatics, DOI: 10.1109/TII.2016.2569522, (Date of publication: May 18th 2016)
[3] M. Marsousi, K. Plataniotis, and S. Stergiopoulos, “Kidney Detection in 3D Ultrasound Imagery Based on Shape and Texture Priors”, to be
submitted at IEEE Transaction on Biomedical Engineering (T-BME) on September 2016.
Conference Papers:
[4] M. Marsousi, X. Lee, and K. Plataniotis, “Shape-included Label-Consistent Discriminative Dictionary Learning: An Approach to Detect and
Segment Multi-Class Objects in Image”, IEEE international conference on Image Processing (ICIP), 2016, accepted.
[5] M. Marsousi, K. Plataniotis, and S. Stergiopoulos. “Atlas-based segmentation of abdominal organs in 3D ultrasound, and its application in
automated kidney segmentation.”, IEEE International conference in Engineering in Medicine and Biology Society (EMBC), pp. 2001-2005, 2015.
[6] M. Marsousi and K. Plataniotis, “Binomial classification based on DLENE features in sparse representation: Application in kidney detection in
3D ultrasound.” IEEE International Conference in Acoustics, Speech and Signal Processing (ICASSP), pp. 1017-1021, 2015.
[7] M. Marsousi, K. Plataniotis, and S. Stergiopoulos, “Shape-based kidney detection and segmentation in three-dimensional abdominal ultrasound
images”. IEEE International conference in Engineering in Medicine and Biology Society (EMBC), pp. 2890-2894, 2014.
[8] M. Marsousi, K. Plataniotis, and S. Stergiopoulos. “A multi-steps segmentation approach for 3D ultrasound images using the combination of 3D-
Snake and Level-Set.” IEEE International Conference in Digital Signal Processing (DSP), pp. 1-4, 2013.
US patent:
[9] S. Stergiopoulos, P. Shek, K. Plataniotis, and M. Marsousi. “Computer aided diagnosis for detecting abdominal bleeding with 3D ultrasound
imaging.” U.S. Patent Application 14/159,744, filed January 21, 2014.