This document presents a method for brain tumor segmentation using multi-level Otsu thresholding and the Chan-Vese active contour model. The method first applies multi-level Otsu thresholding to preprocessed MRI images to obtain the initial initialization area for the active contour model. Specifically, it uses 3-level Otsu thresholding. It then uses the Chan-Vese active contour model to segment the tumor area, starting from the initialized area. The method is tested on 85 brain MRI images and achieves a Dice similarity coefficient of 0.7856, outperforming other compared methods.
Brain tumor visualization for magnetic resonance images using modified shape...IJECEIAES
3D visualization plays an essential role in medical diagnosis and setting treatment plans especially for brain cancer. There have been many attempts for brain tumor reconstruction and visualization using various techniques. However, this problem is still considered unsolved as more accurate results are needed in this critical field. In this paper, a sequence of 2D slices of brain magnetic resonance Images was used to reconstruct a 3D model for the brain tumor. The images were automatically segmented using wavelet multi-resolution expectation maximization algorithm. Then, the inter-slice gaps were interpolated using the proposed modified shape-based interpolation method. The method involves three main steps; transferring the binary tumor images to distance images using a suitable distance function, interpolating the distance images using cubic spline interpolation and thresholding the interpolated values to get the reconstructed slices. The final tumor is then visualized as a 3D isosurface. We evaluated the proposed method by removing an original slice from the input images and interpolating it, the results outperform the original shape-based interpolation method by an average of 3% reaching 99% of accuracy for some slice images.
1) The document presents an integrated technique for detecting brain tumors in MRI images that combines modified texture-based region growing segmentation and edge detection.
2) The technique first performs pre-processing on MRI images, then uses modified texture-based region growing to segment regions. It then applies edge detection to extract the tumor region.
3) Experimental results show the integrated technique provides more accurate tumor detection compared to individual segmentation methods and manual segmentation.
SEGMENTATION OF MAGNETIC RESONANCE BRAIN TUMOR USING INTEGRATED FUZZY K-MEANS...ijcsit
Segmentation is a process of partitioning the image into several objects. It plays a vital role in many fields
such as satellite, remote sensing, object identification, face tracking and most importantly in medical field.
In radiology, magnetic resonance imaging (MRI) is used to investigate the human body processes and
functions of organisms. In hospitals, this technique has been using widely for medical diagnosis, to find the
disease stage and follow-up without exposure to ionizing radiation.Here in this paper, we proposed a novel
MR brain image segmentation method for detecting the tumor and finding the tumor area with improved
performance over conventional segmentation techniques such as fuzzy c means (FCM), K-means and even
that of manual segmentation in terms of precision time and accuracy. Simulation performance shows that
the proposed scheme has performed superior to the existing segmentation methods.
This document reviews various automated techniques that have been developed for brain tumor detection. It summarizes research done by several researchers on methods like sequential floating forward selection, color coding schemes using brain atlases, neural networks, region growing segmentation combined with area calculation, symmetry analysis of tumor areas in MRI images, and combining clustering and classification algorithms. The paper concludes that image segmentation plays an important role in medical applications like tumor diagnosis and that more robust techniques are needed for high accuracy and reliability.
This document provides a literature survey on methods for detecting brain tumors from MRI images. It discusses several segmentation techniques that have been used for this purpose, including thresholding, edge-based, region-based, k-means clustering, fuzzy c-means clustering, and optimization methods like ant colony optimization, genetic algorithms, and particle swarm optimization. The document reviews related work comparing these methods and evaluates their performance based on metrics like PSNR and RMSE. It concludes that while no single universal method exists, fuzzy c-means is well-suited for medical image segmentation tasks due to its simplicity and ability to provide faster clustering.
Literature Survey on Detection of Brain Tumor from MRI Images IOSR Journals
This document provides a literature survey on methods for detecting brain tumors from MRI images. It discusses several segmentation and clustering techniques that have been used for this purpose, including thresholding, edge-based segmentation, region-based segmentation, fuzzy c-means clustering, and k-means clustering. The document also reviews related work applying these methods and evaluates their effectiveness at automatically detecting and segmenting brain tumors from MRI data.
Automatic Diagnosis of Abnormal Tumor Region from Brain Computed Tomography I...ijcseit
The research work presented in this paper is to achieve the tissue classification and automatically
diagnosis the abnormal tumor region present in Computed Tomography (CT) images using the wavelet
based statistical texture analysis method. Comparative studies of texture analysis method are performed
for the proposed wavelet based texture analysis method and Spatial Gray Level Dependence Method
(SGLDM). Our proposed system consists of four phases i) Discrete Wavelet Decomposition (ii)
Feature extraction (iii) Feature selection (iv) Analysis of extracted texture features by classifier. A
wavelet based statistical texture feature set is derived from normal and tumor regions. Genetic Algorithm
(GA) is used to select the optimal texture features from the set of extracted texture features. We construct
the Support Vector Machine (SVM) based classifier and evaluate the performance of classifier by
comparing the classification results of the SVM based classifier with the Back Propagation Neural network
classifier(BPN). The results of Support Vector Machine (SVM), BPN classifiers for the texture analysis
methods are evaluated using Receiver Operating Characteristic (ROC) analysis. Experimental results
show that the classification accuracy of SVM is 96% for 10 fold cross validation method. The system
has been tested with a number of real Computed Tomography brain images and has achieved satisfactory
results.
IRJET-A Review on Brain Tumor Detection using BFCFCM AlgorithmIRJET Journal
The document presents a review of brain tumor detection using the BFCFCM clustering algorithm. It begins with an introduction to brain tumors and MRI imaging. It then reviews several existing techniques for brain tumor detection using artificial neural networks, linear discriminant analysis, neuro-fuzzy systems, and region growing segmentation with watershed algorithms. The document proposes a method using pre-processing, skull masking, segmentation with an advanced fuzzy c-means algorithm, feature extraction through thresholding, and an SVM classifier. Segmentation partitions the MRI image into regions/objects of interest like the tumor. Feature extraction analyzes the segmented regions to characterize the tumor for classification.
Brain tumor visualization for magnetic resonance images using modified shape...IJECEIAES
3D visualization plays an essential role in medical diagnosis and setting treatment plans especially for brain cancer. There have been many attempts for brain tumor reconstruction and visualization using various techniques. However, this problem is still considered unsolved as more accurate results are needed in this critical field. In this paper, a sequence of 2D slices of brain magnetic resonance Images was used to reconstruct a 3D model for the brain tumor. The images were automatically segmented using wavelet multi-resolution expectation maximization algorithm. Then, the inter-slice gaps were interpolated using the proposed modified shape-based interpolation method. The method involves three main steps; transferring the binary tumor images to distance images using a suitable distance function, interpolating the distance images using cubic spline interpolation and thresholding the interpolated values to get the reconstructed slices. The final tumor is then visualized as a 3D isosurface. We evaluated the proposed method by removing an original slice from the input images and interpolating it, the results outperform the original shape-based interpolation method by an average of 3% reaching 99% of accuracy for some slice images.
1) The document presents an integrated technique for detecting brain tumors in MRI images that combines modified texture-based region growing segmentation and edge detection.
2) The technique first performs pre-processing on MRI images, then uses modified texture-based region growing to segment regions. It then applies edge detection to extract the tumor region.
3) Experimental results show the integrated technique provides more accurate tumor detection compared to individual segmentation methods and manual segmentation.
SEGMENTATION OF MAGNETIC RESONANCE BRAIN TUMOR USING INTEGRATED FUZZY K-MEANS...ijcsit
Segmentation is a process of partitioning the image into several objects. It plays a vital role in many fields
such as satellite, remote sensing, object identification, face tracking and most importantly in medical field.
In radiology, magnetic resonance imaging (MRI) is used to investigate the human body processes and
functions of organisms. In hospitals, this technique has been using widely for medical diagnosis, to find the
disease stage and follow-up without exposure to ionizing radiation.Here in this paper, we proposed a novel
MR brain image segmentation method for detecting the tumor and finding the tumor area with improved
performance over conventional segmentation techniques such as fuzzy c means (FCM), K-means and even
that of manual segmentation in terms of precision time and accuracy. Simulation performance shows that
the proposed scheme has performed superior to the existing segmentation methods.
This document reviews various automated techniques that have been developed for brain tumor detection. It summarizes research done by several researchers on methods like sequential floating forward selection, color coding schemes using brain atlases, neural networks, region growing segmentation combined with area calculation, symmetry analysis of tumor areas in MRI images, and combining clustering and classification algorithms. The paper concludes that image segmentation plays an important role in medical applications like tumor diagnosis and that more robust techniques are needed for high accuracy and reliability.
This document provides a literature survey on methods for detecting brain tumors from MRI images. It discusses several segmentation techniques that have been used for this purpose, including thresholding, edge-based, region-based, k-means clustering, fuzzy c-means clustering, and optimization methods like ant colony optimization, genetic algorithms, and particle swarm optimization. The document reviews related work comparing these methods and evaluates their performance based on metrics like PSNR and RMSE. It concludes that while no single universal method exists, fuzzy c-means is well-suited for medical image segmentation tasks due to its simplicity and ability to provide faster clustering.
Literature Survey on Detection of Brain Tumor from MRI Images IOSR Journals
This document provides a literature survey on methods for detecting brain tumors from MRI images. It discusses several segmentation and clustering techniques that have been used for this purpose, including thresholding, edge-based segmentation, region-based segmentation, fuzzy c-means clustering, and k-means clustering. The document also reviews related work applying these methods and evaluates their effectiveness at automatically detecting and segmenting brain tumors from MRI data.
Automatic Diagnosis of Abnormal Tumor Region from Brain Computed Tomography I...ijcseit
The research work presented in this paper is to achieve the tissue classification and automatically
diagnosis the abnormal tumor region present in Computed Tomography (CT) images using the wavelet
based statistical texture analysis method. Comparative studies of texture analysis method are performed
for the proposed wavelet based texture analysis method and Spatial Gray Level Dependence Method
(SGLDM). Our proposed system consists of four phases i) Discrete Wavelet Decomposition (ii)
Feature extraction (iii) Feature selection (iv) Analysis of extracted texture features by classifier. A
wavelet based statistical texture feature set is derived from normal and tumor regions. Genetic Algorithm
(GA) is used to select the optimal texture features from the set of extracted texture features. We construct
the Support Vector Machine (SVM) based classifier and evaluate the performance of classifier by
comparing the classification results of the SVM based classifier with the Back Propagation Neural network
classifier(BPN). The results of Support Vector Machine (SVM), BPN classifiers for the texture analysis
methods are evaluated using Receiver Operating Characteristic (ROC) analysis. Experimental results
show that the classification accuracy of SVM is 96% for 10 fold cross validation method. The system
has been tested with a number of real Computed Tomography brain images and has achieved satisfactory
results.
IRJET-A Review on Brain Tumor Detection using BFCFCM AlgorithmIRJET Journal
The document presents a review of brain tumor detection using the BFCFCM clustering algorithm. It begins with an introduction to brain tumors and MRI imaging. It then reviews several existing techniques for brain tumor detection using artificial neural networks, linear discriminant analysis, neuro-fuzzy systems, and region growing segmentation with watershed algorithms. The document proposes a method using pre-processing, skull masking, segmentation with an advanced fuzzy c-means algorithm, feature extraction through thresholding, and an SVM classifier. Segmentation partitions the MRI image into regions/objects of interest like the tumor. Feature extraction analyzes the segmented regions to characterize the tumor for classification.
Support vector machine based discrete wavelet transform for magnetic resonanc...TELKOMNIKA JOURNAL
Here, a brain tumor classification method using the support vector machine (SVM) algorithm by utilizing discrete wavelet transform (DWT) transformation and feature extraction of gray-level co-occurrence matrix (GLCM) and local binary pattern (LBP) has been implemented using the magnetic resonance imaging (MRI) image belong to the low-grade glioma (LGG) or high-grade glioma (HGG) group. SVM algorithm used as a classification method has been widely used in research that raises the topic of classification. Through the formation of a hyperplane between 2 data classes, the SVM algorithm can be said to be a reliable method but does not require complicated computations. The DWT transformation is intended to provide clearer feature details from the MRI image, so that when the feature extraction algorithm is applied, it is expected that the extracted features will differ between benign tumor MRI images and malignant tumor MRI images. In 1 level DWT using high-low (HL) sub-band yield the highest specificity, sensitivity, and accuracy than using 3 levels using HL or low-high (LH) sub-band in LGG MRI image.Compared with another research, our proposed method is slightly better in terms of accuracy to classify the brain tumor image with achieved the accuracy of 98.6486%.
A deep learning approach for brain tumor detection using magnetic resonance ...IJECEIAES
The growth of abnormal cells in the brain’s tissue causes brain tumors. Brain tumors are considered one of the most dangerous disorders in children and adults. It develops quickly, and the patient’s survival prospects are slim if not appropriately treated. Proper treatment planning and precise diagnoses are essential to improving a patient’s life expectancy. Brain tumors are mainly diagnosed using magnetic resonance imaging (MRI). As part of a convolution neural network (CNN)-based illustration, an architecture containing five convolution layers, five max-pooling layers, a Flatten layer, and two dense layers has been proposed for detecting brain tumors from MRI images. The proposed model includes an automatic feature extractor, modified hidden layer architecture, and activation function. Several test cases were performed, and the proposed model achieved 98.6% accuracy and 97.8% precision score with a low cross-entropy rate. Compared with other approaches such as adjacent feature propagation network (AFPNet), mask region-based CNN (mask RCNN), YOLOv5, and Fourier CNN (FCNN), the proposed model has performed better in detecting brain tumors.
IRJET - Detection of Heamorrhage in Brain using Deep LearningIRJET Journal
This document presents a method for detecting hemorrhage in brain CT scans using deep learning. It begins with an introduction to brain hemorrhage and the need for automated detection. Previous related work using various segmentation and classification methods is summarized. Deep learning is identified as a promising technique due to its ability to extract complex features from images. The proposed method uses a convolutional neural network model with several convolutional, max pooling, dropout and dense layers to classify brain CT scans as either normal or hemorrhagic. The model is trained on 180 images and tested on 20 images, achieving an accuracy of 94.4% at predicting hemorrhage. The method provides a fast and automated way to detect hemorrhage in brain CT scans to help
Mri brain tumour detection by histogram and segmentationiaemedu
This document summarizes a research paper on detecting brain tumors in MRI images using a combination of histogram thresholding, modified gradient vector field (GVF), and morphological operators. The non-brain regions are removed using morphological operators. Histogram thresholding is then used to detect if the brain is normal or abnormal/contains a tumor. If abnormal, the modified GVF is used to detect the tumor contour. The proposed method aims to be computationally efficient by only performing segmentation if a tumor is detected. It was tested on many MRI brain images and performance was validated against human expert segmentation.
Mri brain tumour detection by histogram and segmentationiaemedu
This document summarizes a research paper on detecting brain tumors in MRI images using a combination of histogram thresholding, modified gradient vector field (GVF), and morphological operators. The non-brain regions are removed using morphological operators. Histogram thresholding is then used to detect if the brain is normal or abnormal/contains a tumor. If abnormal, the modified GVF is used to detect the tumor contour. The proposed method aims to be computationally efficient by only performing segmentation if a tumor is detected. It was tested on many MRI brain images and performance was validated against human expert segmentation.
Mri brain tumour detection by histogram and segmentation by modified gvf model 2IAEME Publication
The document describes a new method for detecting and segmenting brain tumors in MRI images. It combines histogram thresholding, modified gradient vector flow, and morphological operators. Histogram thresholding is used to detect if the brain is normal or abnormal. If abnormal, modified GVF is used to segment the tumor contour. Otherwise, segmentation is skipped to minimize computation time. The method was tested on many MRI brain images and tumor detection and dimensions were validated against expert segmentation. It provides an efficient and computationally inexpensive approach for brain tumor detection and segmentation in MRI images.
Mri brain tumour detection by histogram and segmentation by modified gvf model 2iaemedu
The document summarizes a proposed method for detecting brain tumors in MRI images in 4 steps:
1. Skull stripping and smoothing are performed to isolate the brain region.
2. Histogram thresholding is used to detect if the brain is normal or abnormal by comparing histograms of halves of the brain image.
3. For abnormal brains, a modified gradient vector flow (GVF) model is used to create a force field and detect the tumor contour.
4. The area of the tumor is then calculated. The method aims to minimize segmentation time by skipping segmentation for normal brains detected in Step 2. Validation with expert segmentation is performed.
IRJET- Brain Tumor Detection using Hybrid Model of DCT DWT and ThresholdingIRJET Journal
The document presents a new hybrid model for detecting brain tumors in MRI images. It uses a combination of discrete cosine transform (DCT), discrete wavelet transform (DWT), principal component analysis (PCA), and fuzzy c-means clustering. DCT and DWT are applied to extract features from MRI images. PCA is then used to reduce the dimensions of the extracted features. Finally, fuzzy c-means clustering is used to segment and detect tumors. The proposed hybrid model is evaluated using objective metrics like RMSE, PSNR, correlation, contrast and entropy. Results show the hybrid model achieves better values for these metrics compared to using DCT or DWT alone, indicating it more accurately detects and segments tumors in MRI images.
Brain Tumor Detection using Clustering Algorithms in MRI ImagesIRJET Journal
This document presents a novel brain tumor detection system using k-means clustering integrated with fuzzy c-means clustering and artificial neural networks. The system takes advantage of both algorithms for minimal computation time and accuracy. It accurately extracts the tumor region and calculates the tumor area by comparing the results to ground truths of the MRI images. K-means performs initial segmentation, then fuzzy c-means locates the approximate segmented tumor based on membership and cluster selection criteria. Features are extracted and an artificial neural network classifies MRI images as normal or containing a tumor. The system achieves high accuracy, sensitivity and specificity when validated against ground truths.
MALIGNANT AND BENIGN BRAIN TUMOR SEGMENTATION AND CLASSIFICATION USING SVM WI...sipij
In this article a method is proposed for segmentation and classification of benign and malignant tumor slices in brain Computed Tomography (CT) images. In this study image noises are removed using median and wiener filter and brain tumors are segmented using Support Vector Machine (SVM). Then a two-level discrete wavelet decomposition of tumor image is performed and the approximation at the second level is obtained to replace the original image to be used for texture analysis. Here, 17 features are extracted that 6 of them are selected using Student’s t-test. Dominant gray level run length and gray level co-occurrence texture features are used for SVM training. Malignant and benign tumors are classified using SVM with kernel width and Weighted kernel width (WSVM) and k-Nearest Neighbors (k-NN) classifier. Classification accuracy of classifiers are evaluated using 10 fold cross validation method. The segmentation results are
also compared with the experienced radiologist ground truth. The experimental results show that the proposed WSVM classifier is able to achieve high classification accuracy effectiveness as measured by sensitivity and specificity.
IRJET - A Review on Segmentation of Chest RadiographsIRJET Journal
This document reviews and compares various techniques for segmenting anatomical structures from chest radiographs. It begins with an introduction to image segmentation and its importance in medical imaging. It then describes 12 different segmentation methods that have been used for segmenting lungs and other structures from chest radiographs, including active shape models, active appearance models, pixel classification, visual saliency, convolutional neural networks, and others. For each method, it provides details on the algorithm and compares their performance based on accuracy, sensitivity and specificity. In conclusion, it discusses some of the challenges of medical image segmentation and suggests that hybrid approaches combining multiple techniques may be most effective.
An overview of automatic brain tumor detection frommagnetic resonance imagesMangesh Lingampalle
The document discusses several techniques for automatically detecting brain tumors from magnetic resonance (MR) images. It begins with an overview of MR imaging and challenges of manual tumor detection. Several existing techniques are then summarized, including thresholding-based methods, fuzzy classification with deformable models, using wavelets and statistics to segment tissues, feature extraction with Adaboost classification, and color-converted k-means clustering. The document proposes a technique using undecimated wavelet transform (UDWT) and Gabor filters for preprocessing, followed by morphological operations and parameter analysis to detect tumors. Automatic detection techniques could help address limitations of manual detection and improve diagnosis of brain tumors.
A novel framework for efficient identification of brain cancer region from br...IJECEIAES
Diagnosis of brain cancer using existing imaging techniques, e.g., Magnetic Resonance Imaging (MRI) is shrouded with various degrees of challenges. At present, there are very few significant research models focusing on introducing some novel and unique solutions towards such problems of detection. Moreover, existing techniques are found to have lesser accuracy as compared to other detection schemes. Therefore, the proposed paper presents a framework that introduces a series of simple and computationally cost-effective techniques that have assisted in leveraging the accuracy level to a very higher degree. The proposed framework takes the input image and subjects it to non-conventional segmentation mechanism followed by optimizing the performance using directed acyclic graph, Bayesian Network, and neural network. The study outcome of the proposed system shows the significantly higher degree of accuracy in detection performance as compared to frequently existing approaches.
Human brain is the most complex structure where identifying the tumor like diseases are extremely challenging because differentiating the components of a brain is complex. In this paper, pillar k-means algorithm is used for segmentation of brain tumor from magnetic resonance image (MRI).Generally, the brain tumor is detected by radiologist through analysis of MR images which takes longer time. The pillar k-means algorithm’s experimental results clarify the effectiveness of our approach to improve the segmentation quality, accuracy, and computational time. Classify, the tumor from the brain MR images using Bayesian classification.
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.
Multiple Analysis of Brain Tumor Detection Based on FCMIRJET Journal
The document proposes a system to detect brain tumors in MRI images using multiple steps including pre-processing, segmentation using fuzzy c-means clustering, and feature extraction using fuzzy rules. It discusses how pre-processing improves tumor detection, fuzzy c-means segmentation identifies tumor regions and size, and prior approaches have limitations. The proposed system aims to better detect and identify brain tumors in MRI images as compared to other algorithms.
IRJET- A Novel Segmentation Technique for MRI Brain Tumor ImagesIRJET Journal
This document summarizes several research papers on techniques for segmenting brain tumors in MRI images. It discusses challenges in brain tumor segmentation and describes various approaches that have been proposed, including methods using feature selection, kernel sparse representation, multiple kernel learning (MKL), and post-processing techniques. The document also reviews state-of-the-art segmentation, registration, and modeling methods for brain tumor images and their performance.
Breast Mass Segmentation Using a Semi-automatic Procedure Based on Fuzzy C-me...TELKOMNIKA JOURNAL
Mammography is the primary modality that helped in the early detection and diagnosis of women
breast diseases. Further, the process of extracting the masses in mammogram represents a challenging task
facing the radiologists, due to problems such as fuzzy or speculated borders, low contrast and the presence of
intensity inhomogeneities. Aims to help the radiologists in the diagnosis of breast cancer, many approaches
have been conducted to automatically segment the masses in mammograms. Towards this aim, in this paper,
we present a new approach for extraction of tumors from region-of-interest (ROI) using the algorithm of Fuzzy
C-Means (FCM) setting two clusters for semi-automated segmentation. The proposed method meant to select
as input data the set of pixels that enable to get the meaningful information required to segment the masses
with high accuracy. This could be accomplished through eliminating unnecessary pixels, which influence on this
process through separating it outside of the input data using an optimal thresho ld given by monitoring the
change of clusters rate during the process of threshold decrementing. The proposed methodology has
successfully segmented the masses, with an average sensitivity of 82.02% and specificity of 98.23%.
IRJET- Brain Tumor Detection and Classification with Feed Forward Back Propag...IRJET Journal
This document presents a method for detecting and classifying brain tumors in MRI images using a feed forward back propagation neural network. It first preprocesses MRI images by dividing them into blocks and applying Haar transforms for noise removal and edge preservation. Statistical, GLCM, morphological and edge features are then extracted from each block. These features are used to identify abnormal areas. The blocks are then classified as normal or tumor using a feed forward back propagation neural network, which can model nonlinear relationships and is trained to reduce error rates. The method achieves 98% classification accuracy on a benchmark MRI dataset. It results in high accuracy tumor detection with less iterations, reducing computation time compared to previous methods.
IRJET - An Efficient Approach for Multi-Modal Brain Tumor Classification usin...IRJET Journal
This paper proposes an efficient approach for multi-modal brain tumor classification using texture features and machine learning. It uses the MICCAI BraTS 2016 dataset and segments tumors using fuzzy c-means clustering. It then extracts texture features like GLCM and LBP and classifies tumors as benign or malignant using an SVM classifier. The proposed method achieved accurate segmentation and classification of brain tumors in MRI images.
Amazon products reviews classification based on machine learning, deep learni...TELKOMNIKA JOURNAL
In recent times, the trend of online shopping through e-commerce stores and websites has grown to a huge extent. Whenever a product is purchased on an e-commerce platform, people leave their reviews about the product. These reviews are very helpful for the store owners and the product’s manufacturers for the betterment of their work process as well as product quality. An automated system is proposed in this work that operates on two datasets D1 and D2 obtained from Amazon. After certain preprocessing steps, N-gram and word embedding-based features are extracted using term frequency-inverse document frequency (TF-IDF), bag of words (BoW) and global vectors (GloVe), and Word2vec, respectively. Four machine learning (ML) models support vector machines (SVM), logistic regression (RF), logistic regression (LR), multinomial Naïve Bayes (MNB), two deep learning (DL) models convolutional neural network (CNN), long-short term memory (LSTM), and standalone bidirectional encoder representations (BERT) are used to classify reviews as either positive or negative. The results obtained by the standard ML, DL models and BERT are evaluated using certain performance evaluation measures. BERT turns out to be the best-performing model in the case of D1 with an accuracy of 90% on features derived by word embedding models while the CNN provides the best accuracy of 97% upon word embedding features in the case of D2. The proposed model shows better overall performance on D2 as compared to D1.
Design, simulation, and analysis of microstrip patch antenna for wireless app...TELKOMNIKA JOURNAL
In this study, a microstrip patch antenna that works at 3.6 GHz was built and tested to see how well it works. In this work, Rogers RT/Duroid 5880 has been used as the substrate material, with a dielectric permittivity of 2.2 and a thickness of 0.3451 mm; it serves as the base for the examined antenna. The computer simulation technology (CST) studio suite is utilized to show the recommended antenna design. The goal of this study was to get a more extensive transmission capacity, a lower voltage standing wave ratio (VSWR), and a lower return loss, but the main goal was to get a higher gain, directivity, and efficiency. After simulation, the return loss, gain, directivity, bandwidth, and efficiency of the supplied antenna are found to be -17.626 dB, 9.671 dBi, 9.924 dBi, 0.2 GHz, and 97.45%, respectively. Besides, the recreation uncovered that the transfer speed side-lobe level at phi was much better than those of the earlier works, at -28.8 dB, respectively. Thus, it makes a solid contender for remote innovation and more robust communication.
Support vector machine based discrete wavelet transform for magnetic resonanc...TELKOMNIKA JOURNAL
Here, a brain tumor classification method using the support vector machine (SVM) algorithm by utilizing discrete wavelet transform (DWT) transformation and feature extraction of gray-level co-occurrence matrix (GLCM) and local binary pattern (LBP) has been implemented using the magnetic resonance imaging (MRI) image belong to the low-grade glioma (LGG) or high-grade glioma (HGG) group. SVM algorithm used as a classification method has been widely used in research that raises the topic of classification. Through the formation of a hyperplane between 2 data classes, the SVM algorithm can be said to be a reliable method but does not require complicated computations. The DWT transformation is intended to provide clearer feature details from the MRI image, so that when the feature extraction algorithm is applied, it is expected that the extracted features will differ between benign tumor MRI images and malignant tumor MRI images. In 1 level DWT using high-low (HL) sub-band yield the highest specificity, sensitivity, and accuracy than using 3 levels using HL or low-high (LH) sub-band in LGG MRI image.Compared with another research, our proposed method is slightly better in terms of accuracy to classify the brain tumor image with achieved the accuracy of 98.6486%.
A deep learning approach for brain tumor detection using magnetic resonance ...IJECEIAES
The growth of abnormal cells in the brain’s tissue causes brain tumors. Brain tumors are considered one of the most dangerous disorders in children and adults. It develops quickly, and the patient’s survival prospects are slim if not appropriately treated. Proper treatment planning and precise diagnoses are essential to improving a patient’s life expectancy. Brain tumors are mainly diagnosed using magnetic resonance imaging (MRI). As part of a convolution neural network (CNN)-based illustration, an architecture containing five convolution layers, five max-pooling layers, a Flatten layer, and two dense layers has been proposed for detecting brain tumors from MRI images. The proposed model includes an automatic feature extractor, modified hidden layer architecture, and activation function. Several test cases were performed, and the proposed model achieved 98.6% accuracy and 97.8% precision score with a low cross-entropy rate. Compared with other approaches such as adjacent feature propagation network (AFPNet), mask region-based CNN (mask RCNN), YOLOv5, and Fourier CNN (FCNN), the proposed model has performed better in detecting brain tumors.
IRJET - Detection of Heamorrhage in Brain using Deep LearningIRJET Journal
This document presents a method for detecting hemorrhage in brain CT scans using deep learning. It begins with an introduction to brain hemorrhage and the need for automated detection. Previous related work using various segmentation and classification methods is summarized. Deep learning is identified as a promising technique due to its ability to extract complex features from images. The proposed method uses a convolutional neural network model with several convolutional, max pooling, dropout and dense layers to classify brain CT scans as either normal or hemorrhagic. The model is trained on 180 images and tested on 20 images, achieving an accuracy of 94.4% at predicting hemorrhage. The method provides a fast and automated way to detect hemorrhage in brain CT scans to help
Mri brain tumour detection by histogram and segmentationiaemedu
This document summarizes a research paper on detecting brain tumors in MRI images using a combination of histogram thresholding, modified gradient vector field (GVF), and morphological operators. The non-brain regions are removed using morphological operators. Histogram thresholding is then used to detect if the brain is normal or abnormal/contains a tumor. If abnormal, the modified GVF is used to detect the tumor contour. The proposed method aims to be computationally efficient by only performing segmentation if a tumor is detected. It was tested on many MRI brain images and performance was validated against human expert segmentation.
Mri brain tumour detection by histogram and segmentationiaemedu
This document summarizes a research paper on detecting brain tumors in MRI images using a combination of histogram thresholding, modified gradient vector field (GVF), and morphological operators. The non-brain regions are removed using morphological operators. Histogram thresholding is then used to detect if the brain is normal or abnormal/contains a tumor. If abnormal, the modified GVF is used to detect the tumor contour. The proposed method aims to be computationally efficient by only performing segmentation if a tumor is detected. It was tested on many MRI brain images and performance was validated against human expert segmentation.
Mri brain tumour detection by histogram and segmentation by modified gvf model 2IAEME Publication
The document describes a new method for detecting and segmenting brain tumors in MRI images. It combines histogram thresholding, modified gradient vector flow, and morphological operators. Histogram thresholding is used to detect if the brain is normal or abnormal. If abnormal, modified GVF is used to segment the tumor contour. Otherwise, segmentation is skipped to minimize computation time. The method was tested on many MRI brain images and tumor detection and dimensions were validated against expert segmentation. It provides an efficient and computationally inexpensive approach for brain tumor detection and segmentation in MRI images.
Mri brain tumour detection by histogram and segmentation by modified gvf model 2iaemedu
The document summarizes a proposed method for detecting brain tumors in MRI images in 4 steps:
1. Skull stripping and smoothing are performed to isolate the brain region.
2. Histogram thresholding is used to detect if the brain is normal or abnormal by comparing histograms of halves of the brain image.
3. For abnormal brains, a modified gradient vector flow (GVF) model is used to create a force field and detect the tumor contour.
4. The area of the tumor is then calculated. The method aims to minimize segmentation time by skipping segmentation for normal brains detected in Step 2. Validation with expert segmentation is performed.
IRJET- Brain Tumor Detection using Hybrid Model of DCT DWT and ThresholdingIRJET Journal
The document presents a new hybrid model for detecting brain tumors in MRI images. It uses a combination of discrete cosine transform (DCT), discrete wavelet transform (DWT), principal component analysis (PCA), and fuzzy c-means clustering. DCT and DWT are applied to extract features from MRI images. PCA is then used to reduce the dimensions of the extracted features. Finally, fuzzy c-means clustering is used to segment and detect tumors. The proposed hybrid model is evaluated using objective metrics like RMSE, PSNR, correlation, contrast and entropy. Results show the hybrid model achieves better values for these metrics compared to using DCT or DWT alone, indicating it more accurately detects and segments tumors in MRI images.
Brain Tumor Detection using Clustering Algorithms in MRI ImagesIRJET Journal
This document presents a novel brain tumor detection system using k-means clustering integrated with fuzzy c-means clustering and artificial neural networks. The system takes advantage of both algorithms for minimal computation time and accuracy. It accurately extracts the tumor region and calculates the tumor area by comparing the results to ground truths of the MRI images. K-means performs initial segmentation, then fuzzy c-means locates the approximate segmented tumor based on membership and cluster selection criteria. Features are extracted and an artificial neural network classifies MRI images as normal or containing a tumor. The system achieves high accuracy, sensitivity and specificity when validated against ground truths.
MALIGNANT AND BENIGN BRAIN TUMOR SEGMENTATION AND CLASSIFICATION USING SVM WI...sipij
In this article a method is proposed for segmentation and classification of benign and malignant tumor slices in brain Computed Tomography (CT) images. In this study image noises are removed using median and wiener filter and brain tumors are segmented using Support Vector Machine (SVM). Then a two-level discrete wavelet decomposition of tumor image is performed and the approximation at the second level is obtained to replace the original image to be used for texture analysis. Here, 17 features are extracted that 6 of them are selected using Student’s t-test. Dominant gray level run length and gray level co-occurrence texture features are used for SVM training. Malignant and benign tumors are classified using SVM with kernel width and Weighted kernel width (WSVM) and k-Nearest Neighbors (k-NN) classifier. Classification accuracy of classifiers are evaluated using 10 fold cross validation method. The segmentation results are
also compared with the experienced radiologist ground truth. The experimental results show that the proposed WSVM classifier is able to achieve high classification accuracy effectiveness as measured by sensitivity and specificity.
IRJET - A Review on Segmentation of Chest RadiographsIRJET Journal
This document reviews and compares various techniques for segmenting anatomical structures from chest radiographs. It begins with an introduction to image segmentation and its importance in medical imaging. It then describes 12 different segmentation methods that have been used for segmenting lungs and other structures from chest radiographs, including active shape models, active appearance models, pixel classification, visual saliency, convolutional neural networks, and others. For each method, it provides details on the algorithm and compares their performance based on accuracy, sensitivity and specificity. In conclusion, it discusses some of the challenges of medical image segmentation and suggests that hybrid approaches combining multiple techniques may be most effective.
An overview of automatic brain tumor detection frommagnetic resonance imagesMangesh Lingampalle
The document discusses several techniques for automatically detecting brain tumors from magnetic resonance (MR) images. It begins with an overview of MR imaging and challenges of manual tumor detection. Several existing techniques are then summarized, including thresholding-based methods, fuzzy classification with deformable models, using wavelets and statistics to segment tissues, feature extraction with Adaboost classification, and color-converted k-means clustering. The document proposes a technique using undecimated wavelet transform (UDWT) and Gabor filters for preprocessing, followed by morphological operations and parameter analysis to detect tumors. Automatic detection techniques could help address limitations of manual detection and improve diagnosis of brain tumors.
A novel framework for efficient identification of brain cancer region from br...IJECEIAES
Diagnosis of brain cancer using existing imaging techniques, e.g., Magnetic Resonance Imaging (MRI) is shrouded with various degrees of challenges. At present, there are very few significant research models focusing on introducing some novel and unique solutions towards such problems of detection. Moreover, existing techniques are found to have lesser accuracy as compared to other detection schemes. Therefore, the proposed paper presents a framework that introduces a series of simple and computationally cost-effective techniques that have assisted in leveraging the accuracy level to a very higher degree. The proposed framework takes the input image and subjects it to non-conventional segmentation mechanism followed by optimizing the performance using directed acyclic graph, Bayesian Network, and neural network. The study outcome of the proposed system shows the significantly higher degree of accuracy in detection performance as compared to frequently existing approaches.
Human brain is the most complex structure where identifying the tumor like diseases are extremely challenging because differentiating the components of a brain is complex. In this paper, pillar k-means algorithm is used for segmentation of brain tumor from magnetic resonance image (MRI).Generally, the brain tumor is detected by radiologist through analysis of MR images which takes longer time. The pillar k-means algorithm’s experimental results clarify the effectiveness of our approach to improve the segmentation quality, accuracy, and computational time. Classify, the tumor from the brain MR images using Bayesian classification.
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.
Multiple Analysis of Brain Tumor Detection Based on FCMIRJET Journal
The document proposes a system to detect brain tumors in MRI images using multiple steps including pre-processing, segmentation using fuzzy c-means clustering, and feature extraction using fuzzy rules. It discusses how pre-processing improves tumor detection, fuzzy c-means segmentation identifies tumor regions and size, and prior approaches have limitations. The proposed system aims to better detect and identify brain tumors in MRI images as compared to other algorithms.
IRJET- A Novel Segmentation Technique for MRI Brain Tumor ImagesIRJET Journal
This document summarizes several research papers on techniques for segmenting brain tumors in MRI images. It discusses challenges in brain tumor segmentation and describes various approaches that have been proposed, including methods using feature selection, kernel sparse representation, multiple kernel learning (MKL), and post-processing techniques. The document also reviews state-of-the-art segmentation, registration, and modeling methods for brain tumor images and their performance.
Breast Mass Segmentation Using a Semi-automatic Procedure Based on Fuzzy C-me...TELKOMNIKA JOURNAL
Mammography is the primary modality that helped in the early detection and diagnosis of women
breast diseases. Further, the process of extracting the masses in mammogram represents a challenging task
facing the radiologists, due to problems such as fuzzy or speculated borders, low contrast and the presence of
intensity inhomogeneities. Aims to help the radiologists in the diagnosis of breast cancer, many approaches
have been conducted to automatically segment the masses in mammograms. Towards this aim, in this paper,
we present a new approach for extraction of tumors from region-of-interest (ROI) using the algorithm of Fuzzy
C-Means (FCM) setting two clusters for semi-automated segmentation. The proposed method meant to select
as input data the set of pixels that enable to get the meaningful information required to segment the masses
with high accuracy. This could be accomplished through eliminating unnecessary pixels, which influence on this
process through separating it outside of the input data using an optimal thresho ld given by monitoring the
change of clusters rate during the process of threshold decrementing. The proposed methodology has
successfully segmented the masses, with an average sensitivity of 82.02% and specificity of 98.23%.
IRJET- Brain Tumor Detection and Classification with Feed Forward Back Propag...IRJET Journal
This document presents a method for detecting and classifying brain tumors in MRI images using a feed forward back propagation neural network. It first preprocesses MRI images by dividing them into blocks and applying Haar transforms for noise removal and edge preservation. Statistical, GLCM, morphological and edge features are then extracted from each block. These features are used to identify abnormal areas. The blocks are then classified as normal or tumor using a feed forward back propagation neural network, which can model nonlinear relationships and is trained to reduce error rates. The method achieves 98% classification accuracy on a benchmark MRI dataset. It results in high accuracy tumor detection with less iterations, reducing computation time compared to previous methods.
IRJET - An Efficient Approach for Multi-Modal Brain Tumor Classification usin...IRJET Journal
This paper proposes an efficient approach for multi-modal brain tumor classification using texture features and machine learning. It uses the MICCAI BraTS 2016 dataset and segments tumors using fuzzy c-means clustering. It then extracts texture features like GLCM and LBP and classifies tumors as benign or malignant using an SVM classifier. The proposed method achieved accurate segmentation and classification of brain tumors in MRI images.
Amazon products reviews classification based on machine learning, deep learni...TELKOMNIKA JOURNAL
In recent times, the trend of online shopping through e-commerce stores and websites has grown to a huge extent. Whenever a product is purchased on an e-commerce platform, people leave their reviews about the product. These reviews are very helpful for the store owners and the product’s manufacturers for the betterment of their work process as well as product quality. An automated system is proposed in this work that operates on two datasets D1 and D2 obtained from Amazon. After certain preprocessing steps, N-gram and word embedding-based features are extracted using term frequency-inverse document frequency (TF-IDF), bag of words (BoW) and global vectors (GloVe), and Word2vec, respectively. Four machine learning (ML) models support vector machines (SVM), logistic regression (RF), logistic regression (LR), multinomial Naïve Bayes (MNB), two deep learning (DL) models convolutional neural network (CNN), long-short term memory (LSTM), and standalone bidirectional encoder representations (BERT) are used to classify reviews as either positive or negative. The results obtained by the standard ML, DL models and BERT are evaluated using certain performance evaluation measures. BERT turns out to be the best-performing model in the case of D1 with an accuracy of 90% on features derived by word embedding models while the CNN provides the best accuracy of 97% upon word embedding features in the case of D2. The proposed model shows better overall performance on D2 as compared to D1.
Design, simulation, and analysis of microstrip patch antenna for wireless app...TELKOMNIKA JOURNAL
In this study, a microstrip patch antenna that works at 3.6 GHz was built and tested to see how well it works. In this work, Rogers RT/Duroid 5880 has been used as the substrate material, with a dielectric permittivity of 2.2 and a thickness of 0.3451 mm; it serves as the base for the examined antenna. The computer simulation technology (CST) studio suite is utilized to show the recommended antenna design. The goal of this study was to get a more extensive transmission capacity, a lower voltage standing wave ratio (VSWR), and a lower return loss, but the main goal was to get a higher gain, directivity, and efficiency. After simulation, the return loss, gain, directivity, bandwidth, and efficiency of the supplied antenna are found to be -17.626 dB, 9.671 dBi, 9.924 dBi, 0.2 GHz, and 97.45%, respectively. Besides, the recreation uncovered that the transfer speed side-lobe level at phi was much better than those of the earlier works, at -28.8 dB, respectively. Thus, it makes a solid contender for remote innovation and more robust communication.
Design and simulation an optimal enhanced PI controller for congestion avoida...TELKOMNIKA JOURNAL
This document describes using a snake optimization algorithm to tune the gains of an enhanced proportional-integral controller for congestion avoidance in a TCP/AQM system. The controller aims to maintain a stable and desired queue size without noise or transmission problems. A linearized model of the TCP/AQM system is presented. An enhanced PI controller combining nonlinear gain and original PI gains is proposed. The snake optimization algorithm is then used to tune the parameters of the enhanced PI controller to achieve optimal system performance and response. Simulation results are discussed showing the proposed controller provides a stable and robust behavior for congestion control.
Improving the detection of intrusion in vehicular ad-hoc networks with modifi...TELKOMNIKA JOURNAL
Vehicular ad-hoc networks (VANETs) are wireless-equipped vehicles that form networks along the road. The security of this network has been a major challenge. The identity-based cryptosystem (IBC) previously used to secure the networks suffers from membership authentication security features. This paper focuses on improving the detection of intruders in VANETs with a modified identity-based cryptosystem (MIBC). The MIBC is developed using a non-singular elliptic curve with Lagrange interpolation. The public key of vehicles and roadside units on the network are derived from number plates and location identification numbers, respectively. Pseudo-identities are used to mask the real identity of users to preserve their privacy. The membership authentication mechanism ensures that only valid and authenticated members of the network are allowed to join the network. The performance of the MIBC is evaluated using intrusion detection ratio (IDR) and computation time (CT) and then validated with the existing IBC. The result obtained shows that the MIBC recorded an IDR of 99.3% against 94.3% obtained for the existing identity-based cryptosystem (EIBC) for 140 unregistered vehicles attempting to intrude on the network. The MIBC shows lower CT values of 1.17 ms against 1.70 ms for EIBC. The MIBC can be used to improve the security of VANETs.
Conceptual model of internet banking adoption with perceived risk and trust f...TELKOMNIKA JOURNAL
Understanding the primary factors of internet banking (IB) acceptance is critical for both banks and users; nevertheless, our knowledge of the role of users’ perceived risk and trust in IB adoption is limited. As a result, we develop a conceptual model by incorporating perceived risk and trust into the technology acceptance model (TAM) theory toward the IB. The proper research emphasized that the most essential component in explaining IB adoption behavior is behavioral intention to use IB adoption. TAM is helpful for figuring out how elements that affect IB adoption are connected to one another. According to previous literature on IB and the use of such technology in Iraq, one has to choose a theoretical foundation that may justify the acceptance of IB from the customer’s perspective. The conceptual model was therefore constructed using the TAM as a foundation. Furthermore, perceived risk and trust were added to the TAM dimensions as external factors. The key objective of this work was to extend the TAM to construct a conceptual model for IB adoption and to get sufficient theoretical support from the existing literature for the essential elements and their relationships in order to unearth new insights about factors responsible for IB adoption.
Efficient combined fuzzy logic and LMS algorithm for smart antennaTELKOMNIKA JOURNAL
The smart antennas are broadly used in wireless communication. The least mean square (LMS) algorithm is a procedure that is concerned in controlling the smart antenna pattern to accommodate specified requirements such as steering the beam toward the desired signal, in addition to placing the deep nulls in the direction of unwanted signals. The conventional LMS (C-LMS) has some drawbacks like slow convergence speed besides high steady state fluctuation error. To overcome these shortcomings, the present paper adopts an adaptive fuzzy control step size least mean square (FC-LMS) algorithm to adjust its step size. Computer simulation outcomes illustrate that the given model has fast convergence rate as well as low mean square error steady state.
Design and implementation of a LoRa-based system for warning of forest fireTELKOMNIKA JOURNAL
This paper presents the design and implementation of a forest fire monitoring and warning system based on long range (LoRa) technology, a novel ultra-low power consumption and long-range wireless communication technology for remote sensing applications. The proposed system includes a wireless sensor network that records environmental parameters such as temperature, humidity, wind speed, and carbon dioxide (CO2) concentration in the air, as well as taking infrared photos.The data collected at each sensor node will be transmitted to the gateway via LoRa wireless transmission. Data will be collected, processed, and uploaded to a cloud database at the gateway. An Android smartphone application that allows anyone to easily view the recorded data has been developed. When a fire is detected, the system will sound a siren and send a warning message to the responsible personnel, instructing them to take appropriate action. Experiments in Tram Chim Park, Vietnam, have been conducted to verify and evaluate the operation of the system.
Wavelet-based sensing technique in cognitive radio networkTELKOMNIKA JOURNAL
Cognitive radio is a smart radio that can change its transmitter parameter based on interaction with the environment in which it operates. The demand for frequency spectrum is growing due to a big data issue as many Internet of Things (IoT) devices are in the network. Based on previous research, most frequency spectrum was used, but some spectrums were not used, called spectrum hole. Energy detection is one of the spectrum sensing methods that has been frequently used since it is easy to use and does not require license users to have any prior signal understanding. But this technique is incapable of detecting at low signal-to-noise ratio (SNR) levels. Therefore, the wavelet-based sensing is proposed to overcome this issue and detect spectrum holes. The main objective of this work is to evaluate the performance of wavelet-based sensing and compare it with the energy detection technique. The findings show that the percentage of detection in wavelet-based sensing is 83% higher than energy detection performance. This result indicates that the wavelet-based sensing has higher precision in detection and the interference towards primary user can be decreased.
A novel compact dual-band bandstop filter with enhanced rejection bandsTELKOMNIKA JOURNAL
In this paper, we present the design of a new wide dual-band bandstop filter (DBBSF) using nonuniform transmission lines. The method used to design this filter is to replace conventional uniform transmission lines with nonuniform lines governed by a truncated Fourier series. Based on how impedances are profiled in the proposed DBBSF structure, the fractional bandwidths of the two 10 dB-down rejection bands are widened to 39.72% and 52.63%, respectively, and the physical size has been reduced compared to that of the filter with the uniform transmission lines. The results of the electromagnetic (EM) simulation support the obtained analytical response and show an improved frequency behavior.
Deep learning approach to DDoS attack with imbalanced data at the application...TELKOMNIKA JOURNAL
A distributed denial of service (DDoS) attack is where one or more computers attack or target a server computer, by flooding internet traffic to the server. As a result, the server cannot be accessed by legitimate users. A result of this attack causes enormous losses for a company because it can reduce the level of user trust, and reduce the company’s reputation to lose customers due to downtime. One of the services at the application layer that can be accessed by users is a web-based lightweight directory access protocol (LDAP) service that can provide safe and easy services to access directory applications. We used a deep learning approach to detect DDoS attacks on the CICDDoS 2019 dataset on a complex computer network at the application layer to get fast and accurate results for dealing with unbalanced data. Based on the results obtained, it is observed that DDoS attack detection using a deep learning approach on imbalanced data performs better when implemented using synthetic minority oversampling technique (SMOTE) method for binary classes. On the other hand, the proposed deep learning approach performs better for detecting DDoS attacks in multiclass when implemented using the adaptive synthetic (ADASYN) method.
The appearance of uncertainties and disturbances often effects the characteristics of either linear or nonlinear systems. Plus, the stabilization process may be deteriorated thus incurring a catastrophic effect to the system performance. As such, this manuscript addresses the concept of matching condition for the systems that are suffering from miss-match uncertainties and exogeneous disturbances. The perturbation towards the system at hand is assumed to be known and unbounded. To reach this outcome, uncertainties and their classifications are reviewed thoroughly. The structural matching condition is proposed and tabulated in the proposition 1. Two types of mathematical expressions are presented to distinguish the system with matched uncertainty and the system with miss-matched uncertainty. Lastly, two-dimensional numerical expressions are provided to practice the proposed proposition. The outcome shows that matching condition has the ability to change the system to a design-friendly model for asymptotic stabilization.
Implementation of FinFET technology based low power 4×4 Wallace tree multipli...TELKOMNIKA JOURNAL
Many systems, including digital signal processors, finite impulse response (FIR) filters, application-specific integrated circuits, and microprocessors, use multipliers. The demand for low power multipliers is gradually rising day by day in the current technological trend. In this study, we describe a 4×4 Wallace multiplier based on a carry select adder (CSA) that uses less power and has a better power delay product than existing multipliers. HSPICE tool at 16 nm technology is used to simulate the results. In comparison to the traditional CSA-based multiplier, which has a power consumption of 1.7 µW and power delay product (PDP) of 57.3 fJ, the results demonstrate that the Wallace multiplier design employing CSA with first zero finding logic (FZF) logic has the lowest power consumption of 1.4 µW and PDP of 27.5 fJ.
Evaluation of the weighted-overlap add model with massive MIMO in a 5G systemTELKOMNIKA JOURNAL
The flaw in 5G orthogonal frequency division multiplexing (OFDM) becomes apparent in high-speed situations. Because the doppler effect causes frequency shifts, the orthogonality of OFDM subcarriers is broken, lowering both their bit error rate (BER) and throughput output. As part of this research, we use a novel design that combines massive multiple input multiple output (MIMO) and weighted overlap and add (WOLA) to improve the performance of 5G systems. To determine which design is superior, throughput and BER are calculated for both the proposed design and OFDM. The results of the improved system show a massive improvement in performance ver the conventional system and significant improvements with massive MIMO, including the best throughput and BER. When compared to conventional systems, the improved system has a throughput that is around 22% higher and the best performance in terms of BER, but it still has around 25% less error than OFDM.
Reflector antenna design in different frequencies using frequency selective s...TELKOMNIKA JOURNAL
In this study, it is aimed to obtain two different asymmetric radiation patterns obtained from antennas in the shape of the cross-section of a parabolic reflector (fan blade type antennas) and antennas with cosecant-square radiation characteristics at two different frequencies from a single antenna. For this purpose, firstly, a fan blade type antenna design will be made, and then the reflective surface of this antenna will be completed to the shape of the reflective surface of the antenna with the cosecant-square radiation characteristic with the frequency selective surface designed to provide the characteristics suitable for the purpose. The frequency selective surface designed and it provides the perfect transmission as possible at 4 GHz operating frequency, while it will act as a band-quenching filter for electromagnetic waves at 5 GHz operating frequency and will be a reflective surface. Thanks to this frequency selective surface to be used as a reflective surface in the antenna, a fan blade type radiation characteristic at 4 GHz operating frequency will be obtained, while a cosecant-square radiation characteristic at 5 GHz operating frequency will be obtained.
Reagentless iron detection in water based on unclad fiber optical sensorTELKOMNIKA JOURNAL
A simple and low-cost fiber based optical sensor for iron detection is demonstrated in this paper. The sensor head consist of an unclad optical fiber with the unclad length of 1 cm and it has a straight structure. Results obtained shows a linear relationship between the output light intensity and iron concentration, illustrating the functionality of this iron optical sensor. Based on the experimental results, the sensitivity and linearity are achieved at 0.0328/ppm and 0.9824 respectively at the wavelength of 690 nm. With the same wavelength, other performance parameters are also studied. Resolution and limit of detection (LOD) are found to be 0.3049 ppm and 0.0755 ppm correspondingly. This iron sensor is advantageous in that it does not require any reagent for detection, enabling it to be simpler and cost-effective in the implementation of the iron sensing.
Impact of CuS counter electrode calcination temperature on quantum dot sensit...TELKOMNIKA JOURNAL
In place of the commercial Pt electrode used in quantum sensitized solar cells, the low-cost CuS cathode is created using electrophoresis. High resolution scanning electron microscopy and X-ray diffraction were used to analyze the structure and morphology of structural cubic samples with diameters ranging from 40 nm to 200 nm. The conversion efficiency of solar cells is significantly impacted by the calcination temperatures of cathodes at 100 °C, 120 °C, 150 °C, and 180 °C under vacuum. The fluorine doped tin oxide (FTO)/CuS cathode electrode reached a maximum efficiency of 3.89% when it was calcined at 120 °C. Compared to other temperature combinations, CuS nanoparticles crystallize at 120 °C, which lowers resistance while increasing electron lifetime.
In place of the commercial Pt electrode used in quantum sensitized solar cells, the low-cost CuS cathode is created using electrophoresis. High resolution scanning electron microscopy and X-ray diffraction were used to analyze the structure and morphology of structural cubic samples with diameters ranging from 40 nm to 200 nm. The conversion efficiency of solar cells is significantly impacted by the calcination temperatures of cathodes at 100 °C, 120 °C, 150 °C, and 180 °C under vacuum. The fluorine doped tin oxide (FTO)/CuS cathode electrode reached a maximum efficiency of 3.89% when it was calcined at 120 °C. Compared to other temperature combinations, CuS nanoparticles crystallize at 120 °C, which lowers resistance while increasing electron lifetime.
A progressive learning for structural tolerance online sequential extreme lea...TELKOMNIKA JOURNAL
This article discusses the progressive learning for structural tolerance online sequential extreme learning machine (PSTOS-ELM). PSTOS-ELM can save robust accuracy while updating the new data and the new class data on the online training situation. The robustness accuracy arises from using the householder block exact QR decomposition recursive least squares (HBQRD-RLS) of the PSTOS-ELM. This method is suitable for applications that have data streaming and often have new class data. Our experiment compares the PSTOS-ELM accuracy and accuracy robustness while data is updating with the batch-extreme learning machine (ELM) and structural tolerance online sequential extreme learning machine (STOS-ELM) that both must retrain the data in a new class data case. The experimental results show that PSTOS-ELM has accuracy and robustness comparable to ELM and STOS-ELM while also can update new class data immediately.
Electroencephalography-based brain-computer interface using neural networksTELKOMNIKA JOURNAL
This study aimed to develop a brain-computer interface that can control an electric wheelchair using electroencephalography (EEG) signals. First, we used the Mind Wave Mobile 2 device to capture raw EEG signals from the surface of the scalp. The signals were transformed into the frequency domain using fast Fourier transform (FFT) and filtered to monitor changes in attention and relaxation. Next, we performed time and frequency domain analyses to identify features for five eye gestures: opened, closed, blink per second, double blink, and lookup. The base state was the opened-eyes gesture, and we compared the features of the remaining four action gestures to the base state to identify potential gestures. We then built a multilayer neural network to classify these features into five signals that control the wheelchair’s movement. Finally, we designed an experimental wheelchair system to test the effectiveness of the proposed approach. The results demonstrate that the EEG classification was highly accurate and computationally efficient. Moreover, the average performance of the brain-controlled wheelchair system was over 75% across different individuals, which suggests the feasibility of this approach.
Adaptive segmentation algorithm based on level set model in medical imagingTELKOMNIKA JOURNAL
For image segmentation, level set models are frequently employed. It offer best solution to overcome the main limitations of deformable parametric models. However, the challenge when applying those models in medical images stills deal with removing blurs in image edges which directly affects the edge indicator function, leads to not adaptively segmenting images and causes a wrong analysis of pathologies wich prevents to conclude a correct diagnosis. To overcome such issues, an effective process is suggested by simultaneously modelling and solving systems’ two-dimensional partial differential equations (PDE). The first PDE equation allows restoration using Euler’s equation similar to an anisotropic smoothing based on a regularized Perona and Malik filter that eliminates noise while preserving edge information in accordance with detected contours in the second equation that segments the image based on the first equation solutions. This approach allows developing a new algorithm which overcome the studied model drawbacks. Results of the proposed method give clear segments that can be applied to any application. Experiments on many medical images in particular blurry images with high information losses, demonstrate that the developed approach produces superior segmentation results in terms of quantity and quality compared to other models already presented in previeous works.
Automatic channel selection using shuffled frog leaping algorithm for EEG bas...TELKOMNIKA JOURNAL
Drug addiction is a complex neurobiological disorder that necessitates comprehensive treatment of both the body and mind. It is categorized as a brain disorder due to its impact on the brain. Various methods such as electroencephalography (EEG), functional magnetic resonance imaging (FMRI), and magnetoencephalography (MEG) can capture brain activities and structures. EEG signals provide valuable insights into neurological disorders, including drug addiction. Accurate classification of drug addiction from EEG signals relies on appropriate features and channel selection. Choosing the right EEG channels is essential to reduce computational costs and mitigate the risk of overfitting associated with using all available channels. To address the challenge of optimal channel selection in addiction detection from EEG signals, this work employs the shuffled frog leaping algorithm (SFLA). SFLA facilitates the selection of appropriate channels, leading to improved accuracy. Wavelet features extracted from the selected input channel signals are then analyzed using various machine learning classifiers to detect addiction. Experimental results indicate that after selecting features from the appropriate channels, classification accuracy significantly increased across all classifiers. Particularly, the multi-layer perceptron (MLP) classifier combined with SFLA demonstrated a remarkable accuracy improvement of 15.78% while reducing time complexity.
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%.
Harnessing WebAssembly for Real-time Stateless Streaming PipelinesChristina Lin
Traditionally, dealing with real-time data pipelines has involved significant overhead, even for straightforward tasks like data transformation or masking. However, in this talk, we’ll venture into the dynamic realm of WebAssembly (WASM) and discover how it can revolutionize the creation of stateless streaming pipelines within a Kafka (Redpanda) broker. These pipelines are adept at managing low-latency, high-data-volume scenarios.
Electric vehicle and photovoltaic advanced roles in enhancing the financial p...IJECEIAES
Climate change's impact on the planet forced the United Nations and governments to promote green energies and electric transportation. The deployments of photovoltaic (PV) and electric vehicle (EV) systems gained stronger momentum due to their numerous advantages over fossil fuel types. The advantages go beyond sustainability to reach financial support and stability. The work in this paper introduces the hybrid system between PV and EV to support industrial and commercial plants. This paper covers the theoretical framework of the proposed hybrid system including the required equation to complete the cost analysis when PV and EV are present. In addition, the proposed design diagram which sets the priorities and requirements of the system is presented. The proposed approach allows setup to advance their power stability, especially during power outages. The presented information supports researchers and plant owners to complete the necessary analysis while promoting the deployment of clean energy. The result of a case study that represents a dairy milk farmer supports the theoretical works and highlights its advanced benefits to existing plants. The short return on investment of the proposed approach supports the paper's novelty approach for the sustainable electrical system. In addition, the proposed system allows for an isolated power setup without the need for a transmission line which enhances the safety of the electrical network
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.
CHINA’S GEO-ECONOMIC OUTREACH IN CENTRAL ASIAN COUNTRIES AND FUTURE PROSPECTjpsjournal1
The rivalry between prominent international actors for dominance over Central Asia's hydrocarbon
reserves and the ancient silk trade route, along with China's diplomatic endeavours in the area, has been
referred to as the "New Great Game." This research centres on the power struggle, considering
geopolitical, geostrategic, and geoeconomic variables. Topics including trade, political hegemony, oil
politics, and conventional and nontraditional security are all explored and explained by the researcher.
Using Mackinder's Heartland, Spykman Rimland, and Hegemonic Stability theories, examines China's role
in Central Asia. This study adheres to the empirical epistemological method and has taken care of
objectivity. This study analyze primary and secondary research documents critically to elaborate role of
china’s geo economic outreach in central Asian countries and its future prospect. China is thriving in trade,
pipeline politics, and winning states, according to this study, thanks to important instruments like the
Shanghai Cooperation Organisation and the Belt and Road Economic Initiative. According to this study,
China is seeing significant success in commerce, pipeline politics, and gaining influence on other
governments. This success may be attributed to the effective utilisation of key tools such as the Shanghai
Cooperation Organisation and the Belt and Road Economic Initiative.
TIME DIVISION MULTIPLEXING TECHNIQUE FOR COMMUNICATION SYSTEMHODECEDSIET
Time Division Multiplexing (TDM) is a method of transmitting multiple signals over a single communication channel by dividing the signal into many segments, each having a very short duration of time. These time slots are then allocated to different data streams, allowing multiple signals to share the same transmission medium efficiently. TDM is widely used in telecommunications and data communication systems.
### How TDM Works
1. **Time Slots Allocation**: The core principle of TDM is to assign distinct time slots to each signal. During each time slot, the respective signal is transmitted, and then the process repeats cyclically. For example, if there are four signals to be transmitted, the TDM cycle will divide time into four slots, each assigned to one signal.
2. **Synchronization**: Synchronization is crucial in TDM systems to ensure that the signals are correctly aligned with their respective time slots. Both the transmitter and receiver must be synchronized to avoid any overlap or loss of data. This synchronization is typically maintained by a clock signal that ensures time slots are accurately aligned.
3. **Frame Structure**: TDM data is organized into frames, where each frame consists of a set of time slots. Each frame is repeated at regular intervals, ensuring continuous transmission of data streams. The frame structure helps in managing the data streams and maintaining the synchronization between the transmitter and receiver.
4. **Multiplexer and Demultiplexer**: At the transmitting end, a multiplexer combines multiple input signals into a single composite signal by assigning each signal to a specific time slot. At the receiving end, a demultiplexer separates the composite signal back into individual signals based on their respective time slots.
### Types of TDM
1. **Synchronous TDM**: In synchronous TDM, time slots are pre-assigned to each signal, regardless of whether the signal has data to transmit or not. This can lead to inefficiencies if some time slots remain empty due to the absence of data.
2. **Asynchronous TDM (or Statistical TDM)**: Asynchronous TDM addresses the inefficiencies of synchronous TDM by allocating time slots dynamically based on the presence of data. Time slots are assigned only when there is data to transmit, which optimizes the use of the communication channel.
### Applications of TDM
- **Telecommunications**: TDM is extensively used in telecommunication systems, such as in T1 and E1 lines, where multiple telephone calls are transmitted over a single line by assigning each call to a specific time slot.
- **Digital Audio and Video Broadcasting**: TDM is used in broadcasting systems to transmit multiple audio or video streams over a single channel, ensuring efficient use of bandwidth.
- **Computer Networks**: TDM is used in network protocols and systems to manage the transmission of data from multiple sources over a single network medium.
### Advantages of TDM
- **Efficient Use of Bandwidth**: TDM all
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.
Batteries -Introduction – Types of Batteries – discharging and charging of battery - characteristics of battery –battery rating- various tests on battery- – Primary battery: silver button cell- Secondary battery :Ni-Cd battery-modern battery: lithium ion battery-maintenance of batteries-choices of batteries for electric vehicle applications.
Fuel Cells: Introduction- importance and classification of fuel cells - description, principle, components, applications of fuel cells: H2-O2 fuel cell, alkaline fuel cell, molten carbonate fuel cell and direct methanol fuel cells.
Introduction- e - waste – definition - sources of e-waste– hazardous substances in e-waste - effects of e-waste on environment and human health- need for e-waste management– e-waste handling rules - waste minimization techniques for managing e-waste – recycling of e-waste - disposal treatment methods of e- waste – mechanism of extraction of precious metal from leaching solution-global Scenario of E-waste – E-waste in India- case studies.
1. TELKOMNIKA Telecommunication Computing Electronics and Control
Vol. 20, No. 4, August 2022, pp. 825~833
ISSN: 1693-6930, DOI: 10.12928/TELKOMNIKA.v20i4.21679 825
Journal homepage: http://telkomnika.uad.ac.id
Brain tumor segmentation using multi-level Otsu thresholding
and Chan-Vese active contour model
Heru Pramono Hadi 1
, Edi Faisal2
, Eko Hari Rachmawanto2
1
Department of Information System, Faculty of Computer Science, Dian Nuswantoro University, Semarang, Indonesia
2
Department of Informatics Engineering, Faculty of Computer Science, Dian Nuswantoro University, Semarang, Indonesia
Article Info ABSTRACT
Article history:
Received Apr 03, 2021
Revised Mar 31, 2022
Accepted Apr 13, 2022
Research on brain tumor segmentation has been developed, ranging from
threshold-based methods to the use of the deep learning algorithm. In this
study, we proposed a region-based brain tumor segmentation method,
namely the active contour model (ACM). Tumor segmentation was carried
out using fluid attenuated inversion recovery (FLAIR) modality magnetic
resonance imaging (MRI) image data obtained from the multimodal brain
tumor image segmentation benchmark (BRATS) 2015 dataset of 86 images.
The initial stage of our segmentation method is to find the initial
initialization point/area for the ACM algorithm using multi-level Otsu
thresholding, with the level used in this study is 3 levels. After the initial
initialization area has been obtained, the segmentation process is continued
with ACM which explores the tumor area to obtain a full and accurate tumor
area result. The results of this study obtained dice similarity (DS) for our
study of 0.7856 with a total time required of 28.080722 seconds, which
better than other method that we also compared with ours, 0.75 compared to
0.78 in term of DS.
Keywords:
Active contour model
Brain tumor
MRI
Multi-level threshold
Segmentation
This is an open access article under the CC BY-SA license.
Corresponding Author:
Heru Pramono Hadi
Department of Information System, Faculty of Computer Science, Dian Nuswantoro University
207 Imam Bonjol Street, Semarang City, Central Java
Email: heru.pramono.hadi@dsn.dinus.ac.id
1. INTRODUCTION
Segmentation is a science in the field of digital image processing that aims to find more information
contained in images. In the medical field, segmentation can assist medical personnel in identifying areas of
the patient’s body with the help of an magnetic resonance imaging (MRI) or computerized tomography (CT)
machine [1]. By utilizing the right segmentation method, the disease can be detected accurately and making it
easier for medical personnel to take steps for healing or adventure [2]. The technology used to describe the
inside of the human body includes MRI and CT. Each technology has advantages and disadvantages. MRI is
safer than the CT method because it does not emit radiation, but the results of the MRI machine image are
affected by noise from the scan results [3]. MRI images can provide a lot of useful information if this
information can be extracted correctly and correctly. For example, in the MRI image of the brain which
contains information about the tumor using a precise and accurate segmentation method, the area of the
tumor can be extracted accurately as well. Brain tumor segmentation has become a popular research topic in
recent years [4].
Several segmentation methods that have been proposed and conducted include the use of popular
clustering algorithms such as the fuzzy C-means (FCM) clustering algorithms [5], [6] and the use of classical
clustering methods such as K-means combined with other algorithms such as in [7] which combines K-means
with mean shift segmentation to reduce file size and detect brain tumors. From all of the clustering methods
2. ISSN: 1693-6930
TELKOMNIKA Telecommun Comput El Control, Vol. 20, No. 4, August 2022: 825-833
826
that have been proposed and conducted, there are still some weaknesses, namely the inability to accurately
distinguish brain tumor areas due to inhomogeneity problems on MRI images. Therefore, the brain tumor
segmentation method developed by utilizing the neural network method to detect tumors as in research [8], [9].
From the results obtained from the segmentation using the neural network, it can be concluded that the
method proposed in each study obtained satisfactory results, but the weakness of each method that uses a
neural network is the relatively long computation time. Therefore, a segmentation method based on the
region/area of the image has emerged, called region-based segmentation. Region-based segmentation
methods such as the active contour model (ACM) are one of the most widely used methods in brain tumor
segmentation research [10], [11].
In general, the ACM method is divided into 2, namely edge-based and region-based, the edge-based
segmentation model is based on information from the edges of the image to determine the path of the
algorithm to the edges of the expected image, whereas the region-based model, segmentation runs based on
information from the edges of the image. Information contained in the surrounding area, by calculating the
statistical value of each region in the image. Many studies that use the ACM method have been carried out,
including by Banday and Mir [12], who proposed a semi-automatic brain tumor segmentation method where
user interaction is required to determine the initial area of the ACM method, uses the gray level co-ocurrence
matrix (GLCM) and gray level run-length matrix (GLRLM) features to generate internal forces and external
forces for ACM, and the Gabor filter is based on an edge-based ACM model. The pricipal component
analysis (PCA) method is also used to reduce the features that have been extracted so that 3 features of each
extraction feature are selected as parameters in the research. Another study using the ACM segmentation
method was proposed by Pham et al. [13], who proposed 2 fitness functions to segment brain tumors
accurately, taking into account local information from MRI images which also remains reliable in dealing
with bias in MRI images. Sun et al. [14] also researched the segmentation of brain tumors using a
combination of 2 algorithms. In his research, we used fuzzy-based energy calculations which were used as
parameters for the ACM algorithm so that the curve would not easily fall to the local minima value. Another
combination method proposed by Sheela overcomes the initial initialization problem of the ACM method and
also the edge area problem of the segmentation results. Sheela and Suganthi [15] uses radius contraction and
expansion to select the initial initialization area, then the FCM algorithm is used to eliminate the resulting
areas from ACM that still have non-tumor areas. Research related to the Chan-Vese-based ACM method was
also conducted by [16] who makes a system that can determine the most appropriate method for segmenting
brain tumors based on previously extracted features, in the form of 12 key features including the mean,
harmonic mean, trimmed mean, max value, median, standard deviation, skewness, kurtosis, entropy, contrast,
energy, and homogeneity, and it was found that the Chan-Vese ACM method can be relied on in brain tumor
segmentation. Combined methods for segmenting brain tumors are proposed by [2] which is divided into 2
stages, first one is eliminating the part of the normal brain using the threshold function then using the Harris
extraction feature algorithm which detects the edges and corners of the observation area to determine the
greatest energy value. From the results of the extraction features, the convex hull method is used to roughly
estimate the portion of the brain tumor which is then used as an initial initialization for the ACM algorithm.
Another research that using the combination of several algorithm such as Kapur’s entropy and Chan-Vese
algorithm conducted by provide 2 proces to segment brain tumor in MRI images. Bat algorithm and Kapur’s
entropry are used for extracting the trilevel of threshold from the image, then segmentation process is done
using active contour segmentation and also as post-processing to identify the boundary of the tumor area.
The use of the brain tumor segmentation method based on the region was also developed by [17] by
adapting the Bayesian theorem method as a parameter to determine the relation between pixels which can
solve the inhomogeneity intensity problem that exists in the MRI image, besides that the proposed method is
claimed to be able to segment tumors accurately even though it is affected by bad noise, by using the Markov
random field as a function of energy with how to form a windows area which will be used to calculate the
relation between pixels. The window area size used in this study is 8. The development of the segmentation
method based on the active contour model is becoming more advanced, as in [3], which developed the
extended local patch fuzzy ACM with a modified superpixel method which is expected to increase the
robustness of the proposed method. The extended localized patch-based fuzzy active contour (ELPFAC)
method that is proposed itself relies on the observation area which is divided into 2 parts which then
calculates each energy from each part with additional energy calculations in the part that has a black area
such as the image background, this is because in the previous method, which was developed by the author,
the black area/background image that is included in the observation area makes a different representation of
the energy in the gray part of the image, in this case, the brain tumor area, so an ELPFAC method was
developed to solve this problem. The ACM method can indeed provide good segmentation results if the
image to be segmented has homogeneous pixels, but in fact, this is not possible, therefore Sandhya et al. [18],
proposes a new method, namely a combination of self organization map (SOM) and ACM where SOM has a
3. TELKOMNIKA Telecommun Comput El Control
Brain tumor segmentation using multi-level Otsu thresholding and … (Heru Pramono Hadi)
827
role to provide information on inhomogeneity intensity for the ACM algorithm. From several studies that
have been done it can be concluded that the ACM method is a powerful method in segmenting MRI images,
but from the overall method a few of the methods that have been proposed mention the selection of a starting
point as the initialization of the ACM algorithm, which is the first step in the segmentation process with the
method. Sauwen et al. [19] proposed a semi-automated method for segmenting tumor region using regularized
non negative matric factorization which calculate the approximate the next area from the user-selected seed for
a fine tumor segmentation, then followed by morphological post-processing to remove the outliers from the
segmentation result. A hybrid method for segmenting brain tumor was proposed by [2], using Harris feature
extraction and convex hull for determining the first area initialization then followed by active contour model
to explore the tumor region and after that a morphological operations was used to remove holes or unwanted
pixel that still persist from the segmentation process.
In this study, we propose a method that can provide initial initialization for the ACM algorithm in
order to obtain accurate and relatively fast tumor segmentation, requiring as fews iteration as possible in the
ACM algorithm. By utilizing the multi-level Otsu threshold applied to MRI images with fluid attenuated
inversion recovery (FLAIR) modality, to find the initial initialization area, the Chan-Vese ACM algorithm is
then used to walk to the surrounding area to find specific tumor areas. The advantages offered by our
proposed method are the speed and low computational cost in segmenting MRI images.
2. RESEARCH METHOD
2.1. Preprocessing
Before the image enters the segmentation stage, the image is subjected to a preprocessing stage to
improve image quality. In this study, we used 2 preprocessing steps, namely noise removal and contrast
adjustment. We also perform image cropping to acquire only the meaningful image information through
these stages:
− Cropping image and convert to grayscale space
The size of the MRI image used in this study is 512×512 pixels, but the dimensions of the image
still leave a slice notation for each extracted MRI image in the lower-left corner, both for MRI images and
ground truth images. Therefore, we cropped the image for both types of images in order to provide accurate
and precise segmentation results, namely in the tumor area alone without any interruption from other parts.
Here, we obtain an image dimension of 317×311 pixels for both types of images. After the image has been
successfully cropped, the MRI image is then converted to a gray image to maximize the results of the
multi-level threshold algorithm.
− Noise removal using Wiener filter
MRI images are often used as objects of research to detect diseases in the human body, but this is
often difficult to do because MRI images are impacted by noise due to the conversion process of the MRI
machine readings [20]. The use of a Wiener filter is considered to be able to eliminate noise contained in
MRI images. Here, wiener filter worked but still maintain the quality at the edges of the image, which plays
an important role in knowing the boundary between the tumor area and the normal brain area.
− Contrast adjustment
The use of the multi-level threshold algorithm works well if the contrast in each image area has a
different intensity value because this will affect the results of the multi-level threshold algorithm. Therefore,
to maximize this, we apply a contrast adjustment algorithm that increases the contrast value of the image to
1% at the lower limit and 1% at the upper limit of the image intensity value. This makes light areas of the
image, such as the tumor area, more visible visually, and dark areas such as the background image darker.
2.2. Multi-level Otsu thresholding
The method for selecting the initial initialization area for the ACM algorithm uses the multi-level
thresholding Otsu proposed by [21]. The multi-level thresholding method is one of the most basic methods
for image segmentation, by utilizing the optimization of the Otsu thresholding criterion calculation [22], [23].
In this study, the number of threshold levels is set at 3 levels and applied to the MRI image that has been
converted into a grayscale image. Multi-level thresholding is based on calculating the minimum value of
variance and the maximum value of variance of an image, the initial step is to divide the image histogram
into 2 parts, then calculate the variance value of the 2 classes to obtain the maximum value of the two classes,
and that is what is used as the threshold value. For the multilevel Otsu thresholding formulation, an image 𝐴
has a gray intensity value of {0,1,2,3,…, L-1}, as if a threshold value t divides the image into foreground (𝐶1)
and background (𝐶0), and for each member of the gray intensity values of each class are 𝐶0 = [0,1,2,3,…, L-1]
and 𝐶1 = [t, t + 1, t + 2, t + 3,…, L-1]. Given 𝑝𝑖 as a probability representation of the gray intensity value 𝑖 that
appears on each image pixel. The equation for calculating the probability of the background as in (1) and
4. ISSN: 1693-6930
TELKOMNIKA Telecommun Comput El Control, Vol. 20, No. 4, August 2022: 825-833
828
foreground as in (2) image 𝐴 [23]. To calculate the mean of the foreground and background the following as
in (3) and as in (4); and for the foreground and background calculation equations are as shown in (5).
𝜔0 (t)= ∑ 𝑝𝑖
𝑡−1
𝑖=0
(1)
𝜔1 (𝑡)= ∑ 𝑝𝑖
𝐿−1
𝑖=𝑡
(2)
𝜇0 (𝑡) = ∑ 𝑖
𝑝𝑖
𝜔0
𝑡−1
𝑖=0 (3)
𝜇1 (𝑡) = ∑ 𝑖
𝑝𝑖
𝜔1
𝐿−1
𝑖=𝑡 (4)
𝜎2(𝑡) = 𝜔0(𝑡). 𝜔1(𝑡). (𝜇0(𝑡) − 𝜇1(𝑡))
2
(5)
The equation for multi-level threshold is almost similar to the Otsu threshold equation, but with the
addition of the variable 𝑠, which contains several levels of variables 𝑡 = 𝑡1, 𝑡2, 𝑡3, … , 𝑡𝑠, which divides the
image into 𝑠 + 1 areas 𝐶0, 𝐶1, 𝐶2, …, 𝐶𝑆+1. The addition of the s variable changes the equation from
calculating the variance between class 𝑠 + 1 to be as follows as in (6). And to get the maximum 𝑡 value
which is the threshold value is as follows [21] as in (7).
𝜇𝑠−1 = ∑ 𝑖.
𝑝𝑖
𝜔𝑗
𝑡𝑠−1
𝑖= 𝑡𝑠−1
(6)
(𝑡1
∗
, 𝑡2
∗
, 𝑡2
∗
, … , 𝑡𝑠
∗) = 𝑚𝑎𝑥
0≤𝑡1,𝑡2,𝑡3,…,𝑡𝑠≤𝐿−1
𝜎2(𝑡1, 𝑡2, 𝑡3, … , 𝑡𝑠) (7)
Based on Figure 1, the red box being the non-tumor area and the blue box being the tumor area.
We can conclude this because we have observed all the datasets we use and from all image datasets we can
make the decision that the largest area that has been detected is a strong candidate as the initial seed for the
initialization of the ACM algorithm. We apply morphological area filtering to select areas from the results of
converting the MRI image to a binary image using a threshold level to extract the area which will be used as
the ACM initialization.
2.3. Active contour model
In this study, the active contour model used is the Chan-Vese model developed by Chan in his
research active contour without edges [24]. Segmented has a severe noise disturbance and inhomogeneity
intensity in the MRI image pixels [18], [25]. This causes the segmentation results to get poor performance
because the Chan-Vese (CV) algorithm is difficult to find the minimum energy point used to generate
internal forces that make the contour moving outward run continuously to find the minimum energy.
However, it does not cover up that ACM is a good method of segmenting MRI images if it is applied to the
right image type. Some of the advantages between ACM and other segmentation methods according to [12]
robust against noise, robust against false edges, and information on shape and texture will improve
segmentation results [18], [26], [27]. For the CV-ACM algorithm mechanism itself is to minimize the energy
function [2] as in (8), where C is a curve that goes along iteration, inside (C) is the inner area of curve C and
outside (C) is the outer area of curve C, and i1 also i2 are input constants for the inside and outside curves,
respectively. Chan-Vese optimized as in (9).
𝐹1(𝐶) + 𝐹2(𝐶) = ∫ |𝐼(𝑥, 𝑦) − 𝑖1|2
𝑑𝑥𝑑𝑦 + ∫ |𝐼(𝑥, 𝑦) − 𝑖2|2
𝑑𝑥𝑑𝑦
𝑜𝑢𝑡𝑠𝑖𝑑𝑒(𝐶)
𝑖𝑛𝑠𝑖𝑑𝑒(𝐶)
(8)
𝐹(𝑖1, 𝑖2, 𝐶) = 𝛼. 𝐿𝑒𝑛𝑔𝑡ℎ(𝐶) + 𝛽. 𝐴𝑟𝑒𝑎(𝑖𝑛𝑠𝑖𝑑𝑒(𝐶)) + 𝑘1 ∫ |𝐼(𝑥, 𝑦) − 𝑖1|2
𝑑𝑥𝑑𝑦 +
𝑖𝑛𝑠𝑖𝑑𝑒(𝐶)
𝑘2 ∫ |𝐼(𝑥, 𝑦) − 𝑖2|2
𝑑𝑥𝑑𝑦
𝑜𝑢𝑡𝑠𝑖𝑑𝑒(𝐶)
(9)
It is intended that the calculation of the C curve function can be calculated at the object boundary,
where 𝛼 ≥ 0, 𝛽 ≥ 0, 𝑘1 𝑎𝑛𝑑 𝑘2 ≥ 0, which are the constant values. The next step for the segmentation stage
is to find the tumor area on the MRI image using the ACM algorithm. At the outset of the explanation of this
study, we stated that our method has the advantage of being the time it takes to achieve the most optimal
results. For this, we conducted several experiments by changing the maximum number of iterations required
for the ACM algorithm to be able to fully segment brain tumors, and we found that the number of iterations
of 20 times is the final result we get from several experiments that have been conducted.
5. TELKOMNIKA Telecommun Comput El Control
Brain tumor segmentation using multi-level Otsu thresholding and … (Heru Pramono Hadi)
829
In Figure 1, are the results of morphological area selection at the multi-level thresholding stage and
then added morphological enhancements that have been used in research [20] which aims to improve image
quality in the sense of connecting between pixels on a separate threshold image and eliminating pixels that
are not included in the structural element used. As shown in Figure 1, the blue square used for initial area of
ACM, but there is also a red square that indicate other candidate for the initial area of ACM, the parameter
we used for choosing the optimal candidate is the biggest blob with the highest intensity value.
The parameters in this study use a ‘disk’ shape with a radius of 5 for structural elements which aims to
connect pixels and a ‘disk’ shape with a radius of 3 for structural elements which aims to eliminate pixels
that are not within the radius of the structural element, so that the initialization area obtained becomes
smoother than the threshold image. It does not affect the process of segmenting the brain tumor area.
Multi threshold
Initial area of ACM
Figure 1. Example results using multi-level threshold and initial area of ACM
3. RESULTS AND ANALYSIS
Our research uses MRI images obtained from the multimodal brain tumor image segmentation
benchmark (BRATS) 2015 image dataset which is widely use in the brain tumor segmentation such as
in [2], [19], [28]. We extracted 86 MRI images from 86 different patients with FLAIR modality as shown in
Figure 2(a) along with ground truth images with slices that correspond to one another as in Figure 2(b).
The choice of FLAIR modality MRI image data is because the FLAIR type has brighter characteristics of the
tumor area compared to other areas, such as normal brain areas and skull bones. The dataset of MRI images
obtained from BRATS 2015 has undergone preprocessing elimination of skull bones so that no additional
preprocessing steps are required for this.
(a) (b)
Figure 2. Brain tumor segmentation: (a) MRI Image and (b) ground truth image
The evaluation used in this study used the dice similarity (DS), Jaccard index (JI), and Hausdorff
distance (HS) calculation which compares dice similarity between original image as shown in Figure 2(a)
MRI image and Figure 2(b) ground thruth image with results of the segmentation image. DS and JI are for
measure overlapping areas of the two images being compared while HS calculated the maximum distance
between two images. The image resulting from segmentation (S) will be compared with the ground truth
image (G) as shown in Figure 2(b) using (12). The more the DS and JI value approach 1 while HS value
approaches 0, it can be interpreted that the image of the segmentation results is similar to the ground truth
image, which means that the segmentation gets accurate results.
6. ISSN: 1693-6930
TELKOMNIKA Telecommun Comput El Control, Vol. 20, No. 4, August 2022: 825-833
830
In addition to measuring the accuracy of segmentation, in Table 1, we also measured the time
required for an MRI image to be segmented. All experiments were carried out using a laptop with an AMD
FX 2.58 Ghz processor with 16 GB RAM, and Matlab 2017b. We present the data for several samples of
MRI image data in the following Table 2. It can be seen from the results of time observations in the Table 1,
the time needed to segment 1 MRI image is 1.5 seconds + 0.3. For the DS results, we obtained satisfactory
results with the average DS for the entire image of 0.7905, an average of 0.6765 for the Jaccard index, and an
average of 33.3947 for the Hausdorff dist. This can be achieved because the maximum number of iterations
is only 20 times. As explained in the sub-chapter of the proposed method, the multilevel threshold algorithm
changes the MRI grayscale image to a binary image with a certain threshold value, in this case, there are 3
levels and what we use is level 3, so only part of the MRI image has a grayish intensity value more than the
threshold level 3 will be converted into a binary image obtained binary image results which will then be
selected to be the initial initialization point for the ACM algorithm. The binary image selection result of the
conversion using the threshold value has the role of eliminating small pixel clusters around the largest area so
that finally an optimal initial initialization area is obtained. In this study, we also conducted several tests for
the maximum number of iterations required and we obtained the following data in the Table 3.
𝐷𝑖𝑐𝑒 𝑠𝑖𝑚𝑖𝑙𝑎𝑟𝑖𝑡𝑦 =
|𝑆∩𝐺|
(|𝑆|+|𝐺|)
2
(12)
𝐽𝑎𝑐𝑐𝑎𝑟𝑑 𝑖𝑛𝑑𝑒𝑥 =
|𝑆∩𝐺|
|𝑆∪𝐺|
(13)
𝑑𝐻𝑎𝑢𝑠𝑑𝑜𝑟𝑓𝑓(𝐺, 𝑆) = 𝑚𝑎𝑥 {𝑚𝑎𝑥
𝑎∈𝐺
𝑚𝑖𝑛
𝑏∈𝑆
‖𝑎 − 𝑏‖ , 𝑚𝑎𝑥
𝑎∈𝑆
𝑚𝑖𝑛
𝑏∈𝐺
‖𝑏 − 𝑎‖} (14)
Table 1. Result of segmentation using ACM
Name Original image Intial mask Segmented image Ground truth
MRI (1).jpg
MRI (2).jpg
MRI (9).jpg
MRI (15).jpg
MRI (16).jpg
Please note that we did not try all sample points for the maximum number of iterations, we used an
interval of 10 starting from 10 to 100. From the results we obtained, it was concluded that the number of
iterations = 20 obtained the highest dice similarity and Jaccard index value among all experiments performed.
Mean while for HS value the best value is obtained at iterations = 50. The MaxIter obtained can be reduced
because the process of initializing the area/starting point of the ACM algorithm is close to the actual tumor
7. TELKOMNIKA Telecommun Comput El Control
Brain tumor segmentation using multi-level Otsu thresholding and … (Heru Pramono Hadi)
831
area, this can be seen in the experimental results Table 1. Chan-Vese’s own ACM method is also reliable in
terms of segmenting the tumor area as in Table 4. At the multilevel threshold stage, the addition of a contrast
adjustment process also plays an important role in determining the area/initialization point.
Table 2. Time taken, DS value, JI value, and HS value
Name Time taken (s) Dice similarity Jaccard index Hausdorff dist
MRI (1).jpg 1.488436 0.7760 0.6694 13.0384
MRI (2).jpg 1.756735 0.9097 0.8523 11.4018
MRI (9).jpg 1.427263 0.9151 0.8344 10.0499
MRI (15).jpg 1.556853 0.9449 0.8925 28.2843
MRI (16).jpg 1.462690 0.9156 0.8392 15
MRI (21).jpg 1.774595 0.9633 0.9291 10.2956
MRI (30).jpg 1.866347 0.9075 0.8306 6.3246
Table 3. Number of iterations with best result
Num of MaxIter Dice similarity Jaccard index Hausdorff dist Time taken (s)
100 0.753289 0.6328116 37.244438 99.634963
90 0.7598404 0.6402436 35.873814 92.432717
80 0.7661297 0.6475711 34.317097 90.242293
70 0.7721321 0.6546112 33.388309 80.650162
60 0.7776351 0.6607835 32.713718 73.543678
50 0.7827799 0.6665037 32.379356 58.926755
40 0.7870497 0.6712934 32.462101 57.151485
30 0.790093 0.6752079 32.856724 47.900759
20 0.7905458 0.6765056 33.394741 36.461008
10 0.7828362 0.6680661 34.716537 33.653083
We also compare the performance of our algorithm if we do not include the additional contrast
adjustment stage, and we get the results for DS = 0.7166 with the time taken is = 40.206 at MaxIter = 20.
This proves that the addition of the contrast adjustment stage has an important role in determining the
area/initialization point, with the difference in DS = 0.0739 and the difference in time taken = 3.745 seconds,
which is quite a big difference. For comparison, we compared the performance of our method with several
methods that have been proposed in Table 4. Please note that we did not try all sample points for the
maximum number of iterations, we used an interval of 10 starting from 10 to 100.
Based on Table 4, iterations = 20 obtains the highest dice similarity and Jaccard index value among
all experiments performed. The MaxIter obtained can be reduced because the process of initializing the
area/starting point of the ACM algorithm is close to the actual tumor area, this can be seen in the
experimental results Table 4. Chan-Vese’s own ACM method is also reliable in terms of segmenting the
tumor area.
Table 4. Segmented image comparison
Authors Segmented image Ground truth Dice similarity
Pei et al. [28] 0.64
Shivhare et al. [29] 0.75
Proposed 0.79
8. ISSN: 1693-6930
TELKOMNIKA Telecommun Comput El Control, Vol. 20, No. 4, August 2022: 825-833
832
4. CONCLUSION
This study focuses on fast and accurate segmentation of brain tumors. The MRI image used in this
study was obtained from the BRATS 2015 dataset by extracting 86 MRI images that had tumors and ground
truth images for each patient. Our proposed method focuses on selecting the initial initialization area/point
for the ACM algorithm. The initial initialization area selection uses the multi-level thresholding algorithm
that implements Otsu thresholding. For the threshold level used in this study, we chose 3 threshold levels,
with the level we used was level 3. After that, the MRI image was converted into a binary image with the
selected threshold and then extracted the largest area as the initial initialization area/point. The next step is
segmentation using the ACM algorithm with the parameter MaxIter = 20. The results obtained from the
method we propose are measured by dice similarity of = 0.7905, Jaccard index of = 0.6765 and Hausdorff
dist of = 33.394, with the time taken = 36.461 seconds. From what we have done in this research, we can
conclude that our proposed method is more accurate and faster than other method we compared with.
For further research, we will develop an ACM algorithm that is more accurate in segmenting MRI images,
while still minimizing the time taken algorithm, so that an accurate and fast, and reliable method of brain
tumor segmentation is obtained.
REFERENCES
[1] S. K. Adhikari, J. K. Sing, D. K. Basu, and M. Nasipuri, "Conditional spatial fuzzy C-means clustering algorithm for
segmentation of MRI images," Applied Soft Computing, vol. 34, pp. 758-769, 2015, doi: 10.1016/j.asoc.2015.05.038.
[2] S. N. Shivhare, S. Sharma, and N. Singh, "An efficient brain tumor detection and segmentation in MRI using parameter-free
clustering," Conference: Machine Intelligence and Signal Analysis, 2018, pp. 485-495, doi: 10.1007/978-981-13-0923-6_42.
[3] N. Alipour and R. P. R. Hasanzadeh, "Superpixel-based brain tumor segmentation in MR images using an extended local fuzzy active
contour model," Multimedia Tools and Applications, vol. 80, no. 5, pp. 8835-8859, 2021, doi: 10.1007/s11042-020-10122-1.
[4] A. Bilenia, D. Sharma, H. Raj, R. Raman, and M. Bhattacharya, "Brain tumor segmentation with skull stripping and modified
fuzzy C-means," in Information and Communication Technology for Intelligent Systems, 2018, vol. 1, pp. 229-237,
doi: 10.1007/978-981-13-1742-2_23.
[5] I. A. R. -Méndez, R. Ureña, and E. H. -Viedma, "Fuzzy clustering approach for brain tumor tissue segmentation in magnetic
resonance images," Soft Computing, vol. 23, no. 20, pp. 10105-10117, 2019, doi: 10.1007/s00500-018-3565-3.
[6] R. Setyawan, M. A. Almahfud, C. A. Sari, D. R. I. M. Setiadi, and E. H. Rachmawanto, "MRI Image Segmentation using
Morphological Enhancement and Noise Removal based on Fuzzy C-means," 2018 5th International Conference on Information
Technology, Computer, and Electrical Engineering (ICITACEE), 2018, pp. 99-104, doi: 10.1109/ICITACEE.2018.8576941.
[7] E. A. -Maksoud, M. Elmogy, and R. Al-Awadi, "Brain tumor segmentation based on a hybrid clustering technique," Egyptian
Informatics Journal, vol. 16, no. 1, pp. 71-81, 2015, doi: 10.1016/j.eij.2015.01.003.
[8] M. M. Thaha, K. P. M. Kumar, B. S. Murugan, S. Dhanasekeran, P. Vijayakarthick, and A. S. Selvi, "Brain tumor segmentation using
convolutional neural networks in MRI images," Journal of Medical Systems, vol. 43, p. 294, 2019, doi: 10.1007/s10916-019-1416-0.
[9] M. M. Lopez and J. Ventura, "Dilated convolutions for brain tumor segmentation in MRI scans," in International MICCAI
Brainlesion Workshop, 2018, vol. 10670, pp. 253-262, doi: 10.1007/978-3-319-75238-9_22.
[10] E. I. -Mbuyamba, J. G. A. -Cervantes, J. C. -Negrete, M. A. I. -Manzano, and C. Chalopin, "Automatic selection of localized
region-based active contour models using image content analysis applied to brain tumor segmentation," Computer in Biology and
Medicine, vol. 91, pp. 69-79, 2017, doi: 10.1016/j.compbiomed.2017.10.003.
[11] Q. Miao, R. Liu, P. Zhao, Y. Li, and E. Sun, "A Semi-Supervised Image Classification Model Based on Improved Ensemble
Projection Algorithm," in IEEE Access, vol. 6, pp. 1372-1379, 2018, doi: 10.1109/ACCESS.2017.2778881.
[12] S. A. Banday and A. H. Mir, "Statistical textural feature and deformable model based MR brain tumor segmentation," 2016
International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2016, pp. 657-663,
doi: 10.1109/ICACCI.2016.7732121.
[13] T. X. Pham, P. Siarry, and H. Oulhadj, "A multi-objective optimization approach for brain MRI segmentation using fuzzy entropy
clustering and region-based active contour methods," Magnetic Resonance Imaging, vol. 61, pp. 41-65, 2019,
doi: 10.1016/j.mri.2019.05.009.
[14] W. Sun, E. Dong, and H. Qiao, "A fuzzy energy-based active contour model with adaptive contrast constraint for local
segmentation," Signal, Image and Video Processing, vol. 12, no. 12, pp. 91-98, 2018, doi: 10.1007/s11760-017-1134-3.
[15] C. J. J. Sheela and G. Suganthi, "Brain tumor segmentation with radius contraction and expansion based initial contour detection for
active contour model," Multimedia Tools and Applications, vol. 79, pp. 23793-23819, 2020, doi: 10.1007/s11042-020-09006-1.
[16] E. I. -Mbuyamba et al., "Localized active contour model with background intensity compensation applied on automatic MR brain
tumor segmentation," Neurocomputing, vol. 220, pp. 84-97, 2017, doi: 10.1016/j.neucom.2016.07.057.
[17] Y. Li, G. Cao, T. Wang, Q. Cui, and B. Wang, "A novel local region-based active contour model for image segmentation using
Bayes theorem," Information Science, vol. 506, pp. 443-456, 2020, doi: 10.1016/j.ins.2019.08.021.
[18] G. Sandhya, G. B. Kande, and T. S. Savithri, "Tumor segmentation by a self-organizing-map based active contour model
(SOMACM) from the Brain MRIs," IETE Journal of Research, pp. 1-13, 2020, doi: 10.1080/03772063.2020.1782780.
[19] N. Sauwen et al., "Semi-automated brain tumor segmentation on multi-parametric MRI using regularized non-negative matrix
factorization," BMC Medical Imaging, vol. 17, p. 29, 2017, doi: 10.1186/s12880-017-0198-4.
[20] R. Setyawan, R. B. Asrori, G. Fajar Shidik, A. Z. Fanani, and R. Anggi Premunendar, "Brain Tumor Identification using FCM
Threshold Method and Morphological Area Selection," 2020 International Seminar on Application for Technology of Information
and Communication (iSemantic), 2020, pp. 560-566, doi: 10.1109/iSemantic50169.2020.9234223.
[21] N. Otsu, "A Threshold Selection Method from Gray-Level Histograms," in IEEE Transactions on Systems, Man, and Cybernetics,
vol. 9, no. 1, pp. 62-66, Jan. 1979, doi: 10.1109/TSMC.1979.4310076.
[22] M. H. Merzban and M. Elbayoumi, "Efficient solution of Otsu multilevel image thresholding: A comparative study," Expert
Systems with Applications, vol. 116, pp. 299-309, 2019, doi: 10.1016/j.eswa.2018.09.008.
[23] L. L. Cao, S. Ding, X. W. Fu, and L. Chen, "Otsu multilevel thresholding segmentation based on quantum particle swarm
9. TELKOMNIKA Telecommun Comput El Control
Brain tumor segmentation using multi-level Otsu thresholding and … (Heru Pramono Hadi)
833
optimisation algorithm," International Journal of Wireless and Mobile Computing, vol. 10, no. 3, pp. 272-277, 2016,
doi: 10.1504/IJWMC.2016.077215.
[24] Y. Yuan and C. He, "Adaptive active contours without edges," Mathematical and Computer Modelling, vol. 55, no. 5-6,
pp. 1705-1721, 2012, doi: 10.1016/j.mcm.2011.11.014.
[25] Y. Song, Z. Ji, Q. Sun, and Y. Zheng, "A novel brain tumor segmentation from multi-modality MRI via a level-set-based model,"
Journal of Signal Processing Systems, vol. 87, no. 2, pp. 249-257, 2017, doi: 10.1007/s11265-016-1188-4.
[26] H. Yu, F. He, and Y. Pan, "A novel region-based active contour model via local patch similarity measure for image
segmentation," Multimedia Tools and Applications, vol. 77, no. 18, pp. 24097-24119, 2018, doi: 10.1007/s11042-018-5697-y.
[27] M. T. Dehkordi, "A new active contour model for tumor segmentation," 2017 3rd International Conference on Pattern
Recognition and Image Analysis (IPRIA), 2017, pp. 233-236, doi: 10.1109/PRIA.2017.7983053.
[28] L. Pei, S. M. S. Reza, W. Li, C. Davatzikos, and K. M. Iftekharuddin, "Improved brain tumor segmentation by utilizing tumor
growth model in longitudinal brain MRI," in Proc. SPIE International Society for Optical Engineering, 2017, vol. 10134,
doi: 10.1117/12.2254034.
[29] S. N. Shivhare, N. Kumar, and N. Singh, "A hybrid of active contour model and convex hull for automated brain tumor
segmentation in multimodal MRI," Multimedia Tools and Applications, vol. 78, no. 4, pp. 34207-34229, 2019,
doi: 10.1007/s11042-019-08048-4.
BIOGRAPHIES OF AUTHORS
Heru Pramono Hadi, S.E., M. Kom is senior lecturer in Information System,
Universitas Dian Nuswantoro since 1994. He received his bachelor from Universitas Negeri
Jember in 1991 and his master from STTBI Jakarta in 2001. Now, he has served as reviewer
and active in several researchs in UDINUS. His research interest in utilization of information
technology and information system. He can be contacted at email:
heru.pramono.hadi@dsn.dinus.ac.id.
Edi Faisal, M. Kom is senior lecture in Informatic Engineering, Universitas Dian
Nuswantoro since 1994. He received the Master’s degree in Informatics Engineering from
STTIBI Jakarta in 2001 and currently studying doctoral in Institut Teknologi Sepuluh
November (ITS). He has recently received research grants from Ristekdikti. His research
interest in data mining, image mining, and artificial intelligent. He can be contacted at email:
faisal@dsn.dinus.ac.id.
Eko Hari Rachmawanto, M. Kom received the Master’s degree in Informatic
Engineering from Universitas Dian Nuswantoro and University Teknikal Malaysia Melaka
(UTeM) in 2012. Now he is lecture in Univresitas Dian Nuswantoro since 2012 and has
interest research in steganography, watermarking and image processing. He also achieved
awarded from Ristekbrin DIKTI as the top 50 best researchers in 2020 and several times
awarded as the best author and best paper in various international conferences. He can be
contacted at email: eko.hari@dsn.dinus.ac.id.