publications: - title: "MRI segmentation of medical images using FCM with initialized class centers via genetic algorithm" author: - name: "Mohammad Ali Balafar" link: "http://balafar.blogfa.com/" - name: "Ramli, A.R." link: "https://researchr.org/alias/ramli%2C-a.r." - name: "SARIPAN, M.I." link: "https://researchr.org/alias/saripan%2C-m.i." - name: "MAHMUD, R." link: "https://researchr.org/alias/mahmud%2C-r." - name: "MASHOHOR, S." link: "https://researchr.org/alias/mashohor%2C-s." - name: "Balafar, H." link: "https://researchr.org/alias/balafar%2C-h." abstract: "Image segmentation is a critical stage in many computer vision and image process applications.Accurate segmentation of medical images is very essential in Medical applications but it is very difficult job due to noise and in homogeneity. Fuzzy C-Mean (FCM) is one of the most popular Medical image clustering methods. We noticed that for some images, FCM is sensitive to initialization of centre of clusters. This article introduced a new method based on the combination of genetic algorithm and FCM to solve this problem. The genetic algorithm is used to find initialized centre of the clusters. In this method, the centre is obtained by minimizing an object Function. This object Function specifies sum of distances between each data and their cluster centres. Then FCM is applied with to the case. The experimental result demonstrates the effectiveness of new method by able to initialize centre of the clusters. " tags: - "rule-based" - "data-flow" - "C++" - "Meta-Environment" - "meta-objects" researchr: "https://researchr.org/publication/balafar-mri-0" cites: 0 citedby: 0 journal: "ITSim 2008" kind: "article" key: "balafar-mri-0" - title: "Medical image segmentation using fuzzy C-mean (FCM), Bayesian method and user interaction" author: - name: "Mohammad Ali Balafar" link: "http://balafar.blogfa.com/" - name: "RAMLI, A.B.D.R." link: "https://researchr.org/alias/ramli%2C-a.b.d.r." - name: "SARIPAN, M.I." link: "https://researchr.org/alias/saripan%2C-m.i." - name: "MASHOHOR, S." link: "https://researchr.org/alias/mashohor%2C-s." abstract: "Image segmentation is one of the most important parts of clinical diagnostic tools. Medical images mostly contain noise and in homogeneity. Therefore, accurate segmentation of medical images is a very difficult task. However, the process of accurate segmentation of these images is very important and crucial for a correct diagnosis by clinical tools. In this paper a new method is proposed which is robust against in-homogeneousness and noisiness of images. The user selects training data for each target class. Noise is reduced in image using Stationary wavelet Transform (SWT) then FCM clusters input image to the n clusters where n is the number of target classes. User selects some of the clusters to be partitioned again. FCM clusters each user selected cluster to two sub clusters. This process continues until user to be satisfied. Each cluster is considered as a sub-class. Posterior probability of data to each sub class is calculated using data in those sub-classes. Probability density of each target class at sub classes is calculated using training data. Probability of data to each target class is calculated using probability density of each subclass at input data and probability of each subclass to each target class. At last, the image is clustered using probability of data to each target class. Segmentation of several simulated and real images are demonstrated to show the effectiveness of the new method. " tags: - "data-flow" - "diagnostics" - "C++" - "partitioning" researchr: "https://researchr.org/publication/balafar-medical" cites: 0 citedby: 0 journal: "ICWAPR 2008" kind: "article" key: "balafar-medical" - title: "Medical image segmentation using fuzzy C-mean (FCM) and dominant grey levels of image" author: - name: "Mohammad Ali Balafar" link: "http://balafar.blogfa.com/" year: "2008" doi: "10.1049/cp:20080329 " abstract: "Image segmentation is a critical part of clinical diagnostic tools. Medical images mostly contain noise. Therefore, accurate segmentation of medical images is highly challenging; however, accurate segmentation of these images is very important in correct diagnosis by clinical tools. We proposed a new method for image segmentation based on dominant grey level of image and fuzzy C-mean (FCM). In the postulated method, the colour image is converted to grey level image and stationary wavelet is applied to decrease noise; the image is clustered using ordinary FCM, afterwards, clusters with error more than a threshold are divided to two sub clusters. This process continues until there remain no such, erroneous, clusters. The dominant connected component of each cluster is obtained - if existed. In obtained dominant connected components, the n biggest connected components are selected. N is specified based upon considered number of clusters. Averages of grey levels of n selected components, in grey level image, are considered as dominant grey levels. Dominant grey levels are used as cluster centres. Eventually, the image is clustered using specified cluster centres. Experimental results are demonstrated to show effectiveness of new method. " tags: - "rule-based" - "model-based diagnostics" - "meta-model" - "diagnostics" - "C++" - "Meta-Environment" researchr: "https://researchr.org/publication/balafar2008medical-0" cites: 0 citedby: 0 journal: "VIE" volume: "2008" number: "CP543 " kind: "article" key: "balafar2008medical-0" - title: "Review of brain MRI image segmentation methods" author: - name: "Mohammad Ali Balafar" link: "http://balafar.blogfa.com/" - name: "Abdul Rahman Ramli" link: "https://researchr.org/alias/abdul-rahman-ramli" - name: "M. Iqbal Saripan" link: "https://researchr.org/alias/m.-iqbal-saripan" - name: "Syamsiah Mashohor" link: "https://researchr.org/alias/syamsiah-mashohor" year: "2010" doi: "http://dx.doi.org/10.1007/s10462-010-9155-0" abstract: "Brain image segmentation is one of the most important parts of clinical diagnostic tools. Brain images mostly contain noise, inhomogeneity and sometimes deviation. Therefore, accurate segmentation of brain images is a very difficult task. However, the process of accurate segmentation of these images is very important and crucial for a correct diagnosis by clinical tools. We presented a review of the methods used in brain segmentation. The review covers imaging modalities, magnetic resonance imaging and methods for noise reduction, inhomogeneity correction and segmentation. We conclude with a discussion on the trend of future research in brain segmentation. Keywords Brain - MRI - Segmentation " links: doi: "http://dx.doi.org/10.1007/s10462-010-9155-0" tags: - "diagnostics" - "reviewing" researchr: "https://researchr.org/publication/BalafarRSM10" cites: 0 citedby: 0 journal: "air" volume: "33" number: "3" pages: "261-274" kind: "article" key: "BalafarRSM10" - title: "Medical Image Segmentation Using Fuzzy C-Mean (FCM), Learning Vector Quantization (LVQ) and User Interaction" author: - name: "Mohammad Ali Balafar" link: "http://balafar.blogfa.com/" - name: "Abdul Rahman Ramli" link: "https://researchr.org/alias/abdul-rahman-ramli" - name: "M. Iqbal Saripan" link: "https://researchr.org/alias/m.-iqbal-saripan" - name: "Rozi Mahmud" link: "https://researchr.org/alias/rozi-mahmud" - name: "Syamsiah Mashohor" link: "https://researchr.org/alias/syamsiah-mashohor" year: "2008" doi: "http://dx.doi.org/10.1007/978-3-540-85930-7_24" abstract: "Accurate segmentation of medical images is very essential in medical applications. We proposed a new method, based on combination of Learning Vector Quantization (LVQ), FCM and user interaction to make segmentation more robust against inequality of content with semantic, low contrast, in homogeneity and noise. In the postulated method, noise is decreased using Stationary wavelet Transform (SWT); input image is clustered using FCM to the n clusters where n is the number of target classes, afterwards, user selects some of the clusters to be partitioned again; each user selected cluster is clustered to two sub clusters using FCM. This process continues until user to be satisfied. Then, user selects clusters for each target class; user selected clusters are used to train LVQ. After training LVQ, image pixels are clustered by LVQ. Segmentation of simulated and real images is demonstrated to show effectiveness of new method. Keywords Learning Vector Quantization (LVQ) - medical image segmentation - user interaction " links: doi: "http://dx.doi.org/10.1007/978-3-540-85930-7_24" tags: - "rule-based" - "C++" - "partitioning" researchr: "https://researchr.org/publication/BalafarRSMM08a" cites: 0 citedby: 0 pages: "177-184" booktitle: "icic" kind: "inproceedings" key: "BalafarRSMM08a" - title: "Medical Image Segmentation Using Anisotropic Filter, User Interaction and Fuzzy C-Mean (FCM)" author: - name: "Mohammad Ali Balafar" link: "http://balafar.blogfa.com/" - name: "Abdul Rahman Ramli" link: "https://researchr.org/alias/abdul-rahman-ramli" - name: "M. Iqbal Saripan" link: "https://researchr.org/alias/m.-iqbal-saripan" - name: "Rozi Mahmud" link: "https://researchr.org/alias/rozi-mahmud" - name: "Syamsiah Mashohor" link: "https://researchr.org/alias/syamsiah-mashohor" year: "2008" doi: "http://dx.doi.org/10.1007/978-3-540-85930-7_23" abstract: "We proposed a new clustering method based on Anisotropic Filter, user interaction and fuzzy c-mean (FCM). In the postulated method, the color image is converted to grey level image and anisotropic filter is applied to decrease noise; User selects training data for each target class, afterwards, the image is clustered using ordinary FCM. Due to in-homogeneity and unknown noise some clusters contain training data for more than one target class. These clusters are partitioned again. This process continues until there are not such clusters. Then, the clusters contain training data for a target class assigned to that target class; Mean of intensity in each class is considered as feature for that class, afterwards, feature distance of each unsigned cluster from different class is found then unsigned clusters are signed to target class with least distance from. Experimental result is demonstrated to show effectiveness of new method. " links: doi: "http://dx.doi.org/10.1007/978-3-540-85930-7_23" tags: - "rule-based" - "data-flow" - "C++" - "partitioning" researchr: "https://researchr.org/publication/BalafarRSMM08" cites: 0 citedby: 0 pages: "169-176" booktitle: "icic" kind: "inproceedings" key: "BalafarRSMM08" - title: "Improved Fast Fuzzy C-Mean and its Application in Medical Image Segmentation" author: - name: "Mohammad Ali Balafar" link: "http://balafar.blogfa.com/" - name: "Abdul Rahman Ramli" link: "https://researchr.org/alias/abdul-rahman-ramli" - name: "M. Iqbal Saripan" link: "https://researchr.org/alias/m.-iqbal-saripan" - name: "Syamsiah Mashohor" link: "https://researchr.org/alias/syamsiah-mashohor" - name: "Rozi Mahmud" link: "https://researchr.org/alias/rozi-mahmud" year: "2010" doi: "http://dx.doi.org/10.1142/S0218126610006001" abstract: "Image segmentation is a preliminary stage in diagnosis tools and the accurate segmentation of medical images is crucial for a correct diagnosis by these tools. Sometimes, due to inhomogeneity, low contrast, noise and inequality of content with semantic, automatic methods fail to segment image correctly. Therefore, for these images, it is necessary to use user help to correct method's error. We proposed to upgrade FAST FCM method to use training data to have more accurate results. In this paper, instead of using pixels as training data which is usual, we used di®erent gray levels as training data and that is why we have used FASTFCM, because the input of FASTFCM is gray levels exist in image (histogram of the image). We named the new clustering method improved fast fuzzy C-mean (FCM). We use two facts to improve fast FCM. First, training data for each class are the member of the class. Second, the relevance distance of each input data from the training data of a class show the distance of the input data from the class. To cluster an image, ¯rst, the color image is converted to gray level image; then, from histogram of image, user selects training data for each target class, afterwards, the image is clustered using postulated clustering method. Experimental result is demonstrated to show e®ectiveness of the new method. Keywords: Image segmentation; supervised methods; MRI." links: doi: "http://dx.doi.org/10.1142/S0218126610006001" tags: - "data-flow" - "C++" - "e-science" researchr: "https://researchr.org/publication/BalafarRSMM10a" cites: 0 citedby: 0 journal: "jcsc" volume: "19" number: "1" pages: "203-214" kind: "article" key: "BalafarRSMM10a" - title: "New multi-scale medical image segmentation based on fuzzy c-mean (FCM)" author: - name: "Mohammad Ali Balafar" link: "http://balafar.blogfa.com/" - name: "RAMLI, A.B.D.R." link: "https://researchr.org/alias/ramli%2C-a.b.d.r." - name: "SARIPAN, M.I." link: "https://researchr.org/alias/saripan%2C-m.i." - name: "MAHMUD, R." link: "https://researchr.org/alias/mahmud%2C-r." - name: "MASHOHOR, S." link: "https://researchr.org/alias/mashohor%2C-s." - name: "BALAFAR, M." link: "https://researchr.org/alias/balafar%2C-m." abstract: "Image segmentation is a key process in computer vision and image process applications. Accurate segmentation of medical images is very essential in medical applications but it is very difficult job due to noise and in homogeneity that are usual of medical images. In this paper a new method, based on FCM, is proposed to make FCM more robust against noise. Multi-scale images are obtained by smoothing input image in different scales. FCM is applied to multi-scale images from high scale to low scale. First FCM is applied to image with highest scale. Then in each scale, cluster centers of previous scale are used to initialization membership for current scale. Moreover, in FCM, neighborhood attraction is used to more decrease effect of noise in clustering. Experimental result shows effectiveness of new method. " tags: - "rule-based" - "C++" researchr: "https://researchr.org/publication/balafar-new-0" cites: 0 citedby: 0 journal: "CITISIA 2008" kind: "article" key: "balafar-new-0" - title: "A new method for MR grayscale inhomogeneity correction" author: - name: "Mohammad Ali Balafar" link: "http://balafar.blogfa.com/" - name: "Abdul Rahman Ramli" link: "https://researchr.org/alias/abdul-rahman-ramli" - name: "Syamsiah Mashohor" link: "https://researchr.org/alias/syamsiah-mashohor" year: "2010" abstract: "Intensity inhomogeneity is a smooth intensity change inside originally homogeneous regions. Filter-based inhomogeneity correction methods have been commonly used in literatures. However, there are few literatures which compare effectiveness of these methods for inhomogeneity correction. In this paper, a new filter-based inhomogeneity correction method is proposed and the effectiveness of the proposed method and other filter-based inhomogeneity correction methods are compared. The methods with different kernel sizes are applied on MRI brain images and the quality of inhomogeneity correction of different methods are compared quantitatively. Experimental results show the proposed method in a kernel size of 20 * 20 performs almost better than or equal the performance of other methods in all kernel sizes. " links: "url": "http://dx.doi.org/10.1007/s10462-010-9169-7" tags: - "rule-based" researchr: "https://researchr.org/publication/springerlink%3A10.1007-s10462-010-9169-7" cites: 0 citedby: 0 journal: "Artificial Intelligence Review" volume: "34" kind: "article" key: "springerlink:10.1007-s10462-010-9169-7" - title: "Edge-preserving Clustering Algorithms and Their Application for MRI Image Segmentation" author: - name: "Mohammad Ali Balafar" link: "http://balafar.blogfa.com/" - name: "A. R. Ramli" link: "https://researchr.org/alias/a.-r.-ramli" - name: "MASHOHOR, S." link: "https://researchr.org/alias/mashohor%2C-s." year: "2010" abstract: "our lately defined edge-preserving neighborhood is used to improve an already exist extension for Fuzzy C-Mean (FCM). In the defined neighborhood, a window is centered on the pixel. Then, each sample, in the window, is considered the neighbor of the pixel if there is not any edge between the sample and the pixel. Moreover two extensions for Expectation Maximizing (EM) are introduced to have better clustering results in presence of noise. Promising experimental results of our proposed extensions in compare to two state-of-art extensions for FCM demonstrate the potential of proposed modifications. Index Terms—Neighborhood information, Brain segmentation." tags: - "C++" researchr: "https://researchr.org/publication/balafar2010edge-0" cites: 0 citedby: 0 journal: "Lecture Notes in Engineering and Computer Science" volume: "2180" number: "1" kind: "article" key: "balafar2010edge-0" - title: "2009 Reviewers" author: - name: "ASV, R.K." link: "https://researchr.org/alias/asv%2C-r.k." - name: "Emmanuel, I." link: "https://researchr.org/alias/emmanuel%2C-i." - name: "Abbas, Z." link: "https://researchr.org/alias/abbas%2C-z." - name: "Abbasbandy, S." link: "https://researchr.org/alias/abbasbandy%2C-s." - name: "Abdallah, S." link: "https://researchr.org/alias/abdallah%2C-s." - name: "Ahmad, B." link: "https://researchr.org/alias/ahmad%2C-b." - name: "Akl, S.G." link: "https://researchr.org/alias/akl%2C-s.g." - name: "Al-Baali, M." link: "https://researchr.org/alias/al-baali%2C-m." - name: "Al-Dosary, K." link: "https://researchr.org/alias/al-dosary%2C-k." - name: "Al-Hassan, Q." link: "https://researchr.org/alias/al-hassan%2C-q." - name: "Mohammad Ali Balafar" link: "http://balafar.blogfa.com/" year: "2009" abstract: "In addition to acknowledging the assistance of the members of the Editorial Board, the Editors would like to thank the following people who have offered their assistance in reviewing IJCM submissions over the past year (1 October 2008-30 September 2009). " tags: - "reviewing" researchr: "https://researchr.org/publication/asv20092009-0" cites: 0 citedby: 0 journal: "International Journal of Computer Mathematics" volume: "86" number: "12" kind: "article" key: "asv20092009-0" - title: "Medical Image Segmentation Using Fuzzy C-Mean (FCM) and User Specified Data" author: - name: "Mohammad Ali Balafar" link: "http://balafar.blogfa.com/" - name: "Abdul Rahman Ramli" link: "https://researchr.org/alias/abdul-rahman-ramli" - name: "M. Iqbal Saripan" link: "https://researchr.org/alias/m.-iqbal-saripan" - name: "Syamsiah Mashohor" link: "https://researchr.org/alias/syamsiah-mashohor" - name: "Rozi Mahmud" link: "https://researchr.org/alias/rozi-mahmud" year: "2010" doi: "http://dx.doi.org/10.1142/S0218126610005913" abstract: "Image segmentation is one of the most important parts of clinical diagnostic tools. Medical images mostly contain noise and inhomogeneity. Therefore, accurate segmentation of medical images is a very di±cult task. However, the process of accurate segmentation of these images is very important and crucial for a correct diagnosis by clinical tools. We proposed a new clustering method based on Fuzzy C-Mean (FCM) and user speci¯ed data. In the postulated method, the color image is converted to grey level image and anisotropic ¯lter is applied to decrease noise; User selects training data for each target class, afterwards, the image is clustered using ordinary FCM. Due to inhomogeneity and unknown noise some clusters contain training data for more than one target class. These clusters are partitioned again. This process continues until there are no such clusters. Then, the clusters contain training data for a target class assigned to that target class; Mean of intensity in each class is considered as feature for that class, afterwards, feature distance of each unsigned cluster from di®erent class is found then unsigned clusters are signed to target class with least distance from. Experimental result is demonstrated to show e®ectiveness of new method. Keywords: Image segmentation; supervised methods; MRI; FCM; re-clustering." links: doi: "http://dx.doi.org/10.1142/S0218126610005913" tags: - "rule-based" - "model-based diagnostics" - "data-flow" - "diagnostics" - "C++" - "e-science" - "partitioning" researchr: "https://researchr.org/publication/BalafarRSMM10" cites: 0 citedby: 0 journal: "jcsc" volume: "19" number: "1" pages: "1-14" kind: "article" key: "BalafarRSMM10"