International Journal of Current Research and Review
ISSN: 2231-2196 (Print)ISSN: 0975-5241 (Online)
Bootstrap Slider

Indexed and Abstracted in: Crossref, CAS Abstracts, Publons, CiteFactor, Open J-Gate, ROAD, Indian Citation Index (ICI), Indian Journals Index (IJINDEX), Internet Archive, IP Indexing, Google Scholar, Scientific Indexing Services, Index Copernicus, ResearchBib, Science Central, Revistas Medicas Portuguesas, EBSCO, BOAI, SOROS, NEWJOUR, ResearchGATE, Ulrich's Periodicals Directory, DocStoc, PdfCast, getCITED, SkyDrive, Citebase, e-Print, WorldCat (World's largest network of library content and services), Electronic Journals Library by University Library of Regensburg, SciPeople.

Search Articles

Track manuscript

Readers around the world

Full Html

IJCRR - Vol 04 issue 13, July, 2012

Pages: 114-118

Date of Publication: 18-Jul-2012


Print Article   Download XML  Download PDF

AUTOMATIC MEDICAL IMAGE SEGMENTATION USING SPATIAL FUZZY CLUSTERING METHOD

Author: R.Aishwarya

Category: General Sciences

Abstract:The performance of the set segmentation is subject to appropriate initialization and optimal configuration of controlling parameters, which requires substantial manual intervention. A new fuzzy level set algorithm is proposed in this paper to facilitate medical image segmentation. Moreover fuzzy level set algorithm is enhanced with locally regularized evolution. Such improvements facilitate level set manipulation and lead to more robust segmentation. Performance evaluation of the proposed algorithm was carried on medical images from different modalities .the results confirm its effectiveness for medical image segmentation.

Keywords: Fuzzy logic, Clustering, Image segmentation, Level set method.

Full Text:

INTRODUCTION
Segmentation is defined as partitioning portions of an image. It adds structure to a raw image. In the case of medicine, this can involve identifying which portions of an image is the tumor, or separating white matter from grey matter in a brain scan. Segmentation is a vital aspect of medical imaging. It aids in the visualization of medical data and diagnostics of various dieses. The result of image segmentation is a set of segments that collectively cover the entire image, or a set of contours extracted from the image (see edge detection). Each of the pixels in a region are similar with respect to some characteristic or computed property, such as color, intensity, or texture. Adjacent regions are significantly different with respect to the same characteristic(s). When applied to a stack of images, typical in Medical imaging, the resulting contours after image segmentation can be used to create 3D reconstructions with the help of interpolation algorithms like marching cubes. we will restrict most of our discussion to approaches that generalize the statistical inference beyond first and second moments to entire probability density functions (pdf). From this, segmentation can be reinterpreted as measuring the ?distance? between two distributions via a similarity metric. we relax the assumption of a-priori knowledge, and focus on the accurate segmentation of biological structures or pathologies found in medical imagery. A qualitative comparison between the Bhattacharyya distance and our newly proposed metric is then done to highlight the notion that similarity measures can not be applied equally for image segmentation. In particular situations, one distribution metric may prevail while another measure may be highly dependent on the initialization or statistical information. To the best of our knowledge, a qualitative comparison of segmentation results has not been made.

Digital Image Segmentation
Image segmentation plays an important role in image analysis and computer vision. The goal of image segmentation is partitioning of an image into a set of disjoint regions with uniform and homogeneous attributes such as intensity, color, tone etc. The image segmentation approaches can be divided into four categories; thresholding, clustering, edge detection, and region extraction. In color images, the boundaries between objects are blurred and distorted due to the imaging acquisition process. Furthermore, object definitions are not always crisp and knowledge about the objects in a scene may be vague. Segmentation is a vital aspect of medical imaging. It aids in the visualization of medical data and diagnostics of various dieses. This report presents an implementation of a level set approach for active contour image segmentation. This method is originally developed by Osher and Sethian and then applied to image segmentation by Malladi. No requirements about objects‘ shape and allowance for very flexible topology change are key advantages for this method. Partitional clustering essentially deals with the task of partitioning a set of entities into a number of homogeneous clusters, with respect to a suitable similarity measure. Due to the fuzzy nature of many practical problems, a number of fuzzy clustering methods have been developed following the general fuzzy set theory strategies outlined by Zadeh, The main difference between the traditional hard clustering and fuzzy clustering can be stated as follows. While in hard clustering an entity belongs only to one cluster, in fuzzy clustering entities are allowed to belong to many clusters with discerent degrees of membership.

Partitional clustering essentially deals with the task of partitioning a set of entities into a number of homogeneous clusters, with respect to the fuzzy cluster structure relates to the data from which it is derived, from this different clusters and shapes can be identified. The data is generated from a cluster structure identified. Image segmentation plays an important role in image analysis and computer vision. The goal of image segmentation is partitioning of an image into a set of disjoint regions with uniform and homogeneous attributes such as intensity, color, tone etc. The image segmentation approaches can be divided into four categories; thresholding, clustering, edge detection, and region extraction. In color images, the boundaries between objects are blurred and distorted due to the imaging acquisition process. Furthermore, object definitions are not always crisp and knowledge about the objects in a scene may be vague. Fuzzy set theory and Fuzzy logic are ideally suited to deal with such uncertainties. Fuzzy clustering models have proved a particularly promising solution to the color clustering problem. Such unsupervised models can be used with any number of features and clusters. The Fuzzy C means (FCM) algorithm, proposed by Bezdek (1981), is the first and most widely used algorithm in image segmentation because it has robust characteristics for ambiguity and can retain much more information than hard segmentation methods. Clustering The notion of a cluster varies between algorithms and is one of the many decisions to take when choosing the appropriate algorithm for a particular problem. A clustering is essentially a set of such clusters, usually containing all objects in the data set. Additionally, it may specify the relationship of the clusters to each other, At first the terminology of a cluster seems obvious: a group of data objects. However, the clusters found by different algorithms vary significantly in their properties, and understanding these cluster models is key to understanding the differences between the various algorithms. Typical cluster models include: Connectivity models: for example hierarchical clustering builds models based on distance connectivity. Centroid models: for example the k-means algorithm represents each cluster by a single mean vector. Distribution models: clusters are modeled using statistic distributions, such as multivariate normal distributions used by the Expectation-maximization algorithm. Density models: for example DBSCAN and OPTICS defines clusters as connected dense regions in the data space. Subspace models: in Biclustering (also known as Co-clustering or two-mode-clustering), clusters are modeled with both cluster members and relevant attributes. Group models: some algorithms (unfortunately) do not provide a refined model for their results and just provide the grouping information. A hierarchy of clusters embedded in each other. Clusterings can be roughly distinguished in:

hard clustering: each object belongs to a cluster or not soft clustering (also: fuzzy clustering): each object belongs to each cluster to a certain degree (e.g. a likelihood of belonging to the cluster).

Fuzzy Clustering
Clustering is the process of dividing the data into homogenous regions based on the similarity of objects; information that is logically similar physically is stored together, in order to increase the efficiency in the database system and to minimize the number of disk access. The process of clustering is to assign the q feature vectors into K clusters, for each kth cluster Ck is its center. Fuzzy Clustering has been used in many fields like pattern recognition and Fuzzy identification. A variety of Fuzzy clustering methods have been proposed and most of them are based upon distance criteria. The most widely used algorithm is the Fuzzy C-Mean algorithm (FCM), it uses reciprocal distance to compute fuzzy weights. This algorithm has as input a predefined number of clusters, which is the k from its name. Means stands for an average location of all the members of particular cluster and the output is a partitioning of k cluster on a set of objects. The objective of the FCM cluster is to minimize the total weighted mean square error: The FCM allows each feature vector to belong to multiple clusters with various fuzzy membership values . Then the final classification will be according to the maximum weight of the feature vector over all clusters. The detailed algorithm: Input: Vectors of objects, each object represent s dimensions, where v = {v1,v2,……,vn} in our case it will be an image pixels, each pixel has three dimensions RGB, K = number of clusters. Output = a set of K clusters which minimize the sum of distance error. Algorithm steps: (1) Initialize random weight for each pixel, it uses fuzzy weighting with positive weights {Wqk } between [0, 1]. (2) Standardize the initial weights for each qth feature vector over all K clusters via (3) Standardize the weights over k = 1,…,K for each q to obtain Wqk

SIMULATION RESULTS
We test our region-based segmentation model on several images, which further demonstrates the viability and possible advantage of our distribution metric for image segmentation. A common example that is often tested with energy models that discriminate on probability distributions is the zebra image. The goal here is to capture the entire zebra by separating the distributions so as to obtain a bimodal ?Object? with a unimodal background. We note that several segmentation methods have been able to capture this image. However, for the sake of completeness, we show results in Figure 4. Stages of the segmentation are shown along with the corresponding plots of the probability distributions. Segmenting biological structures from medical images is often a challenging task. This is due to the inherent inhomogeneous distribution of a photometric variable as well as the low contrast and noise (as seen in the Kaposi Sarcoma). In the remaining examples, we segment both the corpus callosum and an MRI image of a heart.

CONCLUSION
We introduce a new metric for image segmentation that quantifies the ?distance? between two distributions as the standard deviation of the difference between logarithms of those densities. While several metrics and measures have been proposed for image segmentation, results often vary drastically. Specifically, although separating distributions using the Bhattacharyya distance as a measure has resulted in the successful segmentation on some challenging imagery, in other cases such as the Kaposi Sarcoma, the Bhattacharyya - based algorithm fails to capture the infected portion of the skin while the energy model proposed in this paper results in a successful segmentation. The differing segmentation results can be traced to how the respective metrics penalize perturbations on a manifold of distributions. Thus, a subject of future work is to investigate and clarify how differences in metrics affect segmentation.

References:

1. X. Han, C. Xu and J. Prince, ?A topology preserving level set method for geometric deformable models?, IEEE Trans. Patt. Anal. Mach. Intell., vol. 25, pp. 755-768, 2003.

2. J. Gomes and O. Faugeras, ?Reconciling distance functions and Level Sets?, J. Visiual Communic. and Imag. Representation, vol. 11, pp. 209-223, 2000.

3. R. Malladi, J. A. Sethian, and B. C. Vemuri, ?Shape modeling with front propagation: a level set approach?, IEEE Trans. Patt. Anal. Mach. Intell., vol. 17, pp. 158-175, 1995.

4. T. Georgiou, ?Distances and riemannian metrics for spectral density functions,? IEEE Trans. on Signal Processing (8), pp. 3395– 4003, 2007.

5. B. Vemuri and Y. Chen, ?Joint image registration and segmentation", Geometric Level Set Methods in Imaging, Vision, and Graphics, Springer, pp. 251-269, 2003.

6. Chen Zhang and Shixiong Xia, ? K-means Clustering Algorithm with Improved Initial center,? in Second International Workshop on Knowledge Discovery and Data Mining (WKDD), pp. 790-792, 2009.

7. P. Bradley, U. Fayyad, Refining initial points for k-means clustering, Proceedings 15th International Conf, on Machine Learning, San Francisco, CA, 1998, pp. 91-99.

8. J. Pena, J. Lozano and P. Larranaga, An Empirical comparison of four initialization methods for the k-means algorithm, Pattern Recognition Letters Vol. 20, 1999.

9. S.L.Chiu, Fuzzy model identification based on cluster estimation, Journal of Intelligent and Fuzzy Systems.

10. Kiyotaka Mizutani and Sadaaki Miyamoto, Possibilistic Approach to Kernel- Based Fuzzy c-Means Clustering .

Announcements

Dr. Pramod Kumar Manjhi joined Editor-in-Chief since July 2021 onwards

SCOPUS (2014, 2019, 2020, 2021 (Till June) currently under re-evaluation)

COPE guidelines for Reviewers


Awards, Research and Publication incentive Schemes by IJCRR

Best Article Award: 

One article from every issue is selected for the ‘Best Article Award’. Authors of selected ‘Best Article’ are rewarded with a certificate. IJCRR Editorial Board members select one ‘Best Article’ from the published issue based on originality, novelty, social usefulness of the work. The corresponding author of selected ‘Best Article Award’ is communicated and information of award is displayed on IJCRR’s website. Drop a mail to editor@ijcrr.com for more details.

Women Researcher Award:

This award is instituted to encourage women researchers to publish her work in IJCRR. Women researcher, who intends to publish her research work in IJCRR as the first author is eligible to apply for this award. Editorial Board members decide on the selection of women researchers based on the originality, novelty, and social contribution of the research work. The corresponding author of the selected manuscript is communicated and information is displayed on IJCRR’s website. Under this award selected women, the author is eligible for publication incentives. Drop a mail to editor@ijcrr.com for more details.

Emerging Researcher Award:

‘Emerging Researcher Award’ is instituted to encourage student researchers to publish their work in IJCRR. Student researchers, who intend to publish their research or review work in IJCRR as the first author are eligible to apply for this award. Editorial Board members decide on the selection of student researchers for the said award based on originality, novelty, and social applicability of the research work. Under this award selected student researcher is eligible for publication incentives. Drop a mail to editor@ijcrr.com for more details.


Best Article Award

A Study by M. Muthu Uma Maheswari et al. entitled "A Study on C-reactive Protein and Liver Function Tests in Laboratory RT-PCR Positive Covid-19 Patients in a Tertiary Care Centre – A Retrospective Study" is awarded Best Article of Vol 13 issue 06 Special issue Modern approaches for diagnosis of COVID-19 and current status of awareness
A Study by Gainneos PD et al. entitled "A Comparative Evaluation of the Levels of Salivary IgA in HIV Affected Children and the Children of the General Population within the Age Group of 9 – 12 Years – A Cross-Sectional Study" is awarded Best Article of Vol 13 issue 05 Special issue on Recent Advances in Dentistry for better Oral Health
A Study by Alkhansa Mahmoud et al. entitled "mRNA Expression of Somatostatin Receptors (1-5) in MCF7 and MDA-MB231 Breast Cancer Cells" is awarded Best Article of Vol 13 issue 06
A Study by Chen YY and Ghazali SRB entitled "Lifetime Trauma, posttraumatic stress disorder Symptoms and Early Adolescence Risk Factors for Poor Physical Health Outcome Among Malaysian Adolescents" is awarded Best Article of Vol 13 issue 04 Special issue on Current Updates in Plant Biology to Medicine to Healthcare Awareness in Malaysia
A Study by Kumari PM et al. entitled "Study to Evaluate the Adverse Drug Reactions in a Tertiary Care Teaching Hospital in Tamilnadu - A Cross-Sectional Study" is awarded Best Article for Vol 13 issue 05
A Study by Anu et al. entitled "Effectiveness of Cytological Scoring Systems for Evaluation of Breast Lesion Cytology with its Histopathological Correlation" is awarded Best Article of Vol 13 issue 04
A Study by Sharipov R. Kh. et al. entitled "Interaction of Correction of Lipid Peroxidation Disorders with Oxibral" is awarded Best Article of Vol 13 issue 03
A Study by Tarek Elwakil et al. entitled "Led Light Photobiomodulation Effect on Wound Healing Combined with Phenytoin in Mice Model" is awarded Best Article of Vol 13 issue 02
A Study by Mohita Ray et al. entitled "Accuracy of Intra-Operative Frozen Section Consultation of Gastrointestinal Biopsy Samples in Correlation with the Final Histopathological Diagnosis" is awarded Best Article for Vol 13 issue 01
A Study by Badritdinova MN et al. entitled "Peculiarities of a Pain in Patients with Ischemic Heart Disease in the Presence of Individual Combines of the Metabolic Syndrome" is awarded Best Article for Vol 12 issue 24
A Study by Sindhu Priya E S et al. entitled "Neuroprotective activity of Pyrazolone Derivatives Against Paraquat-induced Oxidative Stress and Locomotor Impairment in Drosophila melanogaster" is awarded Best Article for Vol 12 issue 23
A Study by Habiba Suhail et al. entitled "Effect of Majoon Murmakki in Dysmenorrhoea (Usre Tams): A Standard Controlled Clinical Study" is awarded Best Article for Vol 12 issue 22
A Study by Ghaffar UB et al. entitled "Correlation between Height and Foot Length in Saudi Population in Majmaah, Saudi Arabia" is awarded Best Article for Vol 12 issue 21
A Study by Leow Jun Xian and Siti Sarah Binti Maidin entitled "Sleep Well: Mobile Application to Address Sleeping Problems" is awarded Best Article for Vol 12 issue 20
A Study by Avijit Singh et al. entitled "Comparison of Post Operative Clinical Outcomes Between “Made in India” TTK Chitra Mechanical Heart Valve Versus St Jude Mechanical Heart Valve in Valve Replacement Surgery" is awarded Best Article for Vol 12 issue 19
A Study by Sonali Banerjee and Mary Mathews N. entitled "Exploring Quality of Life and Perceived Experiences Among Couples Undergoing Fertility Treatment in Western India: A Mixed Methodology" is awarded Best Article for Vol 12 issue 18
A Study by Jabbar Desai et al. entitled "Prevalence of Obstructive Airway Disease in Patients with Ischemic Heart Disease and Hypertension" is awarded Best Article for Vol 12 issue 17
A Study by Juna Byun et al. entitled "Study on Difference in Coronavirus-19 Related Anxiety between Face-to-face and Non-face-to-face Classes among University Students in South Korea" is awarded Best Article for Vol 12 issue 16
A Study by Sudha Ramachandra & Vinay Chavan entitled "Enhanced-Hybrid-Age Layered Population Structure (E-Hybrid-ALPS): A Genetic Algorithm with Adaptive Crossover for Molecular Docking Studies of Drug Discovery Process" is awarded Best article for Vol 12 issue 15
A Study by Varsha M. Shindhe et al. entitled "A Study on Effect of Smokeless Tobacco on Pulmonary Function Tests in Class IV Workers of USM-KLE (Universiti Sains Malaysia-Karnataka Lingayat Education Society) International Medical Programme, Belagavi" is awarded Best article of Vol 12 issue 14, July 2020
A study by Amruta Choudhary et al. entitled "Family Planning Knowledge, Attitude and Practice Among Women of Reproductive Age from Rural Area of Central India" is awarded Best Article for special issue "Modern Therapeutics Applications"
A study by Raunak Das entitled "Study of Cardiovascular Dysfunctions in Interstitial Lung Diseas epatients by Correlating the Levels of Serum NT PRO BNP and Microalbuminuria (Biomarkers of Cardiovascular Dysfunction) with Echocardiographic, Bronchoscopic and HighResolution Computed Tomography Findings of These ILD Patients" is awarded Best Article of Vol 12 issue 13 
A Study by Kannamani Ramasamy et al. entitled "COVID-19 Situation at Chennai City – Forecasting for the Better Pandemic Management" is awarded best article for  Vol 12 issue 12
A Study by Muhammet Lutfi SELCUK and Fatma COLAKOGLU entitled "Distinction of Gray and White Matter for Some Histological Staining Methods in New Zealand Rabbit's Brain" is awarded best article for  Vol 12 issue 11
A Study by Anamul Haq et al. entitled "Etiology of Abnormal Uterine Bleeding in Adolescents – Emphasis Upon Polycystic Ovarian Syndrome" is awarded best article for  Vol 12 issue 10
A Study by Arpita M. et al entitled "Estimation of Reference Interval of Serum Progesterone During Three Trimesters of Normal Pregnancy in a Tertiary Care Hospital of Kolkata" is awarded best article for  Vol 12 issue 09
A Study by Ilona Gracie De Souza & Pavan Kumar G. entitled "Effect of Releasing Myofascial Chain in Patients with Patellofemoral Pain Syndrome - A Randomized Clinical Trial" is awarded best article for  Vol 12 issue 08
A Study by Virendra Atam et. al. entitled "Clinical Profile and Short - Term Mortality Predictors in Acute Stroke with Emphasis on Stress Hyperglycemia and THRIVE Score : An Observational Study" is awarded best article for  Vol 12 issue 07
A Study by K. Krupashree et. al. entitled "Protective Effects of Picrorhizakurroa Against Fumonisin B1 Induced Hepatotoxicity in Mice" is awarded best article for issue Vol 10 issue 20
A study by Mithun K.P. et al "Larvicidal Activity of Crude Solanum Nigrum Leaf and Berries Extract Against Dengue Vector-Aedesaegypti" is awarded Best Article for Vol 10 issue 14 of IJCRR
A study by Asha Menon "Women in Child Care and Early Education: Truly Nontraditional Work" is awarded Best Article for Vol 10 issue 13
A study by Deep J. M. "Prevalence of Molar-Incisor Hypomineralization in 7-13 Years Old Children of Biratnagar, Nepal: A Cross Sectional Study" is awarded Best Article for Vol 10 issue 11 of IJCRR
A review by Chitra et al to analyse relation between Obesity and Type 2 diabetes is awarded 'Best Article' for Vol 10 issue 10 by IJCRR. 
A study by Karanpreet et al "Pregnancy Induced Hypertension: A Study on Its Multisystem Involvement" is given Best Paper Award for Vol 10 issue 09
Late to bed everyday? You may die early, get depression
Egg a day tied to lower risk of heart disease
88 Percent Of Delhi Population Has Vitamin D Deficiency: ASSOCHAM Report

List of Awardees

A Study by Alkhansa Mahmoud et al. entitled "mRNA Expression of Somatostatin Receptors (1-5) in MCF7 and MDA-MB231 Breast Cancer Cells" from Vol 13 issue 06 received Emerging Researcher Award


Awardees of COVID-19 Research

Woman Researcher Award

A Study by Neha Garg et al. entitled "Optimization of the Response to nCOVID-19 Pandemic in Pregnant Women – An Urgent Appeal in Indian Scenario" published in Vol 12 issue 09

A Study by Sana Parveen and Shraddha Jain entitled "Pathophysiologic Enigma of COVID-19 Pandemic with Clinical Correlates" published in Vol 12 issue 13

A Study by Rashmi Jain et al. entitled "Current Consensus Review Article on Drugs and Biologics against nCOVID-19 – A Systematic Review" published in Vol 12 issue 09

Emerging Researcher Award

A Study by Madhan Jeyaraman et al. entitled "Vitamin-D: An Immune Shield Against nCOVID-19" published in Vol 12 issue 09

Study by Dheeraj Kumar Chopra et al. entitled "Lipid-Based Solid Dispersions of Azilsartan Medoxomil with Improved Oral Bioavailability: In Vitro and In Vivo Evaluation" published in Vol 12 issue 19


RSS feed

Indexed and Abstracted in


Antiplagiarism Policy: IJCRR strongly condemn and discourage practice of plagiarism. All received manuscripts have to pass through "Plagiarism Detection Software" test before forwarding for peer review. We consider "Plagiarism is a crime"

IJCRR Code of Conduct: We at IJCRR voluntarily adopt policies on Code of Conduct, and Code of Ethics given by OASPA and COPE. To know about IJCRRs Code of Conduct, Code of Ethics, Artical Retraction policy, Digital Preservation Policy, and Journals Licence policy click here

Disclaimer: International Journal of Current Research and Review (IJCRR) provides platform for researchers to publish and discuss their original research and review work. IJCRR can not be held responsible for views, opinions and written statements of researchers published in this journal.



Company name

International Journal of Current Research and Review (IJCRR) provides platform for researchers to publish and discuss their original research and review work. IJCRR can not be held responsible for views, opinions and written statements of researchers published in this journal

Contact

148, IMSR Building, Ayurvedic Layout,
        Near NIT Complex, Sakkardara,
        Nagpur-24, Maharashtra State, India

editor@ijcrr.com

editor.ijcrr@gmail.com


Copyright © 2021 IJCRR. Specialized online journals by ubijournal .Website by Ubitech solutions