Automatic Brain Tumor Segmentation from MRI using Greedy Snake Model and Fuzzy C-Means Optimization

The automatic brain tumor segmentation in MRI (Magnetic Resonance Images) is becoming a challenging task in the field of medicine, since the brain tumor occurs in different shapes, intensities and sizes. This paper proposes an efficient automatic brain tumor segmentation using Greedy Snake Model and...

Full description

Saved in:
Bibliographic Details
Main Authors: C. Jaspin Jeba Sheela, G. Suganthi
Format: Article
Language:English
Published: Springer 2022-03-01
Series:Journal of King Saud University: Computer and Information Sciences
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1319157818313120
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849315727179251712
author C. Jaspin Jeba Sheela
G. Suganthi
author_facet C. Jaspin Jeba Sheela
G. Suganthi
author_sort C. Jaspin Jeba Sheela
collection DOAJ
description The automatic brain tumor segmentation in MRI (Magnetic Resonance Images) is becoming a challenging task in the field of medicine, since the brain tumor occurs in different shapes, intensities and sizes. This paper proposes an efficient automatic brain tumor segmentation using Greedy Snake Model and Fuzzy C-Means optimization. This method initially identifies the approximate Region Of Interest (ROI), by removing the non-tumor part by two level morphological reconstruction such as dilation and erosion. A mask is formed by thresholding the reconstructed image and is eroded to improve the accuracy of segmentation in Greedy Snake algorithm. Using the mask boundary as initial contour of the snake, the greedy snake model estimates the new boundaries of tumor. These boundaries are accurate in regions where there is sharp edge and are less accurate where there are ramp edges. The inaccurate boundaries are further optimized by using Fuzzy C-Means algorithm to obtain the accurate segmentation output. The region that has large perimeter is finally chosen, to eliminate the in- accurate segmented regions. The experimental verification were done on T1-weighted contrast-enhanced image data set, using the metrics such as dice score, specificity, sensitivity and Hausdorff distance. The proposed method outperforms when compared with the traditional brain tumor segmentation methods in MRI images.
format Article
id doaj-art-60ae33cfe4884e6ab64fc26ec70e66e8
institution Kabale University
issn 1319-1578
language English
publishDate 2022-03-01
publisher Springer
record_format Article
series Journal of King Saud University: Computer and Information Sciences
spelling doaj-art-60ae33cfe4884e6ab64fc26ec70e66e82025-08-20T03:52:03ZengSpringerJournal of King Saud University: Computer and Information Sciences1319-15782022-03-0134355756610.1016/j.jksuci.2019.04.006Automatic Brain Tumor Segmentation from MRI using Greedy Snake Model and Fuzzy C-Means OptimizationC. Jaspin Jeba Sheela0G. Suganthi1Reg.No 17221282162010, St. Xaviers Autonomous College, Palayamkotai affiliated to Manonmaniam Sunadaranar University, Abishekapatti, Tirunelveli 627012, Tamil Nadu, India; Corresponding author.Department of Computer Science, W.C College, Nagercoil affiliated to Manonmaniam Sunadaranar University, Abishekapatti, Tirunelveli 627012, Tamil Nadu, IndiaThe automatic brain tumor segmentation in MRI (Magnetic Resonance Images) is becoming a challenging task in the field of medicine, since the brain tumor occurs in different shapes, intensities and sizes. This paper proposes an efficient automatic brain tumor segmentation using Greedy Snake Model and Fuzzy C-Means optimization. This method initially identifies the approximate Region Of Interest (ROI), by removing the non-tumor part by two level morphological reconstruction such as dilation and erosion. A mask is formed by thresholding the reconstructed image and is eroded to improve the accuracy of segmentation in Greedy Snake algorithm. Using the mask boundary as initial contour of the snake, the greedy snake model estimates the new boundaries of tumor. These boundaries are accurate in regions where there is sharp edge and are less accurate where there are ramp edges. The inaccurate boundaries are further optimized by using Fuzzy C-Means algorithm to obtain the accurate segmentation output. The region that has large perimeter is finally chosen, to eliminate the in- accurate segmented regions. The experimental verification were done on T1-weighted contrast-enhanced image data set, using the metrics such as dice score, specificity, sensitivity and Hausdorff distance. The proposed method outperforms when compared with the traditional brain tumor segmentation methods in MRI images.http://www.sciencedirect.com/science/article/pii/S1319157818313120MRI imagesImage segmentationFuzzy C-means algorithmGreedy snake model
spellingShingle C. Jaspin Jeba Sheela
G. Suganthi
Automatic Brain Tumor Segmentation from MRI using Greedy Snake Model and Fuzzy C-Means Optimization
Journal of King Saud University: Computer and Information Sciences
MRI images
Image segmentation
Fuzzy C-means algorithm
Greedy snake model
title Automatic Brain Tumor Segmentation from MRI using Greedy Snake Model and Fuzzy C-Means Optimization
title_full Automatic Brain Tumor Segmentation from MRI using Greedy Snake Model and Fuzzy C-Means Optimization
title_fullStr Automatic Brain Tumor Segmentation from MRI using Greedy Snake Model and Fuzzy C-Means Optimization
title_full_unstemmed Automatic Brain Tumor Segmentation from MRI using Greedy Snake Model and Fuzzy C-Means Optimization
title_short Automatic Brain Tumor Segmentation from MRI using Greedy Snake Model and Fuzzy C-Means Optimization
title_sort automatic brain tumor segmentation from mri using greedy snake model and fuzzy c means optimization
topic MRI images
Image segmentation
Fuzzy C-means algorithm
Greedy snake model
url http://www.sciencedirect.com/science/article/pii/S1319157818313120
work_keys_str_mv AT cjaspinjebasheela automaticbraintumorsegmentationfrommriusinggreedysnakemodelandfuzzycmeansoptimization
AT gsuganthi automaticbraintumorsegmentationfrommriusinggreedysnakemodelandfuzzycmeansoptimization