Paper Info
Title
Mammogram segmentation using maximal cell strength updation in cellular automata.
Abstract
Breast cancer is the most frequently diagnosed type of cancer among women. Mammogram is one of the most effective tools for early detection of the breast cancer. Various computer-aided systems have been introduced to detect the breast cancer from mammogram images. In a computer-aided diagnosis system, detection and segmentation of breast masses from the background tissues is an important issue. In this paper, an automatic segmentation method is proposed to identify and segment the suspicious mass regions of mammogram using a modified transition rule named maximal cell strength updation in cellular automata (CA). In coarse-level segmentation, the proposed method performs an adaptive global thresholding based on the histogram peak analysis to obtain the rough region of interest. An automatic seed point selection is proposed using gray-level co-occurrence matrix-based sum average feature in the coarse segmented image. Finally, the method utilizes CA with the identified initial seed point and the modified transition rule to segment the mass region. The proposed approach is evaluated over the dataset of 70 mammograms with mass from mini-MIAS database. Experimental results show that the proposed approach yields promising results to segment the mass region in the mammograms with the sensitivity of 92.25 % and accuracy of 93.48 %.
Year
DOI
Venue
2015
10.1007/s11517-015-1280-0
Medical & Biological Engineering & Computing
Keywords
Field
DocType
Cellular automata, Mammogram segmentation, Histogram peak analysis, GLCM, Seed selection
Cellular automaton,Computer vision,Histogram,Breast cancer,Pattern recognition,Segmentation,Region growing,Artificial intelligence,Thresholding,Selection rule,Region of interest,Mathematics
Journal
Volume
Issue
ISSN
53
8
1741-0444
Citations 
PageRank 
References 
9
0.54
230
Authors
2
Search Limit
100230
Name
Order
Citations
PageRank
J Anitha1181.42
J Dinesh Peter290.88