An Adaptive Weighted Error Sensitive Fuzzy Clustering Technique for Mammogram Image Segmentation
Keywords:
Error Sensitivity Modelling, Image Segmentation, FCM Clustering, Mammogram, Image Analysis, Unsupervised ClusteringAbstract
Mammogram image segmentation plays a crucial role in detecting the lesion region in the breast masses. In this context, the key challenging issue is the false positive detection of pectoral muscles or fatty tissues as the lesion region. Further, the presence of noise and imaging errors degrade the segmentation accuracy. To address these problems, we suggest an Adaptive Weighted Error Sensitive Fuzzy Clustering (AWESFC) technique for delineating the different tissue regions in the mammogram images. The basic idea is to incorporate an error sensitive regulating factor in the objective function of the Fuzzy C-means (FCM) algorithm for enhancing the clustering performance in the noisy environment. The suggested technique is experimented with multiple volumes of mammogram images from standard databases. State-of-the-art methods are compared. Quantitative assessment is done using standard evaluation indices. The results indicate better quality with the proposed method.
Downloads
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 International Journal of Computer Information Systems and Industrial Management Applications
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.