Development of CAD System Based on Enhanced Clustering Based Segmentation Algorithm for Detection of Masses in Breast DCE-MRI

Breast cancer continues to be a significant public health problem in the world. Early detection is the key for improving breast cancer prognosis. Mammography is currently the primary method of early detection. But recent research has shown that many cases missed by mammography can be detected in Breast DCE-MRI. Magnetic Resonance (MR) imaging is emerging as the most sensitive modality that is currently available for the detection of primary or recurrent breast cancer. Breast DCE-MRI is more effective than mammography, because it generates much more data. Magnetic resonance imaging (MRI) is emerging as a powerful tool for the diagnosis of breast abnormalities. Computer Aided Detection (CAD) is of great help to this situation and image segmentation is most important process of computer Aided Detection, Magnetic Resonance Imaging data are a major challenge to any image processing software because of the huge amount of image voxels. Automatic approaches to breast cancer detection can help radiologists in this hard task and speed up the inspection process. To segment the mass of the breast region from 3D MRI set, a multistage image processing procedure was proposed. Data acquisition, processing and visualization techniques facilitate diagnosis. Image segmentation is an established necessity for an improved analysis of Magnetic Resonance (MR) images. Segmentation from MR images may aid in tumor treatment by tracking the progress of tumor growth and shrinkage. The advantages of Magnetic Resonance Imaging are that the spatial resolution is high and provides detailed images. The tumor segmentation in Breast MRI image is difficult due to the complicated galactophore structure. The work in this paper attempts to accurately segment the abnormal breast mass in DCEMRI Images. The mass is segmented using a novel clustering algorithm based on unsupervised segmentation, through neural network techniques, of an optimized space in which to perform clustering. The effectiveness of the proposed technique is determined by the extent to which potential abnormalities can be extracted from corresponding breast MRI based on its analysis, this algorithm also proposes changes that could reduce this error, and help to give good results all around. Tests performed on both real and simulated MR images shows good result.