Segmentation of Mammographic Masses Using Gray Level Thresholding
K. Divyadarshini, R. Vanithamani · International journal of tomography and simulation · 2015
Computer aided detection (CAD) intends to provide assistance to the mammography detection, reducing breast cancer misdiagnosis, thus allowing better diagnosis and more efficient treatments. The segmentation of mass tissue from normal breast tissue plays a crucial role in the development of a robust automated classification system because the classification accuracy will depend on the information gathered from the tumor area. In this work, the mammographic images are pre-processed using techniques like filtering and contrast enhancement before performing segmentation. Median filter is used for noise removal and Contrast Limited Adaptive Histogram Equalization (CLAHE) is used for enhancement process. Finally, the segmentation of mass from the mammogram is performed using gray level thresholding technique. The images were collected from Mammographic Image Analysis Society (MIAS) Database and Digital Database for Screening Mammography (DDSM). The experiments were implemented in MATLAB.