A Novel Method for the Detection of Microcalcifications Based on Multi-scale Morphological Gradient Watershed Segmentation Algorithm

摘要

This paper presents an automated system for detecting masses in mammogram images. Breast cancer is one of the leading causes of women mortality in the world. Since the causes are unknown, breast cancer cannot be prevented. It is difficult for radiologists to provide both accurate and uniform evaluation over the enormous number of mammograms generated in widespread screening. Microcalcifications (calcium deposits) and masses are the earliest signs of breast carcinomas and their detection is one of the key issues for breast cancer control. Computer-aided detection of Microcalcifications and masses is an important and challenging task in breast cancer control. This paper presents a novel approach for detecting microcalcification clusters. First digitized mammogram has been taken from Mammography Image Analysis Society (MIAS) database. The Mammogram is preprocessed using Adaptive median filtered. Next, the microcalcification clusters are identified by using the marker extractions of the gradient images obtained by multiscale morphological reconstruction and avoids Over segmentation vivid in Watershed algorithm. Experimental result show that the microcalcification can be accurately and efficiently detected using the proposed approach.