Detection of breast tumor candidates using marker-controlled watershed segmentation and morphological analysis

Abstract

Computer Aided Diagnosis (CAD) was approved to automate breast cancer detection with mammograms in 1998. But due to the great variability in tumor sizes and shapes, and underlying breast tissue structures, pattern recognition algorithms have a difficult time adapting to different situations. In this paper, a marker-controlled watershed segmentation algorithm was developed to locate breast mass tumor candidates. The approach first selected foreground and background markers, and then applied watershed segmentation algorithm to isolate a tumor region from its surrounding tissue. Since watershed segmentation is based on pixel density variation that is present in all mass tumors, the proposed approach was fairly successful in locating tumors under all conditions. Experiment results with Mammographic Image Analysis Society (MIAS) data set showed the overall detection rate for mass tumors is 90%.