Automated Detection of Breast Cancer Metastases in Whole Slide Images

Cancer is considered as one of the most widely spread disease in today’s world. Many people are suffering from this disease unaware of the facts about cancer. Women are more likely to suffer from breast cancer. Cancer spread in the body when the healthy cells grow out of control and form a mass of cells resulting in tumor. This paper describes an algorithm for automated detection of breast cancer metastases in Whole Slide Images. The current procedure for detecting metastases in a breast lymph node is manual and time-consuming in which an experienced pathologist specializing in detection and characterization of tumor regions spends hours to analyze histological slides. This algorithm leverages the capability of advanced Image Processing and Machine learning to improve the detection accuracy as well as overall time needed to localize tumorous regions in Whole Slide Image.