Mammogram Inspection by Computer

Abstract
We have considered the problem of computerized picture processing of mammographic images for the early detection of breast cancer by determination of the very significant microcalcifications. Brightness measures, gray-level statistics, and a compactness measure are applied in a decision tree to characterize the candidate objects. A verification technique was evaluated to differentiate between significant groups of microcalcifications and isolated objects as well as false alarms. Feasibility of the microcalcification detection algorithm was demonstrated in experiments using 132 mammogram subareas, each consisting of 512 ×512 picture elements.