Computer-Aided Detection and Differentiation of Breast Cancer on Mammograms

Mammography is the most sensitive method available for early detection of breast cancer. However, approximately 10–30 % of breast cancer incidents are not detected using mammograms because of the size and location of a lesion, density of the breast tissue, and interpretation ability of radiologists. It is also difficult for radiologists to determine whether a detected lesion is malignant or benign. The positive predictive value of mammography is typically between 15 and 30 %, which is rather low. To overcome these problems, many investigators have developed computer-aided diagnosis (CAD) schemes for identifying regions of potential lesions in mammograms and for evaluating the malignancy of a detected lesion. CAD is defined as a diagnosis performed by a radiologist who considers the computer output as a second opinion. The purpose of CAD is to improve the diagnostic accuracy and consistency of image interpretation by radiologists. In this chapter, we provide a brief summary of some works, development examples, and potential usefulness of CAD in clinical practice.