Components of Computeraided Diagnosis for Breast Ultrasound

Although breast cancer has very high incidence and death rate, the cause of breast cancer is still unknown and there does not exist effective way to prevent the occurrence of breast cancer. Because early detection is a key role in breast cancer diagnosis and treatment, many imaging modalities are continually being developed to screen and diagnose the breast cancer at early stage. Especially, ultrasound (US) is one of useful diagnostic tools to distinguish benign from malignant masses of the breast, however, the ultrasound image has some limitations, such as low resolution and low contrast, speckle noise, and blurry edges between various organs. Recent progress of computer-aided diagnosis (CAD) system demonstrated that the application of CAD system could increase the diagnostic confidence for a physician and provides one possible solution to improve the positive predictive value of breast biopsy. The purposes of the paper are to review (1) the advantages and disadvantages of the most widely used breast imaging modalities and (2) each of CAD steps including preprocessing, segmentation, feature extraction and selection, classification and, evaluation. The last objective is (3) to discuss false positive reduction, whole breast ultrasound, elastography, and multi-modality CAD to further improve the performance of CAD.