Computer-aided diagnosis of breast cancer

We will review two current projects pertaining to artificial neural network (ANN) computer models that merge radiologist-extracted findings to perform computer-aided diagnosis (CAD) of breast cancer. The goal of both projects is to obviate the diagnostic excisional biopsy, a costly and invasive surgical procedure, for certain groups of cases. These projects are (1) mammography-based model to predict both malignancy and invasion of all breast lesions, and (2) ultrasound-based model to predict malignancy of breast masses. By providing information which was previously available only through biopsy, these CAD models may help to reduce the number of unnecessary surgical procedures and their associated costs.