Recognition of architectural distortion in mammographic images with transfer learning

Computer-aided diagnosis (CAD) technology can improve the detection of abnormal. Such as calcifications, masses, and architectural distortion. Among the three abnormals, architectural distortion is the most difficult one to detect for both radiologists and CAD systems. In this article, we use automatic architectural distortion detection method to locate initial suspicious areas. Then, combine the transfer learning to detect architectural distortion, the reason we use transfer learning is the number of samples of architectural distortion in mini-MIAS database and Digital Database for Screening Mammography (DDSM) is small, and the number of malignant mass is much larger. The malignant mass and the architectural distortion are similar. Our objective is by transferring malignant mass information to improve the recognition rate of AD in the case of only a small amount of AD training samples.