Evaluation of mammography calcification detection system based on deep learning

Abstract

Objective To evaluate the performance of a deep learning (DL) based mammogram calcification detection system. Methods Screening digital mammographic examinations with standard cranio-caudal (CC) and medio-lateral oblique (MLO) views were performed in 1 431 women (5 488 mammogram images) who were enrolled between January and December in 2013. The DL system and a radiologist detect calcifications separately, and then both results are reviewed by a moreexperiencedradiologist. Sensitivities of the DL model and radiologist were compared. Different calcification morphology, distribution, BI-RADS categories, breast density and patient age were investigated by χ2 tests. Results For DL system, sensitivity of all kinds of calcifications were 96.76% (7 649/7 905). The average false positive was 1.04 per image (5 706/5 488), 3.99 per case (5 706/1 431). The false positive rate was 42.73% (5 706/13 355). There was no significant differences for DL system with different calcification distribution, BI-RADS categories, breast densities and patient ages (P>0.05). Conclusion Deep learning based mammogram calcification detection system shows high sensitivity and stability, which may help to reduce the missing rate of calcification (especially the suspicious ones). Key words: Mammography; Suspicious calcification; Detection; Deep learning