Detecting Cardiovascular Disease from Mammograms With Deep Learning

TLDR

Coronary artery disease is a leading cause of death in women, and breast arterial calcifications seen on mammograms serve as useful risk markers for the disease. This study examines whether an automated, accurate detection of BACs in mammograms can be used for coronary artery disease risk assessment. We trained a 12‑layer convolutional neural network to classify BAC versus non‑BAC, applied a pixel‑wise patch‑based detection, and validated the system with a reader study and performance evaluation on 840 mammograms from 210 cases using FROC and calcium‑mass analysis. The deep‑learning system achieved expert‑level detection in FROC analysis and a 96.24% coefficient of determination in calcium‑mass quantification, indicating its effectiveness for automated BAC detection and cardiovascular risk identification.

Abstract

Coronary artery disease is a major cause of death in women. Breast arterial calcifications (BACs), detected inmammograms, can be useful riskmarkers associated with the disease. We investigate the feasibility of automated and accurate detection ofBACsinmammograms for risk assessment of coronary artery disease. We develop a 12-layer convolutional neural network to discriminate BAC from non-BAC and apply a pixelwise, patch-based procedure for BAC detection. To assess the performance of the system, we conduct a reader study to provide ground-truth information using the consensus of human expert radiologists. We evaluate the performance using a set of 840 full-field digital mammograms from 210 cases, using both free-responsereceiveroperatingcharacteristic (FROC) analysis and calcium mass quantification analysis. The FROC analysis shows that the deep learning approach achieves a level of detection similar to the human experts. The calcium mass quantification analysis shows that the inferred calcium mass is close to the ground truth, with a linear regression between them yielding a coefficient of determination of 96.24%. Taken together, these results suggest that deep learning can be used effectively to develop an automated system for BAC detection inmammograms to help identify and assess patients with cardiovascular risks.