Performance Gaps of Artificial Intelligence Models Screening Mammography -- Towards Fair and Interpretable Models

Even though deep learning models for abnormality classification can perform well in screening mammography, the demographic and imaging characteristics associated with increased risk of failure for abnormality classification in screening mammograms remain unclear. This retrospective study used data from the Emory BrEast Imaging Dataset (EMBED) including mammograms from 115,931 patients imaged at Emory University Healthcare between 2013 to 2020. Clinical and imaging data includes Breast Imaging Reporting and Data System (BI-RADS) assessment, region of interest coordinates for abnormalities, imaging features, pathologic outcomes, and patient demographics. Deep learning models including InceptionV3, VGG16, ResNet50V2, and ResNet152V2 were developed to distinguish between patches of abnormal tissue and randomly selected patches of normal tissue from the screening mammograms. The distributions of the training, validation and test sets are 29,144 (55.6%) patches of 10,678 (54.2%) patients, 9,910 (18.9%) patches of 3,609 (18.3%) patients, and 13,390 (25.5%) patches of 5,404 (27.5%) patients. We assessed model performance overall and within subgroups defined by age, race, pathologic outcome, and imaging characteristics to evaluate reasons for misclassifications. On the test set, a ResNet152V2 model trained to classify normal versus abnormal tissue patches achieved an accuracy of 92.6% (95%CI=92.0-93.2%), and area under the receiver operative characteristics curve 0.975 (95%CI=0.972-0.978). Imaging characteristics associated with higher misclassifications of images include higher tissue densities (risk ratio [RR]=1.649; p=.010, BI-RADS density C and RR=2.026; p=.003, BI-RADS density D), and presence of architectural distortion (RR=1.026; p<.001). Small but statistically significant differences in performance were observed by age, race, pathologic outcome, and other imaging features (p<.001).
View on arXiv