Although deep learning models for abnormality classification can perform well in screening mammography, the demographic, imaging, and clinical characteristics associated with increased risk of model failure remain unclear. This retrospective study uses the Emory BrEast Imaging Dataset(EMBED) containing mammograms from 115931 patients imaged at Emory Healthcare between 2013-2020, with BI-RADS assessment, region of interest coordinates for abnormalities, imaging features, pathologic outcomes, and patient demographics. Multiple deep learning models were trained to distinguish between abnormal tissue patches and randomly selected normal tissue patches from screening mammograms. We assessed model performance by subgroups defined by age, race, pathologic outcome, tissue density, and imaging characteristics and investigated their associations with false negatives (FN) and false positives (FP). We also performed multivariate logistic regression to control for confounding between subgroups. The top-performing model, ResNet152V2, achieved accuracy of 92.6%(95%CI=92.0-93.2%), and AUC 0.975(95%CI=0.972-0.978). Before controlling for confounding, nearly all subgroups showed statistically significant differences in model performance. However, after controlling for confounding, we found lower FN risk associates with Other race(RR=0.828;p=.050), biopsy-proven benign lesions(RR=0.927;p=.011), and mass(RR=0.921;p=.010) or asymmetry(RR=0.854;p=.040); higher FN risk associates with architectural distortion (RR=1.037;p<.001). Higher FP risk associates to BI-RADS density C(RR=1.891;p<.001) and D(RR=2.486;p<.001). Our results demonstrate subgroup analysis is important in mammogram classifier performance evaluation, and controlling for confounding between subgroups elucidates the true associations between variables and model failure. These results can help guide developing future breast cancer detection models.

翻译：尽管深度学习模型在筛查性乳腺摄影中能够较好地完成异常分类任务，但与模型失败风险增加相关的人口学、影像学及临床特征仍不明确。本回顾性研究使用埃默里乳腺影像数据集（EMBED），该数据集包含2013-2020年间在埃默里医疗中心接受乳腺摄影检查的115,931名患者的影像，涵盖BI-RADS评估、异常区域坐标、影像特征、病理结果及患者人口学信息。研究人员训练了多个深度学习模型，用于区分筛查性乳腺摄影中的异常组织斑块与随机选取的正常组织斑块。我们按年龄、种族、病理结果、乳腺密度及影像特征等亚组评估模型性能，并探究其与假阴性（FN）和假阳性（FP）的关联。同时采用多变量逻辑回归控制亚组间的混杂因素。性能最优的模型ResNet152V2准确率达92.6%（95%CI=92.0-93.2%），AUC为0.975（95%CI=0.972-0.978）。在控制混杂因素前，几乎所有亚组均表现出统计学显著的模型性能差异。然而在控制混杂后，我们发现较低的FN风险与其他种族（RR=0.828；p=0.050）、活检证实的良性病变（RR=0.927；p=0.011）以及肿块（RR=0.921；p=0.010）或不对称（RR=0.854；p=0.040）相关；较高的FN风险与结构扭曲相关（RR=1.037；p<0.001）。较高的FP风险与BI-RADS密度C级（RR=1.891；p<0.001）和D级（RR=2.486；p<0.001）相关。本研究结果表明，亚组分析在乳腺摄影分类器性能评估中至关重要，而控制亚组间混杂因素可阐明变量与模型失败间的真实关联。这些结果有助于指导未来乳腺癌检测模型的开发。