Interpretable deep learning models for better clinician-AI communication in clinical mammography
Interpretable deep learning models for better clinician-AI communication in clinical mammography
复制标题
可解释的深度学习模型，可在临床乳房 X 光检查中实现更好的临床医生与 AI 沟通
DOI：
10.1117/12.2612372
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Rudin, Cynthia
中科院分区：
文献类型：
--
作者：
Barnett, Alina J.;Sharma, Vaibhav;Gajjar, Neel;Fang, Jerry D.;Schwartz, Fides;Chen, Chaofan;Lo, Joseph Y.;Rudin, Cynthia
人们越来越有兴趣使用深度学习和计算机视觉来帮助指导临床决策，例如是否根据乳房X光检查进行活检。现有的网络通常是黑箱，无法解释它们是如何做出预测的。我们提出了一个可解释的深度学习网络，它解释了它在BI-RADS特征质量形状和质量边缘方面的预测。我们的模型预测肿块边缘和肿块形状，然后使用来自这些可解释模型的logits来预测恶性肿瘤，也使用可解释模型。可解释的质量裕度模型使用原型零件模型解释其预测。可解释的质量形状模型预测分割，拟合椭圆，然后基于拟合的椭圆的拟合优度和偏心率确定形状。虽然在恶性肿瘤预测模型中包括质量形状logits并没有提高性能，但我们将这种技术作为更好的临床医生-AI沟通框架的一部分。
There is increasing interest in using deep learning and computer vision to help guide clinical decisions, such as whether to order a biopsy based on a mammogram. Existing networks are typically black box, unable to explain how they make their predictions. We present an interpretable deep-learning network which explains its predictions in terms of BI-RADS features mass shape and mass margin. Our model predicts mass margin and mass shape, then uses the logits from those interpretable models to predict malignancy, also using an interpretable model. The interpretable mass margin model explains its predictions using a prototypical parts model. The interpretable mass shape model predicts segmentations, fits an ellipse, then determines shape based on the goodness of fit and eccentricity of the fitted ellipse. While including mass shape logits in the malignancy prediction model did not improve performance, we present this technique as part of a framework for better clinician-AI communication.