用于乳腺癌检测与分割的多任务框架中BI-RADS描述符的事后可解释性
Post-Hoc Explainability of BI-RADS Descriptors in a Multi-task Framework for Breast Cancer Detection and Segmentation
- University of Idaho（爱达荷大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对乳腺CAD系统可解释性不足的问题，提出MT-BI-RADS多任务可解释深度学习方法，通过输出BI-RADS分类、同步肿瘤分割、基于Shapley Values的描述符量化贡献三层解释，提升乳腺超声肿瘤良恶性预测的可信度。
AI中文摘要：
尽管医学领域近年取得进展，乳腺癌仍是女性群体中最常见、致死率最高的疾病之一。虽然基于机器学习的计算机辅助诊断（CAD）系统已展现出协助放射科医生分析医学影像的潜力，但性能最优的CAD系统的黑箱特性引发了人们对其可信度与可解释性的担忧。本文提出MT-BI-RADS，一种用于乳腺超声（BUS）图像肿瘤检测的新型可解释深度学习方法。该方法提供三层解释，帮助放射科医生理解肿瘤恶性程度预测的决策过程：第一，模型输出放射科医生用于BUS图像分析的BI-RADS分类；第二，模型采用多任务学习，同时分割图像中对应肿瘤的区域；第三，该方法通过基于Shapley Values的事后解释，输出每个BI-RADS描述符对良性或恶性类别预测的量化贡献。
英文摘要：
Despite recent medical advancements, breast cancer remains one of the most prevalent and deadly diseases among women. Although machine learning-based Computer-Aided Diagnosis (CAD) systems have shown potential to assist radiologists in analyzing medical images, the opaque nature of the best-performing CAD systems has raised concerns about their trustworthiness and interpretability. This paper proposes MT-BI-RADS, a novel explainable deep learning approach for tumor detection in Breast Ultrasound (BUS) images. The approach offers three levels of explanations to enable radiologists to comprehend the decision-making process in predicting tumor malignancy. Firstly, the proposed model outputs the BI-RADS categories used for BUS image analysis by radiologists. Secondly, the model employs multi-task learning to concurrently segment regions in images that correspond to tumors. Thirdly, the proposed approach outputs quantified contributions of each BI-RADS descriptor toward predicting the benign or malignant class using post-hoc explanations with Shapley Values.
