Post-Hoc Explainability of BI-RADS Descriptors in a Multi-task Framework for Breast Cancer Detection and Segmentation

TL;DR

This paper introduces MT-BI-RADS, an explainable deep learning model for breast tumor detection that provides BI-RADS categories, tumor segmentation, and descriptor contributions to improve interpretability in breast ultrasound analysis.

Contribution

It presents a novel multi-task framework that combines tumor detection, segmentation, and post-hoc explanation of BI-RADS descriptors in breast ultrasound imaging.

Findings

Provides three levels of explanations for model decisions.

Outputs BI-RADS categories and tumor segmentation.

Quantifies descriptor contributions using Shapley Values.

Abstract

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.