BI-RADS-Net: An Explainable Multitask Learning Approach for Cancer Diagnosis in Breast Ultrasound Images
This addresses the need for trustworthy AI in healthcare by offering explainable cancer diagnosis for clinicians, though it is incremental as it builds on existing multitask learning and explainability methods.
The paper tackles the problem of cancer detection in breast ultrasound images by introducing BI-RADS-Net, an explainable deep learning approach that provides predictions and explanations using clinical features like BI-RADS descriptors, achieving improved model accuracy on a dataset of 1,192 images.
In healthcare, it is essential to explain the decision-making process of machine learning models to establish the trustworthiness of clinicians. This paper introduces BI-RADS-Net, a novel explainable deep learning approach for cancer detection in breast ultrasound images. The proposed approach incorporates tasks for explaining and classifying breast tumors, by learning feature representations relevant to clinical diagnosis. Explanations of the predictions (benign or malignant) are provided in terms of morphological features that are used by clinicians for diagnosis and reporting in medical practice. The employed features include the BI-RADS descriptors of shape, orientation, margin, echo pattern, and posterior features. Additionally, our approach predicts the likelihood of malignancy of the findings, which relates to the BI-RADS assessment category reported by clinicians. Experimental validation on a dataset consisting of 1,192 images indicates improved model accuracy, supported by explanations in clinical terms using the BI-RADS lexicon.