PersonalizedUS: Interpretable Breast Cancer Risk Assessment with Local Coverage Uncertainty Quantification
This work addresses the clinical challenge of reducing unnecessary biopsies and mental health burden for breast cancer patients and clinicians, though it is incremental as it builds on existing conformal prediction methods.
The paper tackles the problem of inaccurate breast cancer risk assessment from ultrasound exams, which leads to unnecessary biopsies, by introducing PersonalizedUS, an interpretable ML system that provides personalized risk estimates with local coverage guarantees and achieves sensitivity, specificity, and predictive values above 0.9, reducing biopsies by up to 65% for certain lesion types with minimal missed cancers.
Correctly assessing the malignancy of breast lesions identified during ultrasound examinations is crucial for effective clinical decision-making. However, the current "golden standard" relies on manual BI-RADS scoring by clinicians, often leading to unnecessary biopsies and a significant mental health burden on patients and their families. In this paper, we introduce PersonalizedUS, an interpretable machine learning system that leverages recent advances in conformal prediction to provide precise and personalized risk estimates with local coverage guarantees and sensitivity, specificity, and predictive values above 0.9 across various threshold levels. In particular, we identify meaningful lesion subgroups where distribution-free, model-agnostic conditional coverage holds, with approximately 90% of our prediction sets containing only the ground truth in most lesion subgroups, thus explicitly characterizing for which patients the model is most suitably applied. Moreover, we make available a curated tabular dataset of 1936 biopsied breast lesions from a recent observational multicenter study and benchmark the performance of several state-of-the-art learning algorithms. We also report a successful case study of the deployed system in the same multicenter context. Concrete clinical benefits include up to a 65% reduction in requested biopsies among BI-RADS 4a and 4b lesions, with minimal to no missed cancer cases.