Evidential Reasoning Advances Interpretable Real-World Disease Screening

Disease screening is critical for early detection and timely intervention in clinical practice. However, current screening models for medical images often suffer from limited interpretability and suboptimal performance, as they lack mechanisms to reference historical cases or provide transparent reasoning pathways. To address these challenges, we introduce EviScreen, an evidential reasoning framework for disease screening that leverages region-level evidence retrieved from knowledge banks of historical cases. The proposed EviScreen offers retrospection interpretability through regional evidence retrieved from dual knowledge banks. Based on the evidential mechanism, the subsequent evidence-aware reasoning module makes predictions using both the current case and evidence from historical cases, thereby enhancing disease screening performance. In addition, unlike conventional methods that rely on post-hoc saliency maps, EviScreen enables advanced localization interpretability through abnormality maps generated via contrastive retrieval. Our method achieves superior performance on our carefully established benchmarks for real-world disease screening, yielding notably higher specificity at clinical-level recall, which reduces both unnecessary follow-up examinations and the associated psychological burden on patients. Code will be publicly available and is currently provided in supplementary material.