Provenance-Enabled Multi-View Diabetic Retinopathy Diagnosis Through Interpretable Process Mining

ICLR 2026 Conference Submission13076 Authors

Keywords: Multi-view, Multi-modal, Diabetic Retinopathy diagnosis

Abstract: Diabetic retinopathy (DR) is a leading cause of blindness among individuals with diabetes. Although the existing deep learning models have demonstrated potential in DR diagnosis, they still lack full-process interpretability. Specifically, these models suffer from three key challenges: reliance on single-source inputs, opaque and untraceable reasoning processes, and the absence of a mechanism for result verification. To meet the requirements of the medical scenario for a trustworthy diagnostic model, we propose a provenance-enabled concept-based framework for multi-view DR diagnostic (ProConMV). This work integrates DR lesion masks, clinical text and multi-view data, utilizing multimodal prompt analysis and visual-text concept interaction to learn the interpretable multi-source input. During the reasoning stage, the proposed framework introduces lesion concepts for causal reasoning chains combining clinical guidelines, and adds doctor intervention for human-machine collaboration. For dynamic fusion decision and verification in multi-view DR diagnosis, we derive via generalization theory that incorporating each view’s lesion concept uncertainty and grading uncertainty reduces the generalization error upper bound. Accordingly, we design a dual uncertainty-aware module to enable provenance-based verification, ultimately enabling verifiable analysis of DR diagnostic results. Extensive experiments conducted on two public multi-view DR datasets demonstrate the effectiveness of our method.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 13076