[Submitted on 29 Jun 2026 (v1), last revised 7 Nov 2026 (this version, v3)]
Abstract:Prototype-based medical image classifiers present three clinical limitations: they treat findings as independent, silently amplify unsafe physician feedback, and require full retraining whenever a new finding is needed. We present GRAPE (Graph-Augmented Prototype Explanations), a unified architecture that targets all three challenges. First, a Graph Attention Task Head boosts macro-F1 by +13.8,pp over the prototype baseline on TBX11K but not on NIH ChestX-ray14, with no graph-specific benefit established. Second, a Concept-Mismatch Safety Check, to our knowledge the first such mechanism in prototype-based medical classifiers, warns when the model’s dominant finding inside a doctor-drawn region conflicts with the claimed label, catching 85% of simulated erroneous annotations with no extra inference cost at a favorable operating point, though sensitivity falls substantially at clinically realistic false-positive budgets. Third, Open-Vocabulary Prototype Anchoring aligns visual prototypes to clinical text, allowing a new finding to be added from a single labeled image without modifying any other component, evaluated for localization only. On NIH ChestX-ray14, one Effusion example matched that concept’s low fully-supervised Pointing Game ceiling in one run but not in a second. On TBX11K, prototype maps achieve 2.1x better lesion localization than end-to-end concept-based baselines. The graph head adds only +1~ms latency at interactive batch size. The project page is available at this https URL.
Submission history
From: Rasul Khanbayov [view email]
[v1] Mon, 29 Jun 2026 20:45:26 UTC (2,734 KB)
[v2] Wed, 1 Jul 2026 14:28:42 UTC (2,734 KB)
[v3] Sat, 7 Nov 2026 00:14:25 UTC (6,295 KB)
