GRAPE: Graph-Augmented Prototype Explanations for Interactive Medical Image Diagnosis
About
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 addresses all three challenges. First, a Graph Attention Task Head models anatomical concept co-occurrence, boosting macro-F1 by +13.8,pp over the prototype baseline on TBX11K. Second, a Concept-Mismatch Safety Check - 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 erroneous annotations versus 51% for MC-Dropout with no extra inference cost. 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. On NIH ChestX-ray14, one Effusion example recovers full-supervision localization accuracy; on TBX11K, prototype maps achieve 2.6x better lesion localization than end-to-end baselines. All three capabilities add only +1~ms latency at interactive batch size. The project page is https://github.com/KurbanIntelligenceLab/GRAPE.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| 3-class tuberculosis detection | TBX11K official (test) | Macro F189.63 | 4 | |
| Multi-label Chest X-ray Classification | NIH ChestX-ray14 (test) | -- | 4 | |
| 5-class classification | NIH 5-class label subset | -- | 1 |