{"ID":5439509,"CreatedAt":"2026-07-01T01:17:58.482524686Z","UpdatedAt":"2026-07-02T20:43:09.5019258Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.30901","arxiv_id":"2606.30901","title":"GRAPE: Graph-Augmented Prototype Explanations for Interactive Medical Image Diagnosis","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 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.","short_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 addresses all...","url_abs":"https://arxiv.org/abs/2606.30901","url_pdf":"https://arxiv.org/pdf/2606.30901v1","authors":"[\"Rasul Khanbayov\",\"Hasan Kurban\"]","published":"2026-06-29T20:45:26Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":613797,"CreatedAt":"2026-07-01T01:17:58.482524686Z","UpdatedAt":"2026-07-01T01:17:58.482524686Z","DeletedAt":null,"paper_id":5439509,"paper_url":"https://arxiv.org/abs/2606.30901","paper_title":"GRAPE: Graph-Augmented Prototype Explanations for Interactive Medical Image Diagnosis","repo_url":"https://github.com/KurbanIntelligenceLab/GRAPE","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}