Pathology-Aware Prototype Evolution via LLM-Driven Semantic Disambiguation for Multicenter Diabetic Retinopathy Diagnosis
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909928619245568 |
|---|---|
| author | Zhu, Chunzheng Lin, Yangfang Shao, Jialin Lin, Jianxin Wang, Yijun |
| author_facet | Zhu, Chunzheng Lin, Yangfang Shao, Jialin Lin, Jianxin Wang, Yijun |
| contents | Diabetic retinopathy (DR) grading plays a critical role in early clinical intervention and vision preservation. Recent explorations predominantly focus on visual lesion feature extraction through data processing and domain decoupling strategies. However, they generally overlook domain-invariant pathological patterns and underutilize the rich contextual knowledge of foundation models, relying solely on visual information, which is insufficient for distinguishing subtle pathological variations. Therefore, we propose integrating fine-grained pathological descriptions to complement prototypes with additional context, thereby resolving ambiguities in borderline cases. Specifically, we propose a Hierarchical Anchor Prototype Modulation (HAPM) framework to facilitate DR grading. First, we introduce a variance spectrum-driven anchor prototype library that preserves domain-invariant pathological patterns. We further employ a hierarchical differential prompt gating mechanism, dynamically selecting discriminative semantic prompts from both LVLM and LLM sources to address semantic confusion between adjacent DR grades. Finally, we utilize a two-stage prototype modulation strategy that progressively integrates clinical knowledge into visual prototypes through a Pathological Semantic Injector (PSI) and a Discriminative Prototype Enhancer (DPE). Extensive experiments across eight public datasets demonstrate that our approach achieves pathology-guided prototype evolution while outperforming state-of-the-art methods. The code is available at https://github.com/zhcz328/HAPM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_22033 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Pathology-Aware Prototype Evolution via LLM-Driven Semantic Disambiguation for Multicenter Diabetic Retinopathy Diagnosis Zhu, Chunzheng Lin, Yangfang Shao, Jialin Lin, Jianxin Wang, Yijun Artificial Intelligence Diabetic retinopathy (DR) grading plays a critical role in early clinical intervention and vision preservation. Recent explorations predominantly focus on visual lesion feature extraction through data processing and domain decoupling strategies. However, they generally overlook domain-invariant pathological patterns and underutilize the rich contextual knowledge of foundation models, relying solely on visual information, which is insufficient for distinguishing subtle pathological variations. Therefore, we propose integrating fine-grained pathological descriptions to complement prototypes with additional context, thereby resolving ambiguities in borderline cases. Specifically, we propose a Hierarchical Anchor Prototype Modulation (HAPM) framework to facilitate DR grading. First, we introduce a variance spectrum-driven anchor prototype library that preserves domain-invariant pathological patterns. We further employ a hierarchical differential prompt gating mechanism, dynamically selecting discriminative semantic prompts from both LVLM and LLM sources to address semantic confusion between adjacent DR grades. Finally, we utilize a two-stage prototype modulation strategy that progressively integrates clinical knowledge into visual prototypes through a Pathological Semantic Injector (PSI) and a Discriminative Prototype Enhancer (DPE). Extensive experiments across eight public datasets demonstrate that our approach achieves pathology-guided prototype evolution while outperforming state-of-the-art methods. The code is available at https://github.com/zhcz328/HAPM. |
| title | Pathology-Aware Prototype Evolution via LLM-Driven Semantic Disambiguation for Multicenter Diabetic Retinopathy Diagnosis |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2511.22033 |