Retina-RAG联合诊断眼底病并生成结构化报告，用低成本实现高精度。
Retina-RAG: Retrieval-Augmented Vision-Language Modeling for Joint Retinal Diagnosis and Clinical Report Generation
- 分模块设计：用高精度分类器+参数高效视觉语言模型，灵活集成。
- 诊断准确率高：糖尿病视网膜病变F1达0.731，黄斑水肿检测达0.948。
- 适合临床落地：单张消费级显卡运行，报告生成质量优于现有方法。
糖尿病视网膜病变（DR）是全球工作年龄人群可预防性失明的主要原因，但现有自动化筛查系统多仅限于图像级分类，缺乏结构化临床报告。本文提出Retina-RAG，一种低成本模块化框架，可联合完成DR分期分级、黄斑水肿（ME）检测与临床报告生成。该架构将高性能眼底图像分类器与经低秩适配（LoRA）微调的视觉语言模型（Qwen2.5-VL-7B-Instruct）解耦，支持灵活组件集成。推理时引入检索增强生成（RAG）模块，注入专业眼科知识及结构化分类输出，提升诊断一致性并减少幻觉。在带有字幕的眼底疾病数据集上，Retina-RAG的DR分级F1-score达0.731，ME检测达0.948，显著优于零样本Qwen（0.096, 0.732）和MMed-RAG（0.541, 0.641）。报告生成方面，ROUGE-L为0.438，SBERT相似度达0.884，全面超越基线。整个系统可在单张消费级GPU上运行，证明临床级眼底AI可用有限算力实现。
原文摘要 · Abstract (English)
Diabetic Retinopathy (DR) is a leading cause of preventable blindness among working-age adults worldwide, yet most automated screening systems are limited to image-level classification and lack clinically structured reporting. We propose Retina-RAG, a low-cost modular framework that jointly performs DR severity grading, macular edema (ME) detection, and report generation. The architecture decouples a high-performance retinal classifier and a parameter-efficient vision-language model (Qwen2.5-VL-7B-Instruct) adapted via Low-Rank Adaptation (LoRA), enabling flexible component integration. A retrieval-augmented generation (RAG) module injects curated ophthalmic knowledge together with structured classifier outputs at inference time to improve diagnostic consistency and reduce hallucinations. Retina-RAG achieves an F1-score of 0.731 for DR grading and 0.948 for ME detection, substantially outperforming zero-shot Qwen (0.096, 0.732) and MMed-RAG (0.541, 0.641) on a retinal disease detection dataset with captions. For report generation, Retina-RAG attains ROUGE-L 0.438 and SBERT similarity 0.884, exceeding all baselines. The full framework operates on a single consumer-grade GPU, demonstrating that clinically structured retinal AI can be achieved with modest computational resources.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。