深度专家注入用于带有领域特定知识的视网膜视觉语言模型的锚定
Deep Expert Injection for Anchoring Retinal VLMs with Domain-Specific Knowledge
AI总结：
本文提出EyExIn框架，通过深度专家注入机制提升视网膜VLMs的领域知识嵌入能力，解决感知与推理间隙问题，实现高精度眼科视觉问答。
摘要：
大型视觉语言模型（LVLMs）在自动化眼科诊断中展现出巨大潜力。然而，其临床应用严重受限于缺乏领域特定知识。本文识别出两个阻碍可靠医疗推理的结构性缺陷：1）感知间隙，即通用视觉编码器无法解析细粒度病理线索（如微动脉瘤）；2）推理间隙，即稀疏视觉证据在深层Transformer层中被大量语言先验逐步覆盖，导致无根据的幻觉。为弥合这些间隙，我们提出EyExIn，一种数据高效的框架，通过深度专家注入机制将专家知识锚定到视网膜VLMs中。我们的架构采用专家意识双流编码策略，将视觉表示分为一般流用于解剖学上下文和专门的专家流用于病理语义。为确保高保真集成，我们设计了语义自适应门控融合模块，动态放大细微病变信号并过滤无关背景噪声。此外，我们引入自适应深度专家注入，通过将融合的视觉特征作为残差偏置直接整合到中间LLM层中，嵌入持久的'视觉锚点'。该机制创建了视觉捷径，迫使推理堆栈严格基于视觉证据。在四个基准上的广泛实验表明，我们的模型在大规模专有系统中始终表现更优。EyExIn显著增强了领域特定知识嵌入，并在眼科视觉问答中实现了最先进的精度，推动了可信眼科AI的发展。
英文摘要：
Large Vision Language Models (LVLMs) show immense potential for automated ophthalmic diagnosis. However, their clinical deployment is severely hindered by lacking domain-specific knowledge. In this work, we identify two structural deficiencies hindering reliable medical reasoning: 1) the Perception Gap, where general-purpose visual encoders fail to resolve fine-grained pathological cues (e.g., microaneurysms); and 2) the Reasoning Gap, where sparse visual evidence is progressively overridden by massive language priors in deeper transformer layers, leading to ungrounded hallucinations. To bridge these gaps, we propose EyExIn, a data-efficient framework designed to anchor retinal VLMs with expert knowledge via a Deep Expert Injection mechanism. Our architecture employs an Expert-Aware Dual-Stream encoding strategy that decouples visual representation into a general stream for anatomical context and a specialized expert stream for pathological semantics. To ensure high-fidelity integration, we design a Semantic-Adaptive Gated Fusion module, which dynamically amplifies subtle lesion signals while filtering irrelevant background noise. Furthermore, we introduce Adaptive Deep Expert Injection to embed persistent "Vision Anchors" by integrating fused visual features as residual biases directly into intermediate LLM layers. This mechanism creates a visual shortcut that forces the reasoning stack to remain strictly grounded in visual evidence. Extensive experiments across four benchmarks demonstrate that our model consistently outperforms massive proprietary systems. EyExIn significantly enhances domain-specific knowledge embedding and achieves state-of-the-art precision in ophthalmic visual question answering, advancing the development of trustworthy ophthalmic AI.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
