MedSynapse-V：通过潜在记忆演化桥接视觉感知与临床直觉
MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution
AI总结：
提出MedSynapse-V框架，通过潜在诊断记忆演化模拟临床专家经验调用，解决医学视觉语言模型因离散分词导致的量化损失、长程信息消散和案例适应性问题，在诊断准确性上显著超越现有方法。
摘要：
高精度医学诊断不仅依赖于静态成像特征，还依赖于专家在图像解读过程中即时调用的隐式诊断记忆。我们指出了医学视觉语言模型中由于离散分词导致的基本认知错位，表现为量化损失、长程信息消散以及缺乏案例自适应专业知识。为弥合这一差距，我们提出了MedSynapse-V，一个用于潜在诊断记忆演化的框架，通过在模型隐藏流中动态合成隐式诊断记忆来模拟临床医生的经验调用。具体而言，它从元查询先验记忆机制开始，其中可学习的探针从解剖先验编码器中检索结构化先验，以生成压缩的隐式记忆。为确保临床保真度，我们引入了因果反事实细化（CCR），利用强化学习和基于区域级特征掩蔽的反事实奖励来量化每个记忆的因果贡献，从而修剪冗余并将潜在表示与诊断逻辑对齐。这一演化过程最终达到内在记忆转换（IMT），一种特权-自主双分支范式，通过全词汇散度对齐将教师分支的诊断模式内化到学生分支中。跨多个数据集的全面实证评估表明，通过将外部专业知识转化为内源参数，我们的方法在诊断准确性上显著优于现有最先进方法，特别是思维链范式。代码可在https://github.com/zhcz328/MedSynapse-V获取。
英文摘要：
High-precision medical diagnosis relies not only on static imaging features but also on the implicit diagnostic memory experts instantly invoke during image interpretation. We pinpoint a fundamental cognitive misalignment in medical VLMs caused by discrete tokenization, leading to quantization loss, long-range information dissipation, and missing case-adaptive expertise. To bridge this gap, we propose ours, a framework for latent diagnostic memory evolution that simulates the experiential invocation of clinicians by dynamically synthesizing implicit diagnostic memories within the model's hidden stream. Specifically, it begins with a Meta Query for Prior Memorization mechanism, where learnable probes retrieve structured priors from an anatomical prior encoder to generate condensed implicit memories. To ensure clinical fidelity, we introduce Causal Counterfactual Refinement (CCR), which leverages reinforcement learning and counterfactual rewards derived from region-level feature masking to quantify the causal contribution of each memory, thereby pruning redundancies and aligning latent representations with diagnostic logic. This evolutionary process culminates in Intrinsic Memory Transition (IMT), a privileged-autonomous dual-branch paradigm that internalizes teacher-branch diagnostic patterns into the student-branch via full-vocabulary divergence alignment. Comprehensive empirical evaluations across multiple datasets demonstrate that ours, by transferring external expertise into endogenous parameters, significantly outperforms existing state-of-the-art methods, particularly chain-of-thought paradigms, in diagnostic accuracy. The code is available at https://github.com/zhcz328/MedSynapse-V.
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。
