Medic-AD：迈向医学视觉语言模型的临床智能
Medic-AD: Towards Medical Vision-Language Model's Clinical Intelligence
可学习异常感知 token 与跨图像差异 token 的设计，可迁移到任何需要纵向对比（随访、变化检测）的视觉-语言模型中，把时序变化显式编码进 token 而非依赖后处理；其可解释性阶段用热力图对齐模型推理，也为医学 VLM 的可信输出提供了可复用的训练范式。
原文依据 inter-image difference tokens (Diff) explicitly encode temporal changes between studies
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论病灶检测、症状追踪与视觉可解释性是真实世界医学图像分析的核心，然而当前的医学视觉语言模型（VLM）仍缺乏将其广博知识转化为临床可执行输出的机制。为弥合这一差距，我们提出 Medic-AD，一个面向临床的 VLM，通过分阶段框架强化上述三项能力。首先，可学习的异常感知 token（Ano）促使模型关注异常区域，并构建更具判别性的以病灶为中心的表征。其次，跨图像差异 token（Diff）显式编码不同检查之间的时序变化，使模型能够区分疾病负荷的恶化、改善与稳定。最后，一个专门的可解释性阶段训练模型生成热力图，突出与病灶相关的区域，提供与模型推理一致的清晰视觉证据。通过这种分阶段设计，Medic-AD 在异常检测、症状追踪与异常分割上稳步提升性能，与闭源基线及医学专用基线相比均取得最优结果。在从真实医院工作流中采集的真实纵向临床数据上的评估进一步表明，Medic-AD 在实际的患者监测与决策支持工作流中能够给出稳定的预测与临床可信的解释。
英文原文摘要 1417 字符
Lesion detection, symptom tracking, and visual explainability are central to real-world medical image analysis, yet current medical Vision-Language Models (VLMs) still lack mechanisms that translate their broad knowledge into clinically actionable outputs. To bridge this gap, we present Medic-AD, a clinically oriented VLM that strengthens these three capabilities through a stage-wise framework. First, learnable anomaly-aware tokens (Ano) encourage the model to focus on abnormal regions and build more discriminative lesion centered representations. Second, inter-image difference tokens (Diff) explicitly encode temporal changes between studies, allowing the model to distinguish worsening, improvement, and stability in disease burden. Finally, a dedicated explainability stage trains the model to generate heatmaps that highlight lesion-related regions, offering clear visual evidence that is consistent with the model's reasoning. Through our staged design, Medic-AD steadily boosts performance across anomaly detection, symptom tracking, and anomaly segmentation, achieving state-of-the-art results compared with both closed source and medical-specialized baselines. Evaluations on real longitudinal clinical data collected from real hospital workflows further show that Medic-AD delivers stable predictions and clinically faithful explanations in practical patient-monitoring and decision-support workflows.