面向视觉锚定的医学报告生成的自监督解剖一致性学习
Self-Supervised Anatomical Consistency Learning for Vision-Grounded Medical Report Generation
AI总结：
针对现有视觉锚定医学报告生成方法依赖专家标注、泛化性差的问题，提出无标注的自监督解剖一致性学习框架SS-ACL，通过分层解剖图与区域级对比学习实现对齐，在报告生成及下游视觉任务上性能显著优于现有方法。
摘要：
视觉锚定的医学报告生成旨在生成医学图像的临床准确描述，以明确的视觉证据为支撑，从而提升可解释性并便于融入临床工作流。然而，现有方法通常依赖单独训练的检测模块，这类模块需要大量专家标注，不仅标注成本高昂，还会因不同数据集间的病理分布偏差限制泛化能力。为解决这些挑战，我们提出自监督解剖一致性学习（Self-Supervised Anatomical Consistency Learning，SS-ACL）——一种全新的无标注框架，借助简单文本提示将生成的报告与对应解剖区域对齐。SS-ACL受人体解剖学固定的自上而下包含结构启发，构建分层解剖图，按空间位置组织实体；它通过递归重建细粒度解剖区域来强制执行样本内空间对齐，从本质上引导注意力图朝向文本提示的视觉相关区域。为进一步增强异常识别的样本间语义对齐，SS-ACL引入了基于解剖一致性的区域级对比学习。这些对齐的嵌入向量作为报告生成的先验，使注意力图能够提供可解释的视觉证据。大量实验表明，无需依赖专家标注的SS-ACL：（1）能生成准确且具备视觉锚定的报告，在词汇准确率上优于当前最优方法10%，临床效能上优25%；（2）在多种下游视觉任务上取得有竞争力的性能，在零样本视觉锚定任务上超越当前主流视觉基础模型8%。
英文摘要：
Vision-grounded medical report generation aims to produce clinically accurate descriptions of medical images, anchored in explicit visual evidence to improve interpretability and facilitate integration into clinical workflows. However, existing methods often rely on separately trained detection modules that require extensive expert annotations, introducing high labeling costs and limiting generalizability due to pathology distribution bias across datasets. To address these challenges, we propose Self-Supervised Anatomical Consistency Learning (SS-ACL) -- a novel and annotation-free framework that aligns generated reports with corresponding anatomical regions using simple textual prompts. SS-ACL constructs a hierarchical anatomical graph inspired by the invariant top-down inclusion structure of human anatomy, organizing entities by spatial location. It recursively reconstructs fine-grained anatomical regions to enforce intra-sample spatial alignment, inherently guiding attention maps toward visually relevant areas prompted by text. To further enhance inter-sample semantic alignment for abnormality recognition, SS-ACL introduces a region-level contrastive learning based on anatomical consistency. These aligned embeddings serve as priors for report generation, enabling attention maps to provide interpretable visual evidence. Extensive experiments demonstrate that SS-ACL, without relying on expert annotations, (i) generates accurate and visually grounded reports -- outperforming state-of-the-art methods by 10\% in lexical accuracy and 25\% in clinical efficacy, and (ii) achieves competitive performance on various downstream visual tasks, surpassing current leading visual foundation models by 8\% in zero-shot visual grounding.
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。
