基于原型的知识引导的细粒度结构化放射科报告
Prototype-Based Knowledge Guidance for Fine-Grained Structured Radiology Reporting
AI总结：
ProtoSR通过整合自由文本信息提升细粒度结构化放射科报告的自动化水平，利用多模态知识库和原型条件残差增强模型预测，有效改进了对罕见发现和属性的识别能力。
摘要：
结构化放射科报告比自由文本报告能更快更一致地进行沟通，但自动化仍然困难，因为模型必须对罕见发现和属性做出许多细粒度的离散决策，而这些决策只能从有限的结构化监督中获得。相比之下，自由文本报告在常规医疗中大量产生，并通过详细的描述隐含地编码了与图像相关的信息。为了利用这种无结构的知识，我们提出了ProtoSR，一种将自由文本信息注入结构化报告生成的方法。首先，我们介绍了一个自动提取管道，利用指令调优的LLM挖掘80000多个MIMIC-CXR研究，并构建一个与结构化报告模板对齐的多模态知识库，用视觉原型表示每个答案选项。使用这个知识库，ProtoSR被训练来检索与当前图像-问题对相关的原型，并通过原型条件的残差来增强模型预测，提供一种数据驱动的第二意见，选择性地纠正预测。在Rad-ReStruct基准测试中，ProtoSR取得了最先进的结果，最大的改进体现在详细属性问题上，证明了将自由文本衍生的信号整合到细粒度图像理解中的价值。
英文摘要：
Structured radiology reporting promises faster, more consistent communication than free text, but automation remains difficult as models must make many fine-grained, discrete decisions about rare findings and attributes from limited structured supervision. In contrast, free-text reports are produced at scale in routine care and implicitly encode fine-grained, image-linked information through detailed descriptions. To leverage this unstructured knowledge, we propose ProtoSR, an approach for injecting free-text information into structured report population. First, we introduce an automatic extraction pipeline that uses an instruction-tuned LLM to mine 80k+ MIMIC-CXR studies and build a multimodal knowledge base aligned with a structured reporting template, representing each answer option with a visual prototype. Using this knowledge base, ProtoSR is trained to retrieve prototypes relevant for the current image-question pair and augment the model predictions through a prototype-conditioned residual, providing a data-driven second opinion that selectively corrects predictions. On the Rad-ReStruct benchmark, ProtoSR achieves state-of-the-art results, with the largest improvements on detailed attribute questions, demonstrating the value of integrating free-text derived signal for fine-grained image understanding.
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。
