基于解剖学依据的自动化胸部 X 光报告事实核查
Anatomically-Grounded Fact Checking of Automated Chest X-ray Reports
AI总结：
针对自动胸片报告的事实错误，本文构建含真假发现及位置描述的合成数据集，训练多标签跨模态对比回归网络，实现可解释的错误定位与核查，并使 SOTA 报告质量提升超 40%。
摘要：
随着大规模视觉语言模型的出现，仅以医学图像为输入、由简单提示引导，就可能生成逼真的放射学报告。然而，由于其在描述所见结果时存在事实错误，其实用性一直受到限制。本文提出一种用于可解释事实核查的新型模型，可识别所见结果中的错误以及报告所指示的错误位置。具体而言，我们分析了自动化报告方法所犯错误的类型，并从一个真值数据集中构建了新的合成数据集，其中图像与关于所见结果及其位置的真实和虚假描述配对。随后，我们在该数据集上训练了一个新的多标签跨模态对比回归网络。我们评估了所得事实核查模型，以及它在多种基准数据集上纠正若干 SOTA 自动化报告工具所生成报告的效用；结果表明，通过此类错误检测与纠正，报告质量提升超过 40%。
英文摘要：
With the emergence of large-scale vision-language models, realistic radiology reports may be generated using only medical images as input guided by simple prompts. However, their practical utility has been limited due to the factual errors in their description of findings. In this paper, we propose a novel model for explainable fact-checking that identifies errors in findings and their locations indicated through the reports. Specifically, we analyze the types of errors made by automated reporting methods and derive a new synthetic dataset of images paired with real and fake descriptions of findings and their locations from a ground truth dataset. A new multi-label cross-modal contrastive regression network is then trained on this datsaset. We evaluate the resulting fact-checking model and its utility in correcting reports generated by several SOTA automated reporting tools on a variety of benchmark datasets with results pointing to over 40\% improvement in report quality through such error detection and correction.
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。
