用图像引导自动修正医学报告错误，提升诊疗可靠性
MedAutoCorrect: Image-Conditioned Autocorrection in Medical Reporting
- 基于图像上下文定位报告中的错误并修复
- 在MIMIC-CXR数据集上实现高精度错误纠正
- 适合需要高可信度报告的医疗AI系统使用
在医学报告中，放射科报告的准确性无论由人工还是机器学习生成都至关重要。本文提出一项新任务：基于图像的报告内容自动修正。我们使用MIMIC-CXR数据集，先人为引入多种类型错误，再提出一种两阶段框架，能够精准定位错误并进行修正，模拟真实场景下的自动纠错过程。该方法旨在解决现有自动化医学报告系统中存在的事实性错误和结论错误等问题，提升关键医疗应用中的报告可靠性。重要的是，该方法可作为安全屏障，保障自动化报告生成的准确性和可信度。在多个基准数据集和前沿报告生成模型上的实验验证了该方法在修正医学报告错误方面的潜力。
原文摘要 · Abstract (English)
In medical reporting, the accuracy of radiological reports, whether generated by humans or machine learning algorithms, is critical. We tackle a new task in this paper: image-conditioned autocorrection of inaccuracies within these reports. Using the MIMIC-CXR dataset, we first intentionally introduce a diverse range of errors into reports. Subsequently, we propose a two-stage framework capable of pinpointing these errors and then making corrections, simulating an \textit{autocorrection} process. This method aims to address the shortcomings of existing automated medical reporting systems, like factual errors and incorrect conclusions, enhancing report reliability in vital healthcare applications. Importantly, our approach could serve as a guardrail, ensuring the accuracy and trustworthiness of automated report generation. Experiments on established datasets and state of the art report generation models validate this method's potential in correcting medical reporting errors.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。