解决胸部X光报告中的测量幻觉问题，提升报告准确性。
FactCheXcker: Mitigating Measurement Hallucinations in Chest X-ray Report Generation Models
- 用改进的查询-代码-更新范式，通过大模型生成代码修正测量值。
- 在MIMIC-CXR数据集上使测量幻觉减少135.0%，平均绝对误差下降。
- 适用于医疗报告生成模型，特别适合关注定量准确性的研究者。
医学视觉-语言模型在生成放射科报告时常出现定量测量错误，导致幻觉，影响临床可信度。我们提出FactCheXcker，一种模块化框架，通过改进的查询-代码-更新范式，消除报告中的测量幻觉。该框架利用专用模块和大语言模型的代码生成能力，基于原始报告生成测量查询并求解。提取可测量发现后，结果被整合进更新后的报告。我们在MIMIC-CXR数据集上评估了气管插管位置（占报告测量的平均78%）任务，涵盖11个医学报告生成模型。结果显示，FactCheXcker显著降低幻觉，提升测量精度，并保持原报告质量。10/11个模型性能提升，测量幻觉减少135.0%（以平均绝对误差衡量）。代码已开源：https://github.com/rajpurkarlab/FactCheXcker。
原文摘要 · Abstract (English)
Medical vision-language models often struggle with generating accurate quantitative measurements in radiology reports, leading to hallucinations that undermine clinical reliability. We introduce FactCheXcker, a modular framework that de-hallucinates radiology report measurements by leveraging an improved query-code-update paradigm. Specifically, FactCheXcker employs specialized modules and the code generation capabilities of large language models to solve measurement queries generated based on the original report. After extracting measurable findings, the results are incorporated into an updated report. We evaluate FactCheXcker on endotracheal tube placement, which accounts for an average of 78% of report measurements, using the MIMIC-CXR dataset and 11 medical report-generation models. Our results show that FactCheXcker significantly reduces hallucinations, improves measurement precision, and maintains the quality of the original reports. Specifically, FactCheXcker improves the performance of 10/11 models and achieves an average improvement of 135.0% in reducing measurement hallucinations measured by mean absolute error. Code is available at https://github.com/rajpurkarlab/FactCheXcker.
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。