Anatomically-Grounded Fact Checking of Automated Chest X-ray Reports
This addresses the issue of unreliable automated radiology reports for medical professionals, though it is incremental as it builds on existing reporting tools.
The paper tackles the problem of factual errors in automated chest X-ray reports by proposing an explainable fact-checking model that identifies errors and their locations, resulting in over 40% improvement in report quality through error detection and correction.
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.