MedAutoCorrect: Image-Conditioned Autocorrection in Medical Reporting

TL;DR

This paper introduces MedAutoCorrect, a two-stage framework that detects and corrects errors in medical reports conditioned on medical images, aiming to improve the accuracy and trustworthiness of automated medical reporting systems.

Contribution

It presents the first image-conditioned autocorrection method for medical reports, addressing factual inaccuracies and enhancing reliability in automated healthcare documentation.

Findings

Effective error detection and correction demonstrated on MIMIC-CXR dataset.

Outperforms existing report generation models in accuracy.

Potential to serve as a reliability safeguard in medical AI systems.

Abstract

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.