Boosting Radiology Report Generation by Infusing Comparison Prior

TL;DR

This paper introduces a method to improve radiology report generation by incorporating comparison prior information extracted from reports, leading to more accurate and realistic reports that avoid referencing non-existent prior exams.

Contribution

A novel rule-based labeler extracts comparison priors from reports, which are integrated into transformer models to enhance report accuracy and realism.

Findings

Outperforms baseline models on IU X-ray and MIMIC-CXR datasets

Generates reports free from false references to prior exams

Improves natural language generation metrics

Abstract

Recent transformer-based models have made significant strides in generating radiology reports from chest X-ray images. However, a prominent challenge remains: these models often lack prior knowledge, resulting in the generation of synthetic reports that mistakenly reference non-existent prior exams. This discrepancy can be attributed to a knowledge gap between radiologists and the generation models. While radiologists possess patient-specific prior information, the models solely receive X-ray images at a specific time point. To tackle this issue, we propose a novel approach that leverages a rule-based labeler to extract comparison prior information from radiology reports. This extracted comparison prior is then seamlessly integrated into state-of-the-art transformer-based models, enabling them to produce more realistic and comprehensive reports. Our method is evaluated on English report datasets, such as IU X-ray and MIMIC-CXR. The results demonstrate that our approach surpasses baseline models in terms of natural language generation metrics. Notably, our model generates reports that are free from false references to non-existent prior exams, setting it apart from previous models. By addressing this limitation, our approach represents a significant step towards bridging the gap between radiologists and generation models in the domain of medical report generation.