GIT-CXR: End-to-End Transformer for Chest X-Ray Report Generation

TL;DR

This paper introduces GIT-CXR, an end-to-end transformer model with curriculum learning for automated chest X-ray report generation, achieving state-of-the-art clinical accuracy and natural language metrics on the MIMIC-CXR dataset.

Contribution

It is the first to apply curriculum learning to end-to-end transformers in medical imaging report generation, improving performance and report quality.

Findings

Achieved new state-of-the-art results on clinical F1 metrics.

Matched current best on BLEU and ROUGE-L metrics.

Demonstrated the effectiveness of curriculum learning in this context.

Abstract

Medical imaging is crucial for diagnosing, monitoring, and treating medical conditions. The medical reports of radiology images are the primary medium through which medical professionals attest their findings, but their writing is time consuming and requires specialized clinical expertise. The automated generation of radiography reports has thus the potential to improve and standardize patient care and significantly reduce clinicians workload. Through our work, we have designed and evaluated an end-to-end transformer-based method to generate accurate and factually complete radiology reports for X-ray images. Additionally, we are the first to introduce curriculum learning for end-to-end transformers in medical imaging and demonstrate its impact in obtaining improved performance. The experiments have been conducted using the MIMIC-CXR-JPG database, the largest available chest X-ray dataset. The results obtained are comparable with the current state-of-the-art on the natural language generation (NLG) metrics BLEU and ROUGE-L, while setting new state-of-the-art results on F1 examples-averaged, F1-macro and F1-micro metrics for clinical accuracy and on the METEOR metric widely used for NLG.