Contrastive concept-phrase pre-training for generating clinically accurate and interpretable chest X-ray reports
Document Type
Article
Source of Publication
Neural Computing and Applications
Publication Date
1-1-2024
Abstract
Automated radiology report generation is an emerging field for improving patient care and alleviating radiologist workload. However, existing methods face a range of challenges such as limited data availability, clinical metric performance, and interpretability. To address these issues, we propose a contrastive concept-phrase pre-training (C2P2) method, which utilizes a phrase-concept grounding task for contrastive learning. C2P2 learns the correspondence between phrases in a report and image concepts by using a phrase classification task to train a multi-label classifier for X-rays and extracting visual concepts of phrases using class activation maps. We then fine-tune a pre-trained BERT model to translate the extracted phrases into reports. Our proposed method outperforms or matches the previous state of the art in clinical efficacy metrics on both internal and external datasets. Moreover, C2P2 leverages more vision language data for pre-training and provides visual explanations of generated phrases.
DOI Link
ISSN
Publisher
Springer Science and Business Media LLC
Disciplines
Computer Sciences
Keywords
Chest X rays, Contrastive learning, Language image pre-training, Medical reports
Scopus ID
Recommended Citation
Tubaishat, Abdallah; Zia, Tehseen; Windridge, David; Nawaz, Muhammad; and Razzaq, Saad, "Contrastive concept-phrase pre-training for generating clinically accurate and interpretable chest X-ray reports" (2024). All Works. 6977.
https://zuscholars.zu.ac.ae/works/6977
Indexed in Scopus
yes
Open Access
no