Weakly Supervised Contrastive Learning for Chest X-Ray Report Generation
An Yan, Zexue He, Xing Lu, Jiang Du, Eric Chang, Amilcare Gentili, Julian McAuley, Chun-Nan Hsu
Abstract
Radiology report generation aims at generating descriptive text from radiology images automatically, which may present an opportunity to improve radiology reporting and interpretation. A typical setting consists of training encoder-decoder models on image-report pairs with a cross entropy loss, which struggles to generate informative sentences for clinical diagnoses since normal findings dominate the datasets. To tackle this challenge and encourage more clinically-accurate text outputs, we propose a novel weakly supervised contrastive loss for medical report generation. Experimental results demonstrate that our method benefits from contrasting target reports with incorrect but semantically-close ones. It outperforms previous work on both clinical correctness and text generation metrics for two public benchmarks.- Anthology ID:
- 2021.findings-emnlp.336
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2021
- Month:
- November
- Year:
- 2021
- Address:
- Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- Findings
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4009–4015
- Language:
- URL:
- https://aclanthology.org/2021.findings-emnlp.336
- DOI:
- 10.18653/v1/2021.findings-emnlp.336
- Cite (ACL):
- An Yan, Zexue He, Xing Lu, Jiang Du, Eric Chang, Amilcare Gentili, Julian McAuley, and Chun-Nan Hsu. 2021. Weakly Supervised Contrastive Learning for Chest X-Ray Report Generation. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 4009–4015, Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Weakly Supervised Contrastive Learning for Chest X-Ray Report Generation (Yan et al., Findings 2021)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2021.findings-emnlp.336.pdf
- Data
- CheXpert, MIMIC-CXR