GREEN: Generative Radiology Report Evaluation and Error Notation

Sophie Ostmeier, Justin Xu, Zhihong Chen, Maya Varma, Louis Blankemeier, Christian Bluethgen, Arne Md, Michael Moseley, Curtis Langlotz, Akshay Chaudhari, Jean-Benoit Delbrouck


Abstract
Evaluating radiology reports is a challenging problem as factual correctness is extremely important due to its medical nature. Existing automatic evaluation metrics either suffer from failing to consider factual correctness (e.g., BLEU and ROUGE) or are limited in their interpretability (e.g., F1CheXpert and F1RadGraph). In this paper, we introduce GREEN (Generative Radiology Report Evaluation and Error Notation), a radiology report generation metric that leverages the natural language understanding of language models to identify and explain clinically significant errors in candidate reports, both quantitatively and qualitatively. Compared to current metrics, GREEN offers: 1) a score aligned with expert preferences, 2) human interpretable explanations of clinically significant errors, enabling feedback loops with end-users, and 3) a lightweight open-source method that reaches the performance of commercial counterparts. We validate our GREEN metric by comparing it to GPT-4, as well as to error counts of 6 experts and preferences of 2 experts. Our method demonstrates not only higher correlation with expert error counts, but simultaneously higher alignment with expert preferences when compared to previous approaches.
Anthology ID:
2024.findings-emnlp.21
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
374–390
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.21
DOI:
Bibkey:
Cite (ACL):
Sophie Ostmeier, Justin Xu, Zhihong Chen, Maya Varma, Louis Blankemeier, Christian Bluethgen, Arne Md, Michael Moseley, Curtis Langlotz, Akshay Chaudhari, and Jean-Benoit Delbrouck. 2024. GREEN: Generative Radiology Report Evaluation and Error Notation. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 374–390, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
GREEN: Generative Radiology Report Evaluation and Error Notation (Ostmeier et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.21.pdf