The Impression section of a radiology report summarizes crucial radiology findings in natural language and plays a central role in communicating these findings to physicians. However, the process of generating impressions by summarizing findings is time-consuming for radiologists and prone to errors. We propose to automate the generation of radiology impressions with neural sequence-to-sequence learning. We further propose a customized neural model for this task which learns to encode the study background information and use this information to guide the decoding process. On a large dataset of radiology reports collected from actual hospital studies, our model outperforms existing non-neural and neural baselines under the ROUGE metrics. In a blind experiment, a board-certified radiologist indicated that 67% of sampled system summaries are at least as good as the corresponding human-written summaries, suggesting significant clinical validity. To our knowledge our work represents the first attempt in this direction.
@article{arxiv.1809.04698,
title = {Learning to Summarize Radiology Findings},
author = {Yuhao Zhang and Daisy Yi Ding and Tianpei Qian and Christopher D. Manning and Curtis P. Langlotz},
journal= {arXiv preprint arXiv:1809.04698},
year = {2018}
}
Comments
EMNLP 2018 Workshop on Health Text Mining and Information Analysis (EMNLP-LOUHI). Code and pretrained model available at: https://github.com/yuhaozhang/summarize-radiology-findings