Fine-tuning ERNIE for chest abnormal imaging signs extraction

Journal article

Zhaoning Li, Jiangtao Ren
Journal of Biomedical Informatics, vol. 108, 2020, p. 103492

DOI: 10.1016/j.jbi.2020.103492

View PDF DOI arXiv Github

Cite

APA Click to copy
Li, Z., & Ren, J. (2020). Fine-tuning ERNIE for chest abnormal imaging signs extraction. Journal of Biomedical Informatics, 108, 103492. https://doi.org/10.1016/j.jbi.2020.103492

Chicago/Turabian Click to copy
Li, Zhaoning, and Jiangtao Ren. “Fine-Tuning ERNIE for Chest Abnormal Imaging Signs Extraction.” Journal of Biomedical Informatics 108 (2020): 103492.

MLA Click to copy
Li, Zhaoning, and Jiangtao Ren. “Fine-Tuning ERNIE for Chest Abnormal Imaging Signs Extraction.” Journal of Biomedical Informatics, vol. 108, 2020, p. 103492, doi:10.1016/j.jbi.2020.103492.

BibTeX Click to copy

@article{li2020a,
  title = {Fine-tuning ERNIE for chest abnormal imaging signs extraction},
  year = {2020},
  journal = {Journal of Biomedical Informatics},
  pages = {103492},
  volume = {108},
  doi = {10.1016/j.jbi.2020.103492},
  author = {Li, Zhaoning and Ren, Jiangtao}
}

Citations: 5; JCR-Q2; 2022 JIF: 4.5; 2023中科院分区升级版 医学2区

Highlights

Fine-tuning the pretrained language model alleviates the problem of data insuﬃciency
A novel tag2relation algorithm has been proposed to serve the matching task
Experimental results show that the proposed method outperforms other baselines

Abstract

Chest imaging reports describe the results of chest radiography procedures. Automatic extraction of abnormal imaging signs from chest imaging reports has a pivotal role in clinical research and a wide range of downstream medical tasks. However, there are few studies on information extraction from Chinese chest imaging reports. In this paper, we formulate chest abnormal imaging sign extraction as a sequence tagging and matching problem. On this basis, we propose a transferred abnormal imaging signs extractor with pretrained ERNIE as the backbone, named EASON (fine-tuning ERNIE with CRF for Abnormal Signs ExtractiON), which can address the problem of data insufficiency. In addition, to assign the attributes (the body part and degree) to corresponding abnormal imaging signs from the results of the sequence tagging model, we design a simple but effective tag2relation algorithm based on the nature of chest imaging report text. We evaluate our method on the corpus provided by a medical big data company, and the experimental results demonstrate that our method achieves significant and consistent improvement compared to other baselines.

Keywords

Chest Abnormal Imaging Signs Extraction, Sequence Tagging, ERNIE, Conditional Random Field

The overview architecture of the EASON model