Automatic recognition of abdominal lymph nodes from clinical text

TitleAutomatic recognition of abdominal lymph nodes from clinical text
Publication TypeConference Paper
Year of Publication2020
AuthorsPeng Y, Lee S, Elton DC, Shen T, Tang Y-xing, Chen Q, Wang S, Zhu Y, Summers R, Lu Z
Conference NameProceedings of the 3rd Clinical Natural Language Processing Workshop
Date Published11/2020
PublisherAssociation for Computational Linguistics
Abstract

Lymph node status plays a pivotal role in the treatment of cancer. The extraction of lymph nodes from radiology text reports enables large-scale training of lymph node detection on MRI. In this work, we first propose an ontology of 41 types of abdominal lymph nodes with a hierarchical relationship. We then introduce an end-to-end approach based on the combination of rules and transformer-based methods to detect these abdominal lymph node mentions and classify their types from the MRI radiology reports. We demonstrate the superior performance of a model fine-tuned on MRI reports using BlueBERT, called MriBERT. We find that MriBERT outperforms the rule-based labeler (0.957 vs 0.644 in micro weighted F1-score) as well as other BERT-based variations (0.913 - 0.928). We make the code and MriBERT publicly available at https://github.com/ncbi-nlp/bluebert, with the hope that this method can facilitate the development of medical report annotators to produce labels from scratch at scale.

URLhttps://www.aclweb.org/anthology/2020.clinicalnlp-1.12