RadBARTsum: Domain Specific Adaption of Denoising Sequence-to-Sequence Models for Abstractive Radiology Report Summarization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Jinge, Hasan, Abul, Wu, Honghan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910472927707136
author Wu, Jinge
Hasan, Abul
Wu, Honghan
author_facet Wu, Jinge
Hasan, Abul
Wu, Honghan
contents Radiology report summarization is a crucial task that can help doctors quickly identify clinically significant findings without the need to review detailed sections of reports. This study proposes RadBARTsum, a domain-specific and ontology facilitated adaptation of the BART model for abstractive radiology report summarization. The approach involves two main steps: 1) re-training the BART model on a large corpus of radiology reports using a novel entity masking strategy to improving biomedical domain knowledge learning, and 2) fine-tuning the model for the summarization task using the Findings and Background sections to predict the Impression section. Experiments are conducted using different masking strategies. Results show that the re-training process with domain knowledge facilitated masking improves performances consistently across various settings. This work contributes a domain-specific generative language model for radiology report summarization and a method for utilising medical knowledge to realise entity masking language model. The proposed approach demonstrates a promising direction of enhancing the efficiency of language models by deepening its understanding of clinical knowledge in radiology reports.
format Preprint
id arxiv_https___arxiv_org_abs_2406_03062
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle RadBARTsum: Domain Specific Adaption of Denoising Sequence-to-Sequence Models for Abstractive Radiology Report Summarization
Wu, Jinge
Hasan, Abul
Wu, Honghan
Computation and Language
Radiology report summarization is a crucial task that can help doctors quickly identify clinically significant findings without the need to review detailed sections of reports. This study proposes RadBARTsum, a domain-specific and ontology facilitated adaptation of the BART model for abstractive radiology report summarization. The approach involves two main steps: 1) re-training the BART model on a large corpus of radiology reports using a novel entity masking strategy to improving biomedical domain knowledge learning, and 2) fine-tuning the model for the summarization task using the Findings and Background sections to predict the Impression section. Experiments are conducted using different masking strategies. Results show that the re-training process with domain knowledge facilitated masking improves performances consistently across various settings. This work contributes a domain-specific generative language model for radiology report summarization and a method for utilising medical knowledge to realise entity masking language model. The proposed approach demonstrates a promising direction of enhancing the efficiency of language models by deepening its understanding of clinical knowledge in radiology reports.
title RadBARTsum: Domain Specific Adaption of Denoising Sequence-to-Sequence Models for Abstractive Radiology Report Summarization
topic Computation and Language
url https://arxiv.org/abs/2406.03062