Comparative Analysis of Abstractive Summarization Models for Clinical Radiology Reports

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bhattacharya, Anindita, Rehman, Tohida, Sanyal, Debarshi Kumar, Chattopadhyay, Samiran
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913903457337344
author Bhattacharya, Anindita
Rehman, Tohida
Sanyal, Debarshi Kumar
Chattopadhyay, Samiran
author_facet Bhattacharya, Anindita
Rehman, Tohida
Sanyal, Debarshi Kumar
Chattopadhyay, Samiran
contents The findings section of a radiology report is often detailed and lengthy, whereas the impression section is comparatively more compact and captures key diagnostic conclusions. This research explores the use of advanced abstractive summarization models to generate the concise impression from the findings section of a radiology report. We have used the publicly available MIMIC-CXR dataset. A comparative analysis is conducted on leading pre-trained and open-source large language models, including T5-base, BART-base, PEGASUS-x-base, ChatGPT-4, LLaMA-3-8B, and a custom Pointer Generator Network with a coverage mechanism. To ensure a thorough assessment, multiple evaluation metrics are employed, including ROUGE-1, ROUGE-2, ROUGE-L, METEOR, and BERTScore. By analyzing the performance of these models, this study identifies their respective strengths and limitations in the summarization of medical text. The findings of this paper provide helpful information for medical professionals who need automated summarization solutions in the healthcare sector.
format Preprint
id arxiv_https___arxiv_org_abs_2506_16247
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Comparative Analysis of Abstractive Summarization Models for Clinical Radiology Reports
Bhattacharya, Anindita
Rehman, Tohida
Sanyal, Debarshi Kumar
Chattopadhyay, Samiran
Computation and Language
The findings section of a radiology report is often detailed and lengthy, whereas the impression section is comparatively more compact and captures key diagnostic conclusions. This research explores the use of advanced abstractive summarization models to generate the concise impression from the findings section of a radiology report. We have used the publicly available MIMIC-CXR dataset. A comparative analysis is conducted on leading pre-trained and open-source large language models, including T5-base, BART-base, PEGASUS-x-base, ChatGPT-4, LLaMA-3-8B, and a custom Pointer Generator Network with a coverage mechanism. To ensure a thorough assessment, multiple evaluation metrics are employed, including ROUGE-1, ROUGE-2, ROUGE-L, METEOR, and BERTScore. By analyzing the performance of these models, this study identifies their respective strengths and limitations in the summarization of medical text. The findings of this paper provide helpful information for medical professionals who need automated summarization solutions in the healthcare sector.
title Comparative Analysis of Abstractive Summarization Models for Clinical Radiology Reports
topic Computation and Language
url https://arxiv.org/abs/2506.16247