Saved in:
Bibliographic Details
Main Authors: Wang, Fuying, Du, Shenghui, Yu, Lequan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.15158
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929429592145920
author Wang, Fuying
Du, Shenghui
Yu, Lequan
author_facet Wang, Fuying
Du, Shenghui
Yu, Lequan
contents Radiology reports provide detailed descriptions of medical imaging integrated with patients' medical histories, while report writing is traditionally labor-intensive, increasing radiologists' workload and the risk of diagnostic errors. Recent efforts in automating this process seek to mitigate these issues by enhancing accuracy and clinical efficiency. Emerging research in automating this process promises to alleviate these challenges by reducing errors and streamlining clinical workflows. However, existing automated approaches are based on a single timestamp and often neglect the critical temporal aspect of patients' imaging histories, which is essential for accurate longitudinal analysis. To address this gap, we propose a novel History Enhanced Radiology Report Generation (HERGen) framework that employs a employs a group causal transformer to efficiently integrate longitudinal data across patient visits. Our approach not only allows for comprehensive analysis of varied historical data but also improves the quality of generated reports through an auxiliary contrastive objective that aligns image sequences with their corresponding reports. More importantly, we introduce a curriculum learning-based strategy to adeptly handle the inherent complexity of longitudinal radiology data and thus stabilize the optimization of our framework. The extensive evaluations across three datasets demonstrate that our framework surpasses existing methods in generating accurate radiology reports and effectively predicting disease progression from medical images.
format Preprint
id arxiv_https___arxiv_org_abs_2407_15158
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle HERGen: Elevating Radiology Report Generation with Longitudinal Data
Wang, Fuying
Du, Shenghui
Yu, Lequan
Computer Vision and Pattern Recognition
Radiology reports provide detailed descriptions of medical imaging integrated with patients' medical histories, while report writing is traditionally labor-intensive, increasing radiologists' workload and the risk of diagnostic errors. Recent efforts in automating this process seek to mitigate these issues by enhancing accuracy and clinical efficiency. Emerging research in automating this process promises to alleviate these challenges by reducing errors and streamlining clinical workflows. However, existing automated approaches are based on a single timestamp and often neglect the critical temporal aspect of patients' imaging histories, which is essential for accurate longitudinal analysis. To address this gap, we propose a novel History Enhanced Radiology Report Generation (HERGen) framework that employs a employs a group causal transformer to efficiently integrate longitudinal data across patient visits. Our approach not only allows for comprehensive analysis of varied historical data but also improves the quality of generated reports through an auxiliary contrastive objective that aligns image sequences with their corresponding reports. More importantly, we introduce a curriculum learning-based strategy to adeptly handle the inherent complexity of longitudinal radiology data and thus stabilize the optimization of our framework. The extensive evaluations across three datasets demonstrate that our framework surpasses existing methods in generating accurate radiology reports and effectively predicting disease progression from medical images.
title HERGen: Elevating Radiology Report Generation with Longitudinal Data
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.15158