@inproceedings{huang-etal-2025-ddgip,
title = "{DDGIP}: Radiology Report Generation Through Disease Description Graph and Informed Prompting",
author = "Huang, Chentao and
Li, Guangli and
Zhou, Xinjiong and
Ren, Yafeng and
Zhang, Hongbin",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-naacl.215/",
doi = "10.18653/v1/2025.findings-naacl.215",
pages = "3884--3894",
ISBN = "979-8-89176-195-7",
abstract = "Automatic radiology report generation has attracted considerable attention with the rise of computer-aided diagnostic systems. Due to the inherent biases in medical imaging data, generating reports with precise clinical details is challenging yet crucial for accurate diagnosis. To this end, we design a disease description graph that encapsulates comprehensive and pertinent disease information. By aligning visual features with the graph, our model enhances the quality of the generated reports. Furthermore, we introduce a novel informed prompting method which increases the accuracy of short-gram predictions, acting as an implicit bag-of-words planning for surface realization. Notably, this informed prompt succeeds with a three-layer decoder, reducing the reliance on conventional prompting methods that require extensive model parameters. Extensive experiments on two widely-used datasets, IU-Xray and MIMIC-CXR, demonstrate that our method outperforms previous state-of-the-art models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2025-ddgip">
<titleInfo>
<title>DDGIP: Radiology Report Generation Through Disease Description Graph and Informed Prompting</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chentao</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guangli</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinjiong</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yafeng</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongbin</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-195-7</identifier>
</relatedItem>
<abstract>Automatic radiology report generation has attracted considerable attention with the rise of computer-aided diagnostic systems. Due to the inherent biases in medical imaging data, generating reports with precise clinical details is challenging yet crucial for accurate diagnosis. To this end, we design a disease description graph that encapsulates comprehensive and pertinent disease information. By aligning visual features with the graph, our model enhances the quality of the generated reports. Furthermore, we introduce a novel informed prompting method which increases the accuracy of short-gram predictions, acting as an implicit bag-of-words planning for surface realization. Notably, this informed prompt succeeds with a three-layer decoder, reducing the reliance on conventional prompting methods that require extensive model parameters. Extensive experiments on two widely-used datasets, IU-Xray and MIMIC-CXR, demonstrate that our method outperforms previous state-of-the-art models.</abstract>
<identifier type="citekey">huang-etal-2025-ddgip</identifier>
<identifier type="doi">10.18653/v1/2025.findings-naacl.215</identifier>
<location>
<url>https://aclanthology.org/2025.findings-naacl.215/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>3884</start>
<end>3894</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DDGIP: Radiology Report Generation Through Disease Description Graph and Informed Prompting
%A Huang, Chentao
%A Li, Guangli
%A Zhou, Xinjiong
%A Ren, Yafeng
%A Zhang, Hongbin
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Findings of the Association for Computational Linguistics: NAACL 2025
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-195-7
%F huang-etal-2025-ddgip
%X Automatic radiology report generation has attracted considerable attention with the rise of computer-aided diagnostic systems. Due to the inherent biases in medical imaging data, generating reports with precise clinical details is challenging yet crucial for accurate diagnosis. To this end, we design a disease description graph that encapsulates comprehensive and pertinent disease information. By aligning visual features with the graph, our model enhances the quality of the generated reports. Furthermore, we introduce a novel informed prompting method which increases the accuracy of short-gram predictions, acting as an implicit bag-of-words planning for surface realization. Notably, this informed prompt succeeds with a three-layer decoder, reducing the reliance on conventional prompting methods that require extensive model parameters. Extensive experiments on two widely-used datasets, IU-Xray and MIMIC-CXR, demonstrate that our method outperforms previous state-of-the-art models.
%R 10.18653/v1/2025.findings-naacl.215
%U https://aclanthology.org/2025.findings-naacl.215/
%U https://doi.org/10.18653/v1/2025.findings-naacl.215
%P 3884-3894
Markdown (Informal)
[DDGIP: Radiology Report Generation Through Disease Description Graph and Informed Prompting](https://aclanthology.org/2025.findings-naacl.215/) (Huang et al., Findings 2025)
ACL