@inproceedings{zhou-wang-2024-divide,
title = "Divide and Conquer Radiology Report Generation via Observation Level Fine-grained Pretraining and Prompt Tuning",
author = "Zhou, Yuanpin and
Wang, Huogen",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.433/",
doi = "10.18653/v1/2024.emnlp-main.433",
pages = "7597--7610",
abstract = "The automation of radiology report generation (RRG) holds immense potential to alleviate radiologists' workloads and improve diagnostic accuracy. Despite advancements in image captioning and vision-language pretraining, RRG remains challenging due to the lengthy and complex nature of radiology reports. In this work, we proposes the Divide and Conquer Radiology Report Generation (DCRRG) model, which breaks down full-text radiology reports into concise observation descriptions. This approach enables the model to capture fine-grained representations from each observation through a two-stage process: an encoding stage focusing on observation prediction tasks to learn fine-grained representations, and a decoding stage for integrating these descriptions into cohesive and comprehensive radiology reports. Experimental results on two benchmark datasets demonstrate that DCRRG achieves significant improvements across all evaluated metrics, underscoring its capability to generate semantically coherent and clinically accurate radiology reports."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-wang-2024-divide">
<titleInfo>
<title>Divide and Conquer Radiology Report Generation via Observation Level Fine-grained Pretraining and Prompt Tuning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuanpin</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huogen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The automation of radiology report generation (RRG) holds immense potential to alleviate radiologists’ workloads and improve diagnostic accuracy. Despite advancements in image captioning and vision-language pretraining, RRG remains challenging due to the lengthy and complex nature of radiology reports. In this work, we proposes the Divide and Conquer Radiology Report Generation (DCRRG) model, which breaks down full-text radiology reports into concise observation descriptions. This approach enables the model to capture fine-grained representations from each observation through a two-stage process: an encoding stage focusing on observation prediction tasks to learn fine-grained representations, and a decoding stage for integrating these descriptions into cohesive and comprehensive radiology reports. Experimental results on two benchmark datasets demonstrate that DCRRG achieves significant improvements across all evaluated metrics, underscoring its capability to generate semantically coherent and clinically accurate radiology reports.</abstract>
<identifier type="citekey">zhou-wang-2024-divide</identifier>
<identifier type="doi">10.18653/v1/2024.emnlp-main.433</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-main.433/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>7597</start>
<end>7610</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Divide and Conquer Radiology Report Generation via Observation Level Fine-grained Pretraining and Prompt Tuning
%A Zhou, Yuanpin
%A Wang, Huogen
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F zhou-wang-2024-divide
%X The automation of radiology report generation (RRG) holds immense potential to alleviate radiologists’ workloads and improve diagnostic accuracy. Despite advancements in image captioning and vision-language pretraining, RRG remains challenging due to the lengthy and complex nature of radiology reports. In this work, we proposes the Divide and Conquer Radiology Report Generation (DCRRG) model, which breaks down full-text radiology reports into concise observation descriptions. This approach enables the model to capture fine-grained representations from each observation through a two-stage process: an encoding stage focusing on observation prediction tasks to learn fine-grained representations, and a decoding stage for integrating these descriptions into cohesive and comprehensive radiology reports. Experimental results on two benchmark datasets demonstrate that DCRRG achieves significant improvements across all evaluated metrics, underscoring its capability to generate semantically coherent and clinically accurate radiology reports.
%R 10.18653/v1/2024.emnlp-main.433
%U https://aclanthology.org/2024.emnlp-main.433/
%U https://doi.org/10.18653/v1/2024.emnlp-main.433
%P 7597-7610
Markdown (Informal)
[Divide and Conquer Radiology Report Generation via Observation Level Fine-grained Pretraining and Prompt Tuning](https://aclanthology.org/2024.emnlp-main.433/) (Zhou & Wang, EMNLP 2024)
ACL