@inproceedings{wang-etal-2023-fine,
title = "Fine-grained Medical Vision-Language Representation Learning for Radiology Report Generation",
author = "Wang, Siyuan and
Peng, Bo and
Liu, Yichao and
Peng, Qi",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.989",
doi = "10.18653/v1/2023.emnlp-main.989",
pages = "15949--15956",
abstract = "Given the input radiology images, the objective of radiology report generation is to produce accurate and comprehensive medical reports, which typically include multiple descriptive clinical sentences associated with different phenotypes. Most existing works have relied on a pre-trained vision encoder to extract the visual representations of the images. In this study, we propose a phenotype-driven medical vision-language representation learning framework to efficiently bridge the gap between visual and textual modalities for improved text-oriented generation. In contrast to conventional methods which learn medical vision-language representations by contrasting images with entire reports, our approach learns more fine-grained representations by contrasting images with each sentence within the reports. The learned fine-grained representations can be used to improve radiology report generation. The experiments on two widely-used datasets MIMIC-CXR and IU X-ray demonstrate that our method can achieve promising performances and substantially outperform the conventional vision-language representation learning methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2023-fine">
<titleInfo>
<title>Fine-grained Medical Vision-Language Representation Learning for Radiology Report Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Siyuan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Given the input radiology images, the objective of radiology report generation is to produce accurate and comprehensive medical reports, which typically include multiple descriptive clinical sentences associated with different phenotypes. Most existing works have relied on a pre-trained vision encoder to extract the visual representations of the images. In this study, we propose a phenotype-driven medical vision-language representation learning framework to efficiently bridge the gap between visual and textual modalities for improved text-oriented generation. In contrast to conventional methods which learn medical vision-language representations by contrasting images with entire reports, our approach learns more fine-grained representations by contrasting images with each sentence within the reports. The learned fine-grained representations can be used to improve radiology report generation. The experiments on two widely-used datasets MIMIC-CXR and IU X-ray demonstrate that our method can achieve promising performances and substantially outperform the conventional vision-language representation learning methods.</abstract>
<identifier type="citekey">wang-etal-2023-fine</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.989</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.989</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>15949</start>
<end>15956</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fine-grained Medical Vision-Language Representation Learning for Radiology Report Generation
%A Wang, Siyuan
%A Peng, Bo
%A Liu, Yichao
%A Peng, Qi
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F wang-etal-2023-fine
%X Given the input radiology images, the objective of radiology report generation is to produce accurate and comprehensive medical reports, which typically include multiple descriptive clinical sentences associated with different phenotypes. Most existing works have relied on a pre-trained vision encoder to extract the visual representations of the images. In this study, we propose a phenotype-driven medical vision-language representation learning framework to efficiently bridge the gap between visual and textual modalities for improved text-oriented generation. In contrast to conventional methods which learn medical vision-language representations by contrasting images with entire reports, our approach learns more fine-grained representations by contrasting images with each sentence within the reports. The learned fine-grained representations can be used to improve radiology report generation. The experiments on two widely-used datasets MIMIC-CXR and IU X-ray demonstrate that our method can achieve promising performances and substantially outperform the conventional vision-language representation learning methods.
%R 10.18653/v1/2023.emnlp-main.989
%U https://aclanthology.org/2023.emnlp-main.989
%U https://doi.org/10.18653/v1/2023.emnlp-main.989
%P 15949-15956
Markdown (Informal)
[Fine-grained Medical Vision-Language Representation Learning for Radiology Report Generation](https://aclanthology.org/2023.emnlp-main.989) (Wang et al., EMNLP 2023)
ACL