@inproceedings{nguyen-etal-2021-automated,
title = "Automated Generation of Accurate {\&} Fluent Medical {X}-ray Reports",
author = "Nguyen, Hoang and
Nie, Dong and
Badamdorj, Taivanbat and
Liu, Yujie and
Zhu, Yingying and
Truong, Jason and
Cheng, Li",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.288",
doi = "10.18653/v1/2021.emnlp-main.288",
pages = "3552--3569",
abstract = "Our paper aims to automate the generation of medical reports from chest X-ray image inputs, a critical yet time-consuming task for radiologists. Existing medical report generation efforts emphasize producing human-readable reports, yet the generated text may not be well aligned to the clinical facts. Our generated medical reports, on the other hand, are fluent and, more importantly, clinically accurate. This is achieved by our fully differentiable and end-to-end paradigm that contains three complementary modules: taking the chest X-ray images and clinical history document of patients as inputs, our classification module produces an internal checklist of disease-related topics, referred to as enriched disease embedding; the embedding representation is then passed to our transformer-based generator, to produce the medical report; meanwhile, our generator also creates a weighted embedding representation, which is fed to our interpreter to ensure consistency with respect to disease-related topics. Empirical evaluations demonstrate very promising results achieved by our approach on commonly-used metrics concerning language fluency and clinical accuracy. Moreover, noticeable performance gains are consistently observed when additional input information is available, such as the clinical document and extra scans from different views.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-etal-2021-automated">
<titleInfo>
<title>Automated Generation of Accurate & Fluent Medical X-ray Reports</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hoang</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dong</namePart>
<namePart type="family">Nie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taivanbat</namePart>
<namePart type="family">Badamdorj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yujie</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingying</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="family">Truong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Our paper aims to automate the generation of medical reports from chest X-ray image inputs, a critical yet time-consuming task for radiologists. Existing medical report generation efforts emphasize producing human-readable reports, yet the generated text may not be well aligned to the clinical facts. Our generated medical reports, on the other hand, are fluent and, more importantly, clinically accurate. This is achieved by our fully differentiable and end-to-end paradigm that contains three complementary modules: taking the chest X-ray images and clinical history document of patients as inputs, our classification module produces an internal checklist of disease-related topics, referred to as enriched disease embedding; the embedding representation is then passed to our transformer-based generator, to produce the medical report; meanwhile, our generator also creates a weighted embedding representation, which is fed to our interpreter to ensure consistency with respect to disease-related topics. Empirical evaluations demonstrate very promising results achieved by our approach on commonly-used metrics concerning language fluency and clinical accuracy. Moreover, noticeable performance gains are consistently observed when additional input information is available, such as the clinical document and extra scans from different views.</abstract>
<identifier type="citekey">nguyen-etal-2021-automated</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.288</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.288</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>3552</start>
<end>3569</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automated Generation of Accurate & Fluent Medical X-ray Reports
%A Nguyen, Hoang
%A Nie, Dong
%A Badamdorj, Taivanbat
%A Liu, Yujie
%A Zhu, Yingying
%A Truong, Jason
%A Cheng, Li
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F nguyen-etal-2021-automated
%X Our paper aims to automate the generation of medical reports from chest X-ray image inputs, a critical yet time-consuming task for radiologists. Existing medical report generation efforts emphasize producing human-readable reports, yet the generated text may not be well aligned to the clinical facts. Our generated medical reports, on the other hand, are fluent and, more importantly, clinically accurate. This is achieved by our fully differentiable and end-to-end paradigm that contains three complementary modules: taking the chest X-ray images and clinical history document of patients as inputs, our classification module produces an internal checklist of disease-related topics, referred to as enriched disease embedding; the embedding representation is then passed to our transformer-based generator, to produce the medical report; meanwhile, our generator also creates a weighted embedding representation, which is fed to our interpreter to ensure consistency with respect to disease-related topics. Empirical evaluations demonstrate very promising results achieved by our approach on commonly-used metrics concerning language fluency and clinical accuracy. Moreover, noticeable performance gains are consistently observed when additional input information is available, such as the clinical document and extra scans from different views.
%R 10.18653/v1/2021.emnlp-main.288
%U https://aclanthology.org/2021.emnlp-main.288
%U https://doi.org/10.18653/v1/2021.emnlp-main.288
%P 3552-3569
Markdown (Informal)
[Automated Generation of Accurate & Fluent Medical X-ray Reports](https://aclanthology.org/2021.emnlp-main.288) (Nguyen et al., EMNLP 2021)
ACL
- Hoang Nguyen, Dong Nie, Taivanbat Badamdorj, Yujie Liu, Yingying Zhu, Jason Truong, and Li Cheng. 2021. Automated Generation of Accurate & Fluent Medical X-ray Reports. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 3552–3569, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.