@inproceedings{you-etal-2022-jpg,
title = "{JPG} - Jointly Learn to Align: Automated Disease Prediction and Radiology Report Generation",
author = "You, Jingyi and
Li, Dongyuan and
Okumura, Manabu and
Suzuki, Kenji",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.523",
pages = "5989--6001",
abstract = "Automated radiology report generation aims to generate paragraphs that describe fine-grained visual differences among cases, especially those between the normal and the diseased. Existing methods seldom consider the cross-modal alignment between textual and visual features and tend to ignore disease tags as an auxiliary for report generation. To bridge the gap between textual and visual information, in this study, we propose a {``}Jointly learning framework for automated disease Prediction and radiology report Generation (JPG){''} to improve the quality of reports through the interaction between the main task (report generation) and two auxiliary tasks (feature alignment and disease prediction). The feature alignment and disease prediction help the model learn text-correlated visual features and record diseases as keywords so that it can output high-quality reports. Besides, the improved reports in turn provide additional harder samples for feature alignment and disease prediction to learn more precise visual and textual representations and improve prediction accuracy. All components are jointly trained in a manner that helps improve them iteratively and progressively. Experimental results demonstrate the effectiveness of JPG on the most commonly used IU X-RAY dataset, showing its superior performance over multiple state-of-the-art image captioning and medical report generation methods with regard to BLEU, METEOR, and ROUGE metrics.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="you-etal-2022-jpg">
<titleInfo>
<title>JPG - Jointly Learn to Align: Automated Disease Prediction and Radiology Report Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jingyi</namePart>
<namePart type="family">You</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongyuan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manabu</namePart>
<namePart type="family">Okumura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kenji</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automated radiology report generation aims to generate paragraphs that describe fine-grained visual differences among cases, especially those between the normal and the diseased. Existing methods seldom consider the cross-modal alignment between textual and visual features and tend to ignore disease tags as an auxiliary for report generation. To bridge the gap between textual and visual information, in this study, we propose a “Jointly learning framework for automated disease Prediction and radiology report Generation (JPG)” to improve the quality of reports through the interaction between the main task (report generation) and two auxiliary tasks (feature alignment and disease prediction). The feature alignment and disease prediction help the model learn text-correlated visual features and record diseases as keywords so that it can output high-quality reports. Besides, the improved reports in turn provide additional harder samples for feature alignment and disease prediction to learn more precise visual and textual representations and improve prediction accuracy. All components are jointly trained in a manner that helps improve them iteratively and progressively. Experimental results demonstrate the effectiveness of JPG on the most commonly used IU X-RAY dataset, showing its superior performance over multiple state-of-the-art image captioning and medical report generation methods with regard to BLEU, METEOR, and ROUGE metrics.</abstract>
<identifier type="citekey">you-etal-2022-jpg</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.523</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>5989</start>
<end>6001</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T JPG - Jointly Learn to Align: Automated Disease Prediction and Radiology Report Generation
%A You, Jingyi
%A Li, Dongyuan
%A Okumura, Manabu
%A Suzuki, Kenji
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F you-etal-2022-jpg
%X Automated radiology report generation aims to generate paragraphs that describe fine-grained visual differences among cases, especially those between the normal and the diseased. Existing methods seldom consider the cross-modal alignment between textual and visual features and tend to ignore disease tags as an auxiliary for report generation. To bridge the gap between textual and visual information, in this study, we propose a “Jointly learning framework for automated disease Prediction and radiology report Generation (JPG)” to improve the quality of reports through the interaction between the main task (report generation) and two auxiliary tasks (feature alignment and disease prediction). The feature alignment and disease prediction help the model learn text-correlated visual features and record diseases as keywords so that it can output high-quality reports. Besides, the improved reports in turn provide additional harder samples for feature alignment and disease prediction to learn more precise visual and textual representations and improve prediction accuracy. All components are jointly trained in a manner that helps improve them iteratively and progressively. Experimental results demonstrate the effectiveness of JPG on the most commonly used IU X-RAY dataset, showing its superior performance over multiple state-of-the-art image captioning and medical report generation methods with regard to BLEU, METEOR, and ROUGE metrics.
%U https://aclanthology.org/2022.coling-1.523
%P 5989-6001
Markdown (Informal)
[JPG - Jointly Learn to Align: Automated Disease Prediction and Radiology Report Generation](https://aclanthology.org/2022.coling-1.523) (You et al., COLING 2022)
ACL