@inproceedings{park-etal-2020-feature,
title = "{F}eature {D}ifference {M}akes {S}ense: {A} medical image captioning model exploiting feature difference and tag information",
author = "Park, Hyeryun and
Kim, Kyungmo and
Yoon, Jooyoung and
Park, Seongkeun and
Choi, Jinwook",
editor = "Rijhwani, Shruti and
Liu, Jiangming and
Wang, Yizhong and
Dror, Rotem",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-srw.14",
doi = "10.18653/v1/2020.acl-srw.14",
pages = "95--102",
abstract = "Medical image captioning can reduce the workload of physicians and save time and expense by automatically generating reports. However, current datasets are small and limited, creating additional challenges for researchers. In this study, we propose a feature difference and tag information combined long short-term memory (LSTM) model for chest x-ray report generation. A feature vector extracted from the image conveys visual information, but its ability to describe the image is limited. Other image captioning studies exhibited improved performance by exploiting feature differences, so the proposed model also utilizes them. First, we propose a difference and tag (DiTag) model containing the difference between the patient and normal images. Then, we propose a multi-difference and tag (mDiTag) model that also contains information about low-level differences, such as contrast, texture, and localized area. Evaluation of the proposed models demonstrates that the mDiTag model provides more information to generate captions and outperforms all other models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="park-etal-2020-feature">
<titleInfo>
<title>Feature Difference Makes Sense: A medical image captioning model exploiting feature difference and tag information</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hyeryun</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyungmo</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jooyoung</namePart>
<namePart type="family">Yoon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seongkeun</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinwook</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shruti</namePart>
<namePart type="family">Rijhwani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiangming</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yizhong</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rotem</namePart>
<namePart type="family">Dror</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Medical image captioning can reduce the workload of physicians and save time and expense by automatically generating reports. However, current datasets are small and limited, creating additional challenges for researchers. In this study, we propose a feature difference and tag information combined long short-term memory (LSTM) model for chest x-ray report generation. A feature vector extracted from the image conveys visual information, but its ability to describe the image is limited. Other image captioning studies exhibited improved performance by exploiting feature differences, so the proposed model also utilizes them. First, we propose a difference and tag (DiTag) model containing the difference between the patient and normal images. Then, we propose a multi-difference and tag (mDiTag) model that also contains information about low-level differences, such as contrast, texture, and localized area. Evaluation of the proposed models demonstrates that the mDiTag model provides more information to generate captions and outperforms all other models.</abstract>
<identifier type="citekey">park-etal-2020-feature</identifier>
<identifier type="doi">10.18653/v1/2020.acl-srw.14</identifier>
<location>
<url>https://aclanthology.org/2020.acl-srw.14</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>95</start>
<end>102</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Feature Difference Makes Sense: A medical image captioning model exploiting feature difference and tag information
%A Park, Hyeryun
%A Kim, Kyungmo
%A Yoon, Jooyoung
%A Park, Seongkeun
%A Choi, Jinwook
%Y Rijhwani, Shruti
%Y Liu, Jiangming
%Y Wang, Yizhong
%Y Dror, Rotem
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F park-etal-2020-feature
%X Medical image captioning can reduce the workload of physicians and save time and expense by automatically generating reports. However, current datasets are small and limited, creating additional challenges for researchers. In this study, we propose a feature difference and tag information combined long short-term memory (LSTM) model for chest x-ray report generation. A feature vector extracted from the image conveys visual information, but its ability to describe the image is limited. Other image captioning studies exhibited improved performance by exploiting feature differences, so the proposed model also utilizes them. First, we propose a difference and tag (DiTag) model containing the difference between the patient and normal images. Then, we propose a multi-difference and tag (mDiTag) model that also contains information about low-level differences, such as contrast, texture, and localized area. Evaluation of the proposed models demonstrates that the mDiTag model provides more information to generate captions and outperforms all other models.
%R 10.18653/v1/2020.acl-srw.14
%U https://aclanthology.org/2020.acl-srw.14
%U https://doi.org/10.18653/v1/2020.acl-srw.14
%P 95-102
Markdown (Informal)
[Feature Difference Makes Sense: A medical image captioning model exploiting feature difference and tag information](https://aclanthology.org/2020.acl-srw.14) (Park et al., ACL 2020)
ACL