@inproceedings{he-etal-2021-towards,
title = "Towards Visual Question Answering on Pathology Images",
author = "He, Xuehai and
Cai, Zhuo and
Wei, Wenlan and
Zhang, Yichen and
Mou, Luntian and
Xing, Eric and
Xie, Pengtao",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-short.90",
doi = "10.18653/v1/2021.acl-short.90",
pages = "708--718",
abstract = "Pathology imaging is broadly used for identifying the causes and effects of diseases or injuries. Given a pathology image, being able to answer questions about the clinical findings contained in the image is very important for medical decision making. In this paper, we aim to develop a pathological visual question answering framework to analyze pathology images and answer medical questions related to these images. To build such a framework, we create PathVQA, a VQA dataset with 32,795 questions asked from 4,998 pathology images. We also propose a three-level optimization framework which performs self-supervised pretraining and VQA finetuning end-to-end to learn powerful visual and textual representations jointly and automatically identifies and excludes noisy self-supervised examples from pretraining. We perform experiments on our created PathVQA dataset and the results demonstrate the effectiveness of our proposed methods. The datasets and code are available at \url{https://github.com/UCSD-AI4H/PathVQA}",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="he-etal-2021-towards">
<titleInfo>
<title>Towards Visual Question Answering on Pathology Images</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xuehai</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhuo</namePart>
<namePart type="family">Cai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenlan</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luntian</namePart>
<namePart type="family">Mou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Xing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pengtao</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</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>Pathology imaging is broadly used for identifying the causes and effects of diseases or injuries. Given a pathology image, being able to answer questions about the clinical findings contained in the image is very important for medical decision making. In this paper, we aim to develop a pathological visual question answering framework to analyze pathology images and answer medical questions related to these images. To build such a framework, we create PathVQA, a VQA dataset with 32,795 questions asked from 4,998 pathology images. We also propose a three-level optimization framework which performs self-supervised pretraining and VQA finetuning end-to-end to learn powerful visual and textual representations jointly and automatically identifies and excludes noisy self-supervised examples from pretraining. We perform experiments on our created PathVQA dataset and the results demonstrate the effectiveness of our proposed methods. The datasets and code are available at https://github.com/UCSD-AI4H/PathVQA</abstract>
<identifier type="citekey">he-etal-2021-towards</identifier>
<identifier type="doi">10.18653/v1/2021.acl-short.90</identifier>
<location>
<url>https://aclanthology.org/2021.acl-short.90</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>708</start>
<end>718</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Visual Question Answering on Pathology Images
%A He, Xuehai
%A Cai, Zhuo
%A Wei, Wenlan
%A Zhang, Yichen
%A Mou, Luntian
%A Xing, Eric
%A Xie, Pengtao
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F he-etal-2021-towards
%X Pathology imaging is broadly used for identifying the causes and effects of diseases or injuries. Given a pathology image, being able to answer questions about the clinical findings contained in the image is very important for medical decision making. In this paper, we aim to develop a pathological visual question answering framework to analyze pathology images and answer medical questions related to these images. To build such a framework, we create PathVQA, a VQA dataset with 32,795 questions asked from 4,998 pathology images. We also propose a three-level optimization framework which performs self-supervised pretraining and VQA finetuning end-to-end to learn powerful visual and textual representations jointly and automatically identifies and excludes noisy self-supervised examples from pretraining. We perform experiments on our created PathVQA dataset and the results demonstrate the effectiveness of our proposed methods. The datasets and code are available at https://github.com/UCSD-AI4H/PathVQA
%R 10.18653/v1/2021.acl-short.90
%U https://aclanthology.org/2021.acl-short.90
%U https://doi.org/10.18653/v1/2021.acl-short.90
%P 708-718
Markdown (Informal)
[Towards Visual Question Answering on Pathology Images](https://aclanthology.org/2021.acl-short.90) (He et al., ACL-IJCNLP 2021)
ACL
- Xuehai He, Zhuo Cai, Wenlan Wei, Yichen Zhang, Luntian Mou, Eric Xing, and Pengtao Xie. 2021. Towards Visual Question Answering on Pathology Images. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 708–718, Online. Association for Computational Linguistics.