@inproceedings{yan-etal-2024-multi,
title = "Multi-modal Concept Alignment Pre-training for Generative Medical Visual Question Answering",
author = "Yan, Quan and
Duan, Junwen and
Wang, Jianxin",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.319",
pages = "5378--5389",
abstract = "Medical Visual Question Answering (Med-VQA) seeks to accurately respond to queries regarding medical images, a task particularly challenging for open-ended questions. This study unveils the Multi-modal Concept Alignment Pre-training (MMCAP) approach for generative Med-VQA, leveraging a knowledge graph sourced from medical image-caption datasets and the Unified Medical Language System. MMCAP advances the fusion of visual and textual medical knowledge via a graph attention network and a transformer decoder. Additionally, it incorporates a Type Conditional Prompt in the fine-tuning phase, markedly boosting the accuracy and relevance of answers to open-ended questions. Our tests on benchmark datasets illustrate MMCAP{'}s superiority over existing methods, demonstrating its high efficiency in data-limited settings and effective knowledge-image alignment capability.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yan-etal-2024-multi">
<titleInfo>
<title>Multi-modal Concept Alignment Pre-training for Generative Medical Visual Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Quan</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junwen</namePart>
<namePart type="family">Duan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianxin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Medical Visual Question Answering (Med-VQA) seeks to accurately respond to queries regarding medical images, a task particularly challenging for open-ended questions. This study unveils the Multi-modal Concept Alignment Pre-training (MMCAP) approach for generative Med-VQA, leveraging a knowledge graph sourced from medical image-caption datasets and the Unified Medical Language System. MMCAP advances the fusion of visual and textual medical knowledge via a graph attention network and a transformer decoder. Additionally, it incorporates a Type Conditional Prompt in the fine-tuning phase, markedly boosting the accuracy and relevance of answers to open-ended questions. Our tests on benchmark datasets illustrate MMCAP’s superiority over existing methods, demonstrating its high efficiency in data-limited settings and effective knowledge-image alignment capability.</abstract>
<identifier type="citekey">yan-etal-2024-multi</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.319</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>5378</start>
<end>5389</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-modal Concept Alignment Pre-training for Generative Medical Visual Question Answering
%A Yan, Quan
%A Duan, Junwen
%A Wang, Jianxin
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F yan-etal-2024-multi
%X Medical Visual Question Answering (Med-VQA) seeks to accurately respond to queries regarding medical images, a task particularly challenging for open-ended questions. This study unveils the Multi-modal Concept Alignment Pre-training (MMCAP) approach for generative Med-VQA, leveraging a knowledge graph sourced from medical image-caption datasets and the Unified Medical Language System. MMCAP advances the fusion of visual and textual medical knowledge via a graph attention network and a transformer decoder. Additionally, it incorporates a Type Conditional Prompt in the fine-tuning phase, markedly boosting the accuracy and relevance of answers to open-ended questions. Our tests on benchmark datasets illustrate MMCAP’s superiority over existing methods, demonstrating its high efficiency in data-limited settings and effective knowledge-image alignment capability.
%U https://aclanthology.org/2024.findings-acl.319
%P 5378-5389
Markdown (Informal)
[Multi-modal Concept Alignment Pre-training for Generative Medical Visual Question Answering](https://aclanthology.org/2024.findings-acl.319) (Yan et al., Findings 2024)
ACL