0 47

Cited 0 times in

EVIDENCE-EMPOWERED TRANSFER LEARNING FOR ALZHEIMER'S DISEASE

DC Field Value Language
dc.contributor.author손범석-
dc.contributor.author최윤성-
dc.date.accessioned2024-05-30T06:52:10Z-
dc.date.available2024-05-30T06:52:10Z-
dc.date.issued2023-09-
dc.identifier.urihttps://ir.ymlib.yonsei.ac.kr/handle/22282913/199404-
dc.description.abstractTransfer learning has been widely utilized to mitigate the data scarcity problem in the field of Alzheimer's disease (AD). Conventional transfer learning relies on re-using models trained on AD-irrelevant tasks such as natural image classification. However, it often leads to negative transfer due to the discrepancy between the non-medical source and target medical domains. To address this, we present evidence-empowered transfer learning for AD diagnosis. Unlike conventional approaches, we leverage an AD-relevant auxiliary task, namely morphological change prediction, without requiring additional MRI data. In this auxiliary task, the diagnosis model learns the evidential and transferable knowledge from morphological features in MRI scans. Experimental results demonstrate that our framework is not only effective in improving detection performance regardless of model capacity, but also more data-efficient and faithful.-
dc.description.statementOfResponsibilityrestriction-
dc.relation.isPartOf2023 IEEE 20TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING, ISBI-
dc.rightsCC BY-NC-ND 2.0 KR-
dc.titleEVIDENCE-EMPOWERED TRANSFER LEARNING FOR ALZHEIMER'S DISEASE-
dc.typeArticle-
dc.contributor.collegeCollege of Medicine (의과대학)-
dc.contributor.departmentDept. of Radiology (영상의학교실)-
dc.contributor.googleauthorKai Tzu-iunn Ong-
dc.contributor.googleauthorHana Kim-
dc.contributor.googleauthorMinjin Kim-
dc.contributor.googleauthorJinseong Jang-
dc.contributor.googleauthorBeomseok Sohn-
dc.contributor.googleauthorYoon Seong Choi-
dc.contributor.googleauthorDosik Hwang-
dc.contributor.googleauthorSeong Jae Hwang-
dc.contributor.googleauthorJinyoung Yeo-
dc.identifier.doi10.1109/ISBI53787.2023.10230842-
dc.contributor.localIdA04960-
dc.contributor.localIdA04137-
dc.identifier.urlhttps://ieeexplore-ieee-org-ssl.access.yonsei.ac.kr/document/10230842-
dc.contributor.alternativeNameSohn, Beomseok-
dc.contributor.affiliatedAuthor손범석-
dc.contributor.affiliatedAuthor최윤성-
dc.identifier.bibliographicCitation2023 IEEE 20TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING, ISBI, , 2023-09-
Appears in Collections:
1. College of Medicine (의과대학) > Dept. of Radiology (영상의학교실) > 1. Journal Papers

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.