Quantification of left ventricular mass in multiple views of echocardiograms using model-agnostic meta learning in a few-shot setting
As a result, the proposed MAML methods demonstrated comparable performance using mean distance error, mean angle error, successful distance error and spatial angular similarity in a few-shot setting compared to models trained with larger labeled datasets for each view of the echocardiogram.
Authors
- Yisak Kim (ORCID: https://orcid.org/0000-0002-5420-1436)
- Yeong Hyeon Kim
- Woohyun Park (ORCID: https://orcid.org/0000-0002-1799-3104)
- Jiyoon Won (ORCID: https://orcid.org/0000-0002-4759-3865)
- Seola Kim
- Dongheon Lee (ORCID: https://orcid.org/0000-0002-3121-7099)
- Dong-Hoon Kim (ORCID: https://orcid.org/0000-0002-8204-8328)
- Jin Young Youm
Institutions
- Seoul National University (KR)
- Chungnam National University (KR)
- Dong-Eui University (KR)
- Asan Medical Center (KR)
- Seoul National University Hospital (KR)
- Nambu University (KR)
- Chung-Ang University Hospital (KR)
- Sungkyunkwan University (KR)
Publication Details
- Journal
- PeerJ Computer Science
- Published
- 2025-09-16
- DOI
- https://doi.org/10.7717/peerj-cs.3161
- Primary Topic
- Cardiovascular Function and Risk Factors
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Chungnam National University
- Korea Human Resource Development Institute for Health and Welfare
- Chungnam National University Hospital
- Division of Human Resource Development