A Meta-Learning Approach for Classifying Multimodal Retinal Images of Retinal Vein Occlusion With Limited Data
Translational Vision Science & Technology · 2024
DOI: 10.1167/tvst.13.9.22 ↗Kurz gefasst
Fachartikel in der Zeitschrift Translational Vision Science & Technology, 2024. Verfasst von Danba Jiachu und 12 weiteren Autor:innen. Beteiligte Einrichtung: Kham Eye Centre, Kandze Prefecture People's Hospital, Kangding, China. Hauptthemen laut MEDLINE: Retinal Vein Occlusion, Deep Learning, Algorithms. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Purpose
To propose and validate a meta-learning approach for detecting retinal vein occlusion (RVO) from multimodal images with only a few samples.
Methods
In this cross-sectional study, we formulate the problem as meta-learning. The meta-training dataset consists of 1254 color fundus (CF) images from 39 different fundus diseases. Two meta-testing datasets include a public domain dataset and an independent dataset from Kandze Prefecture People's Hospital. The proposed meta-learning models comprise two modules: the feature extraction networks and the prototypical networks (PNs). We use two deep learning models (the ResNet and the Contrastive Language-Image Pre-Training networks [CLIP]) for feature extraction. We evaluate the performance of the algorithms using accuracy, area under the receiver operating characteristic curve (AUCROC), F1-score, and recall.
Results
CLIP-based PNs outperform across all meta-testing datasets. For the public APTOS dataset, meta-learning algorithms achieve good results with an accuracy of 86.06% and an AUCROC of 0.87 with only 16 training images. In the hospital datasets, meta-learning algorithms show excellent diagnostic capability for detecting RVO with a very low number of shots (AUCROC above 0.99 for n = 4, 8, and 16, respectively). Notably, even though the meta-training dataset does not include fluorescein angiography (FA) images, meta-learning algorithms also have excellent diagnostic capability for detecting RVO from images with a different modality (AUCROC above 0.93 for n = 4, 8, and 16, respectively).
Conclusions
The proposed meta-learning models excel in detecting RVO, not only on CF images but also on FA images from a different imaging modality. Translational Relevance: The proposed meta-learning models could be useful in automatically detecting RVO on CF and FA images.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Kham Eye Centre, Kandze Prefecture People's Hospital, Kangding, China.
- Joint Shantou International Eye Center of Shantou University and the Chinese University of Hong Kong, Shantou University Medical College, Shantou, Guangdong, China.
- Department of Ophthalmology, Xinhua Hospital Affiliated to Shanghai Jiaotong University School of Medicine, Shanghai, China.
- Discipline Inspection & Supervision Office, Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China.
Zitieren
APA
Jiachu, D., Luo, L., Xie, M., Xie, X., Guo, J., Ye, H., Cai, K., Zhou, L., Song, G., Jiang, F., Huang, D., Zhang, M., & Zheng, C. (2024). A Meta-Learning Approach for Classifying Multimodal Retinal Images of Retinal Vein Occlusion With Limited Data. Translational Vision Science & Technology. https://doi.org/10.1167/tvst.13.9.22
Vancouver
Jiachu D, Luo L, Xie M, Xie X, Guo J, Ye H, et al. A Meta-Learning Approach for Classifying Multimodal Retinal Images of Retinal Vein Occlusion With Limited Data. Translational Vision Science & Technology. 2024. doi:10.1167/tvst.13.9.22
BibTeX
@article{Jiachu2024,
author = {Jiachu, Danba and Luo, Li and Xie, Meng and Xie, Xiaoling and Guo, Jinming and Ye, Hehua and Cai, Kebo and Zhou, Lingling and Song, Gang and Jiang, Feng and Huang, Danqing and Zhang, Mingzhi and Zheng, Ce},
title = {A Meta-Learning Approach for Classifying Multimodal Retinal Images of Retinal Vein Occlusion With Limited Data},
journal = {Translational Vision Science & Technology},
year = {2024},
doi = {10.1167/tvst.13.9.22}
}
EUVIMED