Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.24789 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913159416119296 |
|---|---|
| author | Wang, Yuli Jung, Hyewon Peng, Dongshen Dai, Yuwei Wu, Jing Guan, Haoyue Kato, Yoko Jiao, Zhicheng Sun, Yu Kamel, Ihab Lima, Joao Lin, Cheng Ting Bai, Harrison |
| author_facet | Wang, Yuli Jung, Hyewon Peng, Dongshen Dai, Yuwei Wu, Jing Guan, Haoyue Kato, Yoko Jiao, Zhicheng Sun, Yu Kamel, Ihab Lima, Joao Lin, Cheng Ting Bai, Harrison |
| contents | Vision Transformer (ViT) models, utilizing self-attention mechanisms, have demonstrated robust generalization capabilities across various vision tasks, including image classification. However, these models, typically pretrained on general public datasets, often lack the specialized domain knowledge necessary for medical imaging applications. In this study, we investigate the adaptation of ViT models, specifically for cardiac magnetic resonance (MR) images, using an in-house dataset. We found that pretrained ViT features do not effectively transfer to the cardiac MR domain. To overcome this limitation, we introduce an adaptation strategy that utilizes image-based self-supervised contrastive learning, demonstrating superior performance compared to traditional supervised training approaches. Moreover, our adapted ViT model exhibits strong generalization to external MR datasets such as BraTS and ADNI. Through ablation studies, we further investigate the impact of batch size and dataset scale on performance. Ultimately, our adapted model achieves classification AUC exceeding 0.75 across the four most common cardiac MR sequences. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_24789 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Self-Supervised Contrastive Learning for Cardiac MR Sequence Classification Wang, Yuli Jung, Hyewon Peng, Dongshen Dai, Yuwei Wu, Jing Guan, Haoyue Kato, Yoko Jiao, Zhicheng Sun, Yu Kamel, Ihab Lima, Joao Lin, Cheng Ting Bai, Harrison Computer Vision and Pattern Recognition Image and Video Processing Vision Transformer (ViT) models, utilizing self-attention mechanisms, have demonstrated robust generalization capabilities across various vision tasks, including image classification. However, these models, typically pretrained on general public datasets, often lack the specialized domain knowledge necessary for medical imaging applications. In this study, we investigate the adaptation of ViT models, specifically for cardiac magnetic resonance (MR) images, using an in-house dataset. We found that pretrained ViT features do not effectively transfer to the cardiac MR domain. To overcome this limitation, we introduce an adaptation strategy that utilizes image-based self-supervised contrastive learning, demonstrating superior performance compared to traditional supervised training approaches. Moreover, our adapted ViT model exhibits strong generalization to external MR datasets such as BraTS and ADNI. Through ablation studies, we further investigate the impact of batch size and dataset scale on performance. Ultimately, our adapted model achieves classification AUC exceeding 0.75 across the four most common cardiac MR sequences. |
| title | Self-Supervised Contrastive Learning for Cardiac MR Sequence Classification |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2605.24789 |