MAESIL: Masked Autoencoder for Enhanced Self-supervised Medical Image Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918422970892288 |
|---|---|
| author | Kim, Kyeonghun Jung, Hyeonseok Han, Youngung Lim, Junsu Jean, YeonJu Park, Seongbin Choi, Eunseob Go, Hyunsu Ju, SeoYoung Park, Seohyoung Kim, Gyeongmin Kwon, MinJu Yuh, KyungSeok Kim, Soo Yong Liao, Ken Ying-Kai Kim, Nam-Joon Lee, Hyuk-Jae |
| author_facet | Kim, Kyeonghun Jung, Hyeonseok Han, Youngung Lim, Junsu Jean, YeonJu Park, Seongbin Choi, Eunseob Go, Hyunsu Ju, SeoYoung Park, Seohyoung Kim, Gyeongmin Kwon, MinJu Yuh, KyungSeok Kim, Soo Yong Liao, Ken Ying-Kai Kim, Nam-Joon Lee, Hyuk-Jae |
| contents | Training deep learning models for three-dimensional (3D) medical imaging, such as Computed Tomography (CT), is fundamentally challenged by the scarcity of labeled data. While pre-training on natural images is common, it results in a significant domain shift, limiting performance. Self-Supervised Learning (SSL) on unlabeled medical data has emerged as a powerful solution, but prominent frameworks often fail to exploit the inherent 3D nature of CT scans. These methods typically process 3D scans as a collection of independent 2D slices, an approach that fundamentally discards critical axial coherence and the 3D structural context. To address this limitation, we propose the autoencoder for enhanced self-supervised medical image learning(MAESIL), a novel self-supervised learning framework designed to capture 3D structural information efficiently. The core innovation is the 'superpatch', a 3D chunk-based input unit that balances 3D context preservation with computational efficiency. Our framework partitions the volume into superpatches and employs a 3D masked autoencoder strategy with a dual-masking strategy to learn comprehensive spatial representations. We validated our approach on three diverse large-scale public CT datasets. Our experimental results show that MAESIL demonstrates significant improvements over existing methods such as AE, VAE and VQ-VAE in key reconstruction metrics such as PSNR and SSIM. This establishes MAESIL as a robust and practical pre-training solution for 3D medical imaging tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_00514 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MAESIL: Masked Autoencoder for Enhanced Self-supervised Medical Image Learning Kim, Kyeonghun Jung, Hyeonseok Han, Youngung Lim, Junsu Jean, YeonJu Park, Seongbin Choi, Eunseob Go, Hyunsu Ju, SeoYoung Park, Seohyoung Kim, Gyeongmin Kwon, MinJu Yuh, KyungSeok Kim, Soo Yong Liao, Ken Ying-Kai Kim, Nam-Joon Lee, Hyuk-Jae Computer Vision and Pattern Recognition Artificial Intelligence Training deep learning models for three-dimensional (3D) medical imaging, such as Computed Tomography (CT), is fundamentally challenged by the scarcity of labeled data. While pre-training on natural images is common, it results in a significant domain shift, limiting performance. Self-Supervised Learning (SSL) on unlabeled medical data has emerged as a powerful solution, but prominent frameworks often fail to exploit the inherent 3D nature of CT scans. These methods typically process 3D scans as a collection of independent 2D slices, an approach that fundamentally discards critical axial coherence and the 3D structural context. To address this limitation, we propose the autoencoder for enhanced self-supervised medical image learning(MAESIL), a novel self-supervised learning framework designed to capture 3D structural information efficiently. The core innovation is the 'superpatch', a 3D chunk-based input unit that balances 3D context preservation with computational efficiency. Our framework partitions the volume into superpatches and employs a 3D masked autoencoder strategy with a dual-masking strategy to learn comprehensive spatial representations. We validated our approach on three diverse large-scale public CT datasets. Our experimental results show that MAESIL demonstrates significant improvements over existing methods such as AE, VAE and VQ-VAE in key reconstruction metrics such as PSNR and SSIM. This establishes MAESIL as a robust and practical pre-training solution for 3D medical imaging tasks. |
| title | MAESIL: Masked Autoencoder for Enhanced Self-supervised Medical Image Learning |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2604.00514 |