Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.05247 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915837581983744 |
|---|---|
| author | Beltran-Urbano, Xavier Li, Yiran Zeng, Xinglin Jobson, Katie R. Taso, Manuel Brown, Christopher A. Wolk, David A. McMillan, Corey T. Nashrallah, Ilya M. Yushkevich, Paul A. Wang, Ze Detre, John A. Dolui, Sudipto |
| author_facet | Beltran-Urbano, Xavier Li, Yiran Zeng, Xinglin Jobson, Katie R. Taso, Manuel Brown, Christopher A. Wolk, David A. McMillan, Corey T. Nashrallah, Ilya M. Yushkevich, Paul A. Wang, Ze Detre, John A. Dolui, Sudipto |
| contents | Arterial spin labeling (ASL) perfusion MRI allows direct quantification of regional cerebral blood flow (CBF) without exogenous contrast, enabling noninvasive measurements that can be repeated without constraints imposed by contrast injection. ASL is increasingly acquired in research studies and clinical MRI protocols. Building on successes in structural imaging, recent efforts have implemented deep learning based methods to improve image quality, enable automated quality control, and derive robust quantitative and predictive biomarkers with ASL derived CBF. However, progress has been limited by variable image quality, substantial inter-site, vendor and protocol differences, and limited availability of labeled datasets needed to train models that generalize across cohorts. To address these challenges, we introduce ICHOR, a self supervised pre-training approach for ASL CBF maps that learns transferable representations using 3D masked autoencoders. ICHOR is pretrained via masked image modeling using a Vision Transformer backbone and can be used as a general-purpose encoder for downstream ASL tasks. For pre-training, we curated one of the largest ASL datasets to date, comprising 11,405 ASL CBF scans from 14 studies spanning multiple sites and acquisition protocols. We evaluated the pre-trained ICHOR encoder on three downstream diagnostic classification tasks and one ASL CBF map quality prediction regression task. Across all evaluations, ICHOR outperformed existing neuroimaging self-supervised pre-training methods adapted to ASL. Pre-trained weights and code will be made publicly available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_05247 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ICHOR: A Robust Representation Learning Approach for ASL CBF Maps with Self-Supervised Masked Autoencoders Beltran-Urbano, Xavier Li, Yiran Zeng, Xinglin Jobson, Katie R. Taso, Manuel Brown, Christopher A. Wolk, David A. McMillan, Corey T. Nashrallah, Ilya M. Yushkevich, Paul A. Wang, Ze Detre, John A. Dolui, Sudipto Image and Video Processing Computer Vision and Pattern Recognition Medical Physics Arterial spin labeling (ASL) perfusion MRI allows direct quantification of regional cerebral blood flow (CBF) without exogenous contrast, enabling noninvasive measurements that can be repeated without constraints imposed by contrast injection. ASL is increasingly acquired in research studies and clinical MRI protocols. Building on successes in structural imaging, recent efforts have implemented deep learning based methods to improve image quality, enable automated quality control, and derive robust quantitative and predictive biomarkers with ASL derived CBF. However, progress has been limited by variable image quality, substantial inter-site, vendor and protocol differences, and limited availability of labeled datasets needed to train models that generalize across cohorts. To address these challenges, we introduce ICHOR, a self supervised pre-training approach for ASL CBF maps that learns transferable representations using 3D masked autoencoders. ICHOR is pretrained via masked image modeling using a Vision Transformer backbone and can be used as a general-purpose encoder for downstream ASL tasks. For pre-training, we curated one of the largest ASL datasets to date, comprising 11,405 ASL CBF scans from 14 studies spanning multiple sites and acquisition protocols. We evaluated the pre-trained ICHOR encoder on three downstream diagnostic classification tasks and one ASL CBF map quality prediction regression task. Across all evaluations, ICHOR outperformed existing neuroimaging self-supervised pre-training methods adapted to ASL. Pre-trained weights and code will be made publicly available. |
| title | ICHOR: A Robust Representation Learning Approach for ASL CBF Maps with Self-Supervised Masked Autoencoders |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Medical Physics |
| url | https://arxiv.org/abs/2603.05247 |