Anatomy guided truncated conditional diffusion model for super-resolution arterial spin labeling imaging
NeuroImage · 2026-08 · 336 · 122000
DOI: 10.1016/j.neuroimage.2026.122000 ↗Kurz gefasst
Fachartikel in der Zeitschrift NeuroImage, 2026-08. Verfasst von Yunzhi Xu und 9 weiteren Autor:innen. Beteiligte Einrichtung: College of Biomedical Engineering & Instrument Science, Zhejiang University, Hangzhou 310027, China. Hauptthemen laut MEDLINE: Brain, Cerebrovascular Circulation, Image Processing, Computer-Assisted, Perfusion Magnetic Resonance Imaging. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Institutes of Health, Key Research and Development Program of Zhejiang Province, National Institute of Biomedical Imaging and Bioengineering.
Abstract (Originalsprache)
Arterial Spin Labeling (ASL) is a non-invasive magnetic resonance imaging technique used to measure cerebral blood flow. However, ASL images typically suffer from low resolution and long acquisition times because of the low signal-to-noise ratio. Therefore, high-resolution ASL images are challenging to acquire but highly desirable. This work proposes a super-resolution method for ASL based on an anatomy guided truncated conditional diffusion model, including an anatomy guided data synthesizer, an anatomy guided truncated diffusion module, and a two-stage inference module. The proposed model was developed and validated on retrospective, prospective, and clinical datasets. Its performance was compared against both conventional and deep learning methods. The proposed model demonstrates superior performance, including 2-18% gains in SSIM and 26-50% reductions in FID on the prospectively acquired data, compared to existing methods. The results suggest that the method offers a promising approach for achieving high-resolution ASL imaging. The proposed model is available on GitHub: https://github.com/yunzxu/ATCDM.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- College of Biomedical Engineering & Instrument Science, Zhejiang University, Hangzhou 310027, China.
- School of Computing, State University of New York at Binghamton, Binghamton, NY, USA.
- Radiology, Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, MA, USA.
- Department of Radiology, Children's Hospital, Zhejiang University School of Medicine, National Clinical Research Center for Child Health, Hangzhou, China.
- College of Biomedical Engineering & Instrument Science, Zhejiang University, Hangzhou 310027, China. Electronic address: lz5bf@virginia.edu.
Förderung
- National Institutes of Health
- Key Research and Development Program of Zhejiang Province
- National Institute of Biomedical Imaging and Bioengineering
- National Institute on Aging
- National Key Research and Development Program of China Stem Cell and Translational Research
- Northern California Institute for Research and Education
- Alzheimer's Disease Neuroimaging Initiative
- University of Southern California
Zitieren
APA
Xu, Y., Zheng, J., Lin, R., Shi, L., Li, J., Dai, W., Alsop, D. C., Zhang, H., Zhao, L., & Alzheimer’s Disease Neuroimaging Initiative (2026). Anatomy guided truncated conditional diffusion model for super-resolution arterial spin labeling imaging. NeuroImage, 336, 122000. https://doi.org/10.1016/j.neuroimage.2026.122000
Vancouver
Xu Y, Zheng J, Lin R, Shi L, Li J, Dai W, et al. Anatomy guided truncated conditional diffusion model for super-resolution arterial spin labeling imaging. NeuroImage. 2026;336:122000. doi:10.1016/j.neuroimage.2026.122000
BibTeX
@article{Xu2026,
author = {Xu, Yunzhi and Zheng, Jiaxin and Lin, Ruoge and Shi, Liangchen and Li, Jiaxin and Dai, Weiying and Alsop, David C and Zhang, Hongxi and Zhao, Li and Alzheimer’s Disease Neuroimaging Initiative, Alzheimer’s Disease Neuroimaging Initiative},
title = {Anatomy guided truncated conditional diffusion model for super-resolution arterial spin labeling imaging},
journal = {NeuroImage},
year = {2026},
volume = {336},
pages = {122000},
doi = {10.1016/j.neuroimage.2026.122000}
}
EUVIMED