biostudies-literatureShou QNIBIB NIH HHSNINDS NIH HHS803-818https://www.ebi.ac.uk/biostudies/studies/S-EPMC10841192biostudies-literatureUnknown91(2)<h4>Purpose</h4>To present a Swin Transformer-based deep learning (DL) model (SwinIR) for denoising single-delay and multi-delay 3D arterial spin labeling (ASL) and compare its performance with convolutional neural network (CNN) and other Transformer-based methods.<h4>Methods</h4>SwinIR and CNN-based spatial denoising models were developed for single-delay ASL. The models were trained on 66 subjects (119 scans) and tested on 39 subjects (44 scans) from three different vendors. Spatiotemporal denoising models were developed using another dataset (6 subjects, 10 scans) of multi-delay ASL. A range of input conditions was tested for denoising single and multi-delay ASL, respectively. The performance was evaluated using similarity metrics, spatial SNR and quantification accuracy of cerebral bloMagnetic resonance in medicineTransformer-based deep learning denoising of single and multi-delay 3D arterial spin labeling.PMC10841192R01 EB028297UF1 NS100588U24 NS100591U01 NS100614R01 NS114382UF1 NS100614R01 EB032169Shao XShou QJann KZhao CKim HLu HWang DJJHelmer KGfalseTransformer-based deep learning denoising of single and multi-delay 3D arterial spin labeling.<h4>Purpose</h4>To present a Swin Transformer-based deep learning (DL) model (SwinIR) for denoising single-delay and multi-delay 3D arterial spin labeling (ASL) and compare its performance with convolutional neural network (CNN) and other Transformer-based methods.<h4>Methods</h4>SwinIR and CNN-based spatial denoising models were developed for single-delay ASL. The models were trained on 66 subjects (119 scans) and tested on 39 subjects (44 scans) from three different vendors. Spatiotemporal denoising models were developed using another dataset (6 subjects, 10 scans) of multi-delay ASL. A range of input conditions was tested for denoising single and multi-delay ASL, respectively. The performance was evaluated using similarity metrics, spatial SNR and quantification accuracy of cerebral blo2024-01-01T00:00:00Z2024 Feb2025-04-04T22:07:53.218Z2025-04-04T22:07:53.218ZS-EPMC108411923784904810.1002/mrm.29887