Data-efficient generalization of AI transformers for noise reduction in ultra-fast lung PET scans.
Authors
Affiliations (8)
Affiliations (8)
- Institute of Medical Robotics, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China.
- Department of Nuclear Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
- Institute for Medical Imaging Technology, Ruijin Hospital, Shanghai Jiao Tong University, Shanghai, China.
- Department of Nuclear Medicine, University of Bern, Bern, Switzerland.
- Department of Informatics, Technical University of Munich, Munich, Germany.
- Department of Nuclear Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China. [email protected].
- Institute for Medical Imaging Technology, Ruijin Hospital, Shanghai Jiao Tong University, Shanghai, China. [email protected].
- Institute of Medical Robotics, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China. [email protected].
Abstract
Respiratory motion during PET acquisition may produce lesion blurring. Ultra-fast 20-second breath-hold (U2BH) PET reduces respiratory motion artifacts, but the shortened scanning time increases statistical noise and may affect diagnostic quality. This study aims to denoise the U2BH PET images using a deep learning (DL)-based method. The study was conducted on two datasets collected from five scanners where the first dataset included 1272 retrospectively collected full-time PET data while the second dataset contained 46 prospectively collected U2BH and the corresponding full-time PET/CT images. A robust and data-efficient DL method called mask vision transformer (Mask-ViT) was proposed which, after fine-tuned on a limited number of training data from a target scanner, was directly applied to unseen testing data from new scanners. The performance of Mask-ViT was compared with state-of-the-art DL methods including U-Net and C-Gan taking the full-time PET images as the reference. Statistical analysis on image quality metrics were carried out with Wilcoxon signed-rank test. For clinical evaluation, two readers scored image quality on a 5-point scale (5 = excellent) and provided a binary assessment for diagnostic quality evaluation. The U2BH PET images denoised by Mask-ViT showed statistically significant improvement over U-Net and C-Gan on image quality metrics (p < 0.05). For clinical evaluation, Mask-ViT exhibited a lesion detection accuracy of 91.3%, 90.4% and 91.7%, when it was evaluated on three different scanners. Mask-ViT can effectively enhance the quality of the U2BH PET images in a data-efficient generalization setup. The denoised images meet clinical diagnostic requirements of lesion detectability.