A CT-free deep-learning-based attenuation and scatter correction for copper-64 PET in different time-point scans.
Authors
Affiliations (7)
Affiliations (7)
- Group of Medical Radiation Engineering, Department of Energy Engineering, Sharif University of Technology, Tehran, Iran.
- Group of Medical Radiation Engineering, Department of Energy Engineering, Sharif University of Technology, Tehran, Iran. [email protected].
- Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva, Switzerland.
- Department of Nuclear Medicine, Faculty of Medicine, IKHC, Tehran University of Medical Sciences, Tehran, Iran.
- Department of Nuclear Medicine, Faculty of Medicine, IKHC, Tehran University of Medical Sciences, Tehran, Iran. [email protected].
- Department of Biomedical Physics and Engineering, Faculty of Medicine, Tehran University of Medical Sciences, Tehran, Iran. [email protected].
- Research Center for Nuclear Medicine, Shariati Hospital, Tehran University of Medical Sciences, Tehran, Iran. [email protected].
Abstract
This study aimed to develop and evaluate a deep-learning model for attenuation and scatter correction in whole-body 64Cu-based PET imaging. A swinUNETR model was implemented using the MONAI framework. Whole-body PET-nonAC and PET-CTAC image pairs were used for training, where PET-nonAC served as the input and PET-CTAC as the output. Due to the limited number of Cu-based PET/CT images, a model pre-trained on 51 Ga-PSMA PET images was fine-tuned on 15 Cu-based PET images via transfer learning. The model was trained without freezing layers, adapting learned features to the Cu-based dataset. For testing, six additional Cu-based PET images were used, representing 1-h, 12-h, and 48-h time points, with two images per group. The model performed best at the 12-h time point, with an MSE of 0.002 ± 0.0004 SUV<sup>2</sup>, PSNR of 43.14 ± 0.08 dB, and SSIM of 0.981 ± 0.002. At 48 h, accuracy slightly decreased (MSE = 0.036 ± 0.034 SUV<sup>2</sup>), but image quality remained high (PSNR = 44.49 ± 1.09 dB, SSIM = 0.981 ± 0.006). At 1 h, the model also showed strong results (MSE = 0.024 ± 0.002 SUV<sup>2</sup>, PSNR = 45.89 ± 5.23 dB, SSIM = 0.984 ± 0.005), demonstrating consistency across time points. Despite the limited size of the training dataset, the use of fine-tuning from a previously pre-trained model yielded acceptable performance. The results demonstrate that the proposed deep learning model can effectively generate PET-DLAC images that closely resemble PET-CTAC images, with only minor errors.