LAUSR

PURPOSE Dual respiratory-cardiac gating reduces respiratory and cardiac motion blur in myocardial perfusion (MP) SPECT. However, image noise is increased as detected counts are reduced in each dual gate (DG). We aim to develop a denoising method for dual gating MP-SPECT images using a 3D conditional generative adversarial network (cGAN). METHODS Twenty XCAT phantoms with various 99m Tc-sestamibi distributions, defect characteristics, body and organ sizes were used in the simulation, modeling 6 respiratory and 8 cardiac gates, i.e., 48 DGs for OS-EM reconstruction. Twenty clinical 99m Tc-sestamibi SPECT/CT datasets were re-binned into 7 respiratory gates and 8 cardiac gates, i.e., 56 DGs for ML-EM reconstruction. We evaluated the use of: (i) phantoms' own datasets (PD) or other phantoms' datasets (CD) for training; (ii) the cardiac gate (CG) or the static (NG) data as the training references for cGAN; and (iii) cGAN as compared to conventional 3D post-reconstruction filtering, cardiac gating methods and convolutional neural network (CNN). Normalized mean squared error, noise as assessed by normalized standard deviation, spatial blurring measured as the FWHM of left ventricular (LV) wall, ejection fraction, joint correlation histogram and defect size were analyzed as metrics of image quality. RESULTS Training using patients' own dataset is superior to conventional training based on other patients' data. Using CG image as training reference provides a better trade-off in terms of noise and image blur as compared to the use of NG. cGAN-CG-PD provides superior performance as compared to other denoising methods for all physical and diagnostic indices evaluated in both simulation and clinical studies. CONCLUSIONS cGAN denoising is promising for dual gating MP-SPECT based on the metrics mentioned above. This article is protected by copyright. All rights reserved.