Generation ofF-FDG PET standard scan images from short scans using cycle-consistent generative adversarial network.

Researchers

Journal

Modalities

Models

Abstract

Objective To improve PET image quality, we aim to generate images of quality comparable to standard scan duration images using short scan duration (1/8th and 1/16th standard scan duration) inputs and assess the generated standard scan duration images quantitative and qualitatively. Also, the effect of training dataset properties (i.e., Body Mass Index (BMI)) on the performance of the model(s) will be explored. Approach Whole-body PET scans of 42 patients (41 18F-FDG and one 68Ga-PSMA) scanned with standard radiotracer dosage were included in this study. One 18F-FDG patient data was set aside and the remaining 40 patients were split into four subsets of 10 patients with different mean patient BMI. Multiple copies of a developed Cycle-GAN network were trained on each subset to predict standard scan images using 1/8th and 1/16th short duration scans. Also, the models’ performance was tested on a patient scanned with the 68Ga-PSMA radiotracer. Quantitative performance was tested using peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and normalized root mean squared error (NRMSE) metrics, and two nuclear medicine specialists analyzed images qualitatively. Main Results The developed Cycle-GAN model improved the PSNR, SSIM, and NRMSE of the 1/8th and 1/16th short scan duration inputs both 18F-FDG and 68Ga-PSMA radiotracers. Although, quantitatively PSNR, SSIM, and NRMSE of the 1/16th scan duration level were improved more than 1/8th counterparts, however, the later were qualitatively more appealing.. SUVmean and SUVmax of the generated images were also indicative of the improvements. The Cycle-GAN model was much more capable in terms of image quality improvements and speed than the NLM denoising method. All results proved statistically significant using the paired-sample T-Test statistical test (p-value<0.05). Significance Our suggested approach based on Cycle-GAN could improve the image quality of the 1/8th and 1/16th short scan-duration inputs through noise reduction both quantitively (PSNR, SSIM, NRMSE, SUVmean, and SUVmax) and qualitatively (Contrast, Noise, and Diagnostic Capability) to the level comparable to the standard scan-duration counterparts. The Cycle-GAN Model(s) had a similar performance on the 68Ga-PSMA to the 18F-FDG images and could improve the images qualitatively and quantitatively but requires more extensive study. Overall, images predicted from 1/8th short scan-duration inputs had the upper hand compared with 1/16th short scan-duration inputs.© 2022 Institute of Physics and Engineering in Medicine.