Using deep learning methods to shorten acquisition time in children’s renal cortical imaging
Listed in
This article is not in any list yet, why not save it to one of your lists.Abstract
Purpose
This study evaluates the capability of diffusion-based generative models to reconstruct diagnostic-quality renal cortical images from reduced-acquisition-time pediatric 99mTc-DMSA scintigraphy.
Materials and Methods
A prospective study was conducted on 99mTc-DMSA scintigraphic data from consecutive pediatric patients with suspected urinary tract infections (UTIs) acquired between November 2023 and October 2024. A diffusion model SR3 was trained to reconstruct standard-quality images from simulated reduced-count data. Performance was benchmarked against U-Net, U 2 -Net, Restormer, and a Poisson-based variant of SR3 (PoissonSR3). Quantitative assessment employed peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), Fréchet inception distance (FID), and learned perceptual image patch similarity (LPIPS). Renal contrast and anatomic fidelity were assessed using the target-to-background ratio (TBR) and the Dice similarity coefficient respectively. Wilcoxon signed-rank tests were used for statistical analysis.
Results
The training cohort comprised 94 participants (mean age 5.16±3.90 years; 48 male) with corresponding Poisson-downsampled images, while the test cohort included 36 patients (mean age 6.39±3.16 years; 14 male). SR3 outperformed all models, achieving the highest PSNR (30.976±2.863, P<.001), SSIM (0.760±0.064, P<.001), FID (25.687±16.223, P<.001), and LPIPS (0.055±0.022, P<.001). Further, SR3 maintained excellent renal contrast (TBR: left kidney 7.333±2.176; right kidney 7.156±1.808) and anatomical consistency (Dice coefficient: left kidney 0.749±0.200; right kidney 0.745±0.176), representing significant improvements over the fast scan (all P < .001). While Restormer, U-Net, and PoissonSR3 showed statistically significant improvements across all metrics, U 2 -Net exhibited limited improvement restricted to SSIM and left kidney TBR (P < .001).
Conclusion
SR3 enables high-quality reconstruction of 99mTc-DMSA images from 4-fold accelerated acquisitions, demonstrating potential for substantial reduction in imaging duration while preserving both diagnostic image quality and renal anatomical integrity.
