Kruzhilov Ivan, Kudin Stepan, Vetoshkin Luka, Sokolova Elena, Kokh Vladimir
Applied Mathematics and AI, Moscow Power Engineering Institute, Moscow, Russia.
Sber AI Lab, Moscow, Russia.
Front Med (Lausanne). 2024 Sep 30;11:1415058. doi: 10.3389/fmed.2024.1415058. eCollection 2024.
A reduced acquisition time positively impacts the patient's comfort and the PET scanner's throughput. AI methods may allow for reducing PET acquisition time without sacrificing image quality. The study aims to compare various neural networks to find the best models for PET denoising.
Our experiments consider 212 studies (56,908 images) for 7MBq/kg injected activity and evaluate the models using 2D (RMSE, SSIM) and 3D (SUVpeak and SUVmax error for the regions of interest) metrics. We tested 2D and 2.5D ResNet, Unet, SwinIR, 3D MedNeXt, and 3D UX-Net. We have also compared supervised methods with the unsupervised CycleGAN approach.
The best model for PET denoising is 3D MedNeXt. It improved SSIM on 38.2% and RMSE on 28.1% in 30-s PET denoising and on 16.9% and 11.4% in 60-s PET denoising when compared to the original 90-s PET reducing at the same time SUVmax discrepancy dispersion.
缩短采集时间对患者舒适度和PET扫描仪的通量有积极影响。人工智能方法可能允许在不牺牲图像质量的情况下减少PET采集时间。本研究旨在比较各种神经网络，以找到用于PET去噪的最佳模型。
我们的实验考虑了212项研究（56,908张图像），注射活度为7MBq/kg，并使用二维（均方根误差、结构相似性指数）和三维（感兴趣区域的SUV峰值和SUV最大值误差）指标评估模型。我们测试了二维和2.5维残差神经网络（ResNet）、U-Net、SwinIR、三维医学神经网络（MedNeXt）和三维UX-Net。我们还将监督方法与无监督循环生成对抗网络（CycleGAN）方法进行了比较。
PET去噪的最佳模型是三维医学神经网络（MedNeXt）。与原始的90秒PET相比，在30秒PET去噪中，它将结构相似性指数提高了38.2%，均方根误差提高了28.1%；在60秒PET去噪中，分别提高了16.9%和11.4%，同时降低了SUV最大值差异离散度。
