Skip to main content

ORIGINAL RESEARCH article

Front. Med.
Sec. Nuclear Medicine
Volume 11 - 2024 | doi: 10.3389/fmed.2024.1415058
This article is part of the Research Topic Towards Precision Oncology: Assessing the Role of Radiomics and Artificial Intelligence View all 10 articles

Whole-body PET image denoising for reduced acquisition time

Provisionally accepted
Stepan Kudin Stepan Kudin 1Ivan Kruzhilov Ivan Kruzhilov 1,2*Luka Vetoshkin Luka Vetoshkin 3*Elena Sokolova Elena Sokolova 4*Vladimir Kokh Vladimir Kokh 4*
  • 1 Sber AI Lab, Moscow, Russia
  • 2 Applied mathematics and AI, Moscow Power Engineering Institute, Moscow, Moscow Oblast, Russia
  • 3 Moscow Institute of Physics and Technology, Dolgoprudny, Moscow Oblast, Russia
  • 4 LLC SberMedAI, Moscow, Russia

The final, formatted version of the article will be published soon.

    Purpose: 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 sec PET denoising and on 16.9% and 11.4% in 60 sec PET denoising when compared to the original 90 sec PET reducing at the same time SUVmax discrepancy dispersion.

    Keywords: artificial intelligence, positron emission tomography, SUV, Noise Reduction, MedNeXt, SwinIR

    Received: 09 Apr 2024; Accepted: 30 Aug 2024.

    Copyright: © 2024 Kudin, Kruzhilov, Vetoshkin, Sokolova and Kokh. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence:
    Ivan Kruzhilov, Sber AI Lab, Moscow, Russia
    Luka Vetoshkin, Moscow Institute of Physics and Technology, Dolgoprudny, 141700, Moscow Oblast, Russia
    Elena Sokolova, LLC SberMedAI, Moscow, Russia
    Vladimir Kokh, LLC SberMedAI, Moscow, Russia

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.