Image enhancement of whole-body oncology [18F]-FDG PET scans using deep neural networks to reduce noise
Open Access
- 28 July 2021
- journal article
- research article
- Published by Springer Nature in European Journal of Nuclear Medicine and Molecular Imaging
- Vol. 49 (2) , 539-549
Abstract
Purpose: To enhance the image quality of oncology [18F]-FDG PET scans acquired in shorter times and reconstructed by faster algorithms using deep neural networks. Methods: List-mode data from 277 [18F]-FDG PET/CT scans, from six centres using GE Discovery PET/CT scanners, were split into ¾-, ½- and ¼-duration scans. Full-duration datasets were reconstructed using the convergent block sequential regularised expectation maximisation (BSREM) algorithm. Short-duration datasets were reconstructed with the faster OSEM algorithm. The 277 examinations were divided into training (n = 237), validation (n = 15) and testing (n = 25) sets. Three deep learning enhancement (DLE) models were trained to map full and partial-duration OSEM images into their target full-duration BSREM images. In addition to standardised uptake value (SUV) evaluations in lesions, liver and lungs, two experienced radiologists scored the quality of testing set images and BSREM in a blinded clinical reading (175 series). Results: OSEM reconstructions demonstrated up to 22% difference in lesion SUVmax, for different scan durations, compared to full-duration BSREM. Application of the DLE models reduced this difference significantly for full-, ¾- and ½-duration scans, while simultaneously reducing the noise in the liver. The clinical reading showed that the standard DLE model with full- or ¾-duration scans provided an image quality substantially comparable to full-duration scans with BSREM reconstruction, yet in a shorter reconstruction time. Conclusion: Deep learning–based image enhancement models may allow a reduction in scan time (or injected activity) by up to 50%, and can decrease reconstruction time to a third, while maintaining image quality.Keywords
Funding Information
- Cancer Research UK (C34326/A28684, C4278/A27066)
- Innovate UK (104688)
This publication has 23 references indexed in Scilit:
- DeepPET: A deep encoder–decoder network for directly solving the PET image reconstruction inverse problemMedical Image Analysis, 2019
- Image reconstruction by domain-transform manifold learningNature, 2018
- Standard OSEM vs. regularized PET image reconstruction: qualitative and quantitative comparison using phantom data and various clinical radiopharmaceuticals2018
- 18F-FDG PET/CT assessment of histopathologically confirmed mediastinal lymph nodes in non-small cell lung cancer using a penalised likelihood reconstructionEuropean Radiology, 2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Dosage optimization in positron emission tomography: state-of-the-art methods and future prospects.2015
- Phantom and Clinical Evaluation of the Bayesian Penalized Likelihood Reconstruction Algorithm Q.Clear on an LYSO PET/CT SystemJournal of Nuclear Medicine, 2015
- FDG PET/CT: EANM procedure guidelines for tumour imaging: version 2.0European Journal of Nuclear Medicine and Molecular Imaging, 2014
- Iterative reconstruction techniques in emission computed tomographyPhysics in Medicine & Biology, 2006
- The Equivalence of Weighted Kappa and the Intraclass Correlation Coefficient as Measures of ReliabilityEducational and Psychological Measurement, 1973