Journal
EUROPEAN JOURNAL OF NUCLEAR MEDICINE AND MOLECULAR IMAGING
Volume 49, Issue 2, Pages 539-549Publisher
SPRINGER
DOI: 10.1007/s00259-021-05478-x
Keywords
Deep neural networks; PET; Image quality
Funding
- GE Healthcare
- National Consortium of Intelligent Medical Imaging (NCIMI) through the Industry Strategy Challenge Fund
- Innovate UK [104688]
- Cancer Research UK National Cancer Imaging Translational Accelerator [C34326/A28684, C42780/A27066]
- Innovate UK [104688] Funding Source: UKRI
Ask authors/readers for more resources
The study showed that deep learning-based image enhancement models can significantly improve the image quality of oncology [F-18]-FDG PET scans, achieving image quality comparable to full-duration scans in a shorter reconstruction time.
Purpose To enhance the image quality of oncology [F-18]-FDG PET scans acquired in shorter times and reconstructed by faster algorithms using deep neural networks. Methods List-mode data from 277 [F-18]-FDG PET/CT scans, from six centres using GE Discovery PET/CT scanners, were split into 3/4-, 1/2- and 1/4-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-, 3/4- and 1/2-duration scans, while simultaneously reducing the noise in the liver. The clinical reading showed that the standard DLE model with full- or 3/4-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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available