Journal
JOURNAL OF NUCLEAR MEDICINE
Volume 61, Issue 9, Pages 1388-1396Publisher
SOC NUCLEAR MEDICINE INC
DOI: 10.2967/jnumed.119.239327
Keywords
PET/CT; brain imaging; low-dose imaging; deep learning; radiomics
Funding
- Swiss National Science Foundation [SNRF 320030_176052, SNF 320030_169876]
- Swiss Cancer Research Foundation [KFS-3855-02-2016]
Ask authors/readers for more resources
Our purpose was to assess the performance of full-dose (FD) PET image synthesis in both image and sinogram space from low-dose (LD) PET images and sinograms without sacrificing diagnostic quality using deep learning techniques. Methods: Clinical brain PET/CT studies of 140 patients were retrospectively used for LD-to-FD PET conversion. Five percent of the events were randomly selected from the FD list-mode PET data to simulate a realistic LD acquisition. A modified 3-dimensional U-Net model was implemented to predict FD sinograms in the projection space (PSS) and FD images in image space (PIS) from their corresponding LD sinograms and images, respectively. The quality of the predicted PET images was assessed by 2 nuclear medicine specialists using a 5-point grading scheme. Quantitative analysis using established metrics including the peak signal-to-noise ratio (PSNR), structural similarity index metric (SSIM), regionwise SUV bias, and first-, second- and high-order texture radiomic features in 83 brain regions for the test and evaluation datasets was also performed. Results: All PSS images were scored 4 or higher (good to excellent) by the nuclear medicine specialists. PSNR and SSIM values of 0.96 +/- 0.03 and 0.97 +/- 0.02, respectively, were obtained for PIS, and values of 31.70 +/- 0.75 and 37.30 +/- 0.71, respectively, were obtained for PSS. The average SUV bias calculated over all brain regions was 0.24% +/- 0.96% and 1.05% +/- 1.44% for PSS and PIS, respectively. The Bland-Altman plots reported the lowest SUV bias (0.02) and variance (95% confidence interval, -0.92 to 10.84) for PSS, compared with the reference FD images. The relative error of the homogeneity radiomic feature belonging to the gray-level cooccurrence matrix category was -1.07 +/- 1.77 and 0.28 +/- 1.4 for PIS and PSS, respectively. Conclusion: The qualitative assessment and quantitative analysis demonstrated that the FD PET PSS led to superior performance, resulting in higher image quality and lower SUV bias and variance than for FD PET PIS.
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