Back to Search Start Over

Artificial intelligence-based PET denoising could allow a two-fold reduction in [18F]FDG PET acquisition time in digital PET/CT.

Authors :
Weyts, Kathleen
Lasnon, Charline
Ciappuccini, Renaud
Lequesne, Justine
Corroyer-Dulmont, Aurélien
Quak, Elske
Clarisse, Bénédicte
Roussel, Laurent
Bardet, Stéphane
Jaudet, Cyril
Source :
European Journal of Nuclear Medicine & Molecular Imaging; Sep2022, Vol. 49 Issue 11, p3750-3760, 11p, 1 Black and White Photograph, 2 Diagrams, 5 Charts, 1 Graph
Publication Year :
2022

Abstract

Purpose: We investigated whether artificial intelligence (AI)-based denoising halves PET acquisition time in digital PET/CT. Methods: One hundred ninety-five patients referred for [<superscript>18</superscript>F]FDG PET/CT were prospectively included. Body PET acquisitions were performed in list mode. Original "PET90" (90 s/bed position) was compared to reconstructed ½-duration PET (45 s/bed position) with and without AI-denoising, "PET45AI and PET45". Denoising was performed by SubtlePET™ using deep convolutional neural networks. Visual global image quality (IQ) 3-point scores and lesion detectability were evaluated. Lesion maximal and peak standardized uptake values using lean body mass (SUL<subscript>max</subscript> and SUL<subscript>peak</subscript>), metabolic volumes (MV), and liver SUL<subscript>mean</subscript> were measured, including both standard and EARL<subscript>1</subscript> (European Association of Nuclear Medicine Research Ltd) compliant SUL. Lesion-to-liver SUL ratios (LLR) and liver coefficients of variation (CV<subscript>liv</subscript>) were calculated. Results: PET45 showed mediocre IQ (scored poor in 8% and moderate in 68%) and lesion concordance rate with PET90 (88.7%). In PET45AI, IQ scores were similar to PET90 (P = 0.80), good in 92% and moderate in 8% for both. The lesion concordance rate between PET90 and PET45AI was 836/856 (97.7%), with 7 lesions (0.8%) only detected in PET90 and 13 (1.5%) exclusively in PET45AI. Lesion EARL<subscript>1</subscript> SUL<subscript>peak</subscript> was not significantly different between both PET (P = 0.09). Lesion standard SUL<subscript>peak</subscript>, standard and EARL1 SUL<subscript>max</subscript>, LLR and CV<subscript>liv</subscript> were lower in PET45AI than in PET90 (P < 0.0001), while lesion MV and liver SUL<subscript>mean</subscript> were higher (P < 0.0001). Good to excellent intraclass correlation coefficients (ICC) between PET90 and PET45AI were observed for lesion SUL and MV (ICC ≥ 0.97) and for liver SUL<subscript>mean</subscript> (ICC ≥ 0.87). Conclusion: AI allows [<superscript>18</superscript>F]FDG PET duration in digital PET/CT to be halved, while restoring degraded ½-duration PET image quality. Future multicentric studies, including other PET radiopharmaceuticals, are warranted. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
16197070
Volume :
49
Issue :
11
Database :
Complementary Index
Journal :
European Journal of Nuclear Medicine & Molecular Imaging
Publication Type :
Academic Journal
Accession number :
158671647
Full Text :
https://doi.org/10.1007/s00259-022-05800-1