PURPOSE: While sampled or short-frame realizations have shown the potential power of deep learning to reduce radiation dose for PET images, evidence in true injected ultra-low-dose cases is lacking. Therefore, we evaluated deep learning enhancement using a significantly reduced injected radiotracer protocol for amyloid PET/MRI. METHODS: Eighteen participants underwent two separate 18F-florbetaben PET/MRI studies in which an ultra-low-dose (6.64 ± 3.57 MBq, 2.2 ± 1.3% of standard) or a standard-dose (300 ± 14 MBq) was injected. The PET counts from the standard-dose list-mode data were also undersampled to approximate an ultra-low-dose session. A pre-trained convolutional neural network was fine-tuned using MR images and either the injected or sampled ultra-low-dose PET as inputs. Image quality of the enhanced images was evaluated using three metrics (peak signal-to-noise ratio, structural similarity, and root mean square error), as well as the coefficient of variation (CV) for regional standard uptake value ratios (SUVRs). Mean cerebral uptake was correlated across image types to assess the validity of the sampled realizations. To judge clinical performance, four trained readers scored image quality on a five-point scale (using 15% non-inferiority limits for proportion of studies rated 3 or better) and classified cases into amyloid-positive and negative studies. RESULTS: The deep learning-enhanced PET images showed marked improvement on all quality metrics compared with the low-dose images as well as having generally similar regional CVs as the standard-dose. All enhanced images were non-inferior to their standard-dose counterparts. Accuracy for amyloid status was high (97.2% and 91.7% for images enhanced from injected and sampled ultra-low-dose data, respectively) which was similar to intra-reader reproducibility of standard-dose images (98.6%). CONCLUSION: Deep learning methods can synthesize diagnostic-quality PET images from ultra-low injected dose simultaneous PET/MRI data, demonstrating the general validity of sampled realizations and the potential to reduce dose significantly for amyloid imaging.
PURPOSE: While sampled or short-frame realizations have shown the potential power of deep learning to reduce radiation dose for PET images, evidence in true injected ultra-low-dose cases is lacking. Therefore, we evaluated deep learning enhancement using a significantly reduced injected radiotracer protocol for amyloid PET/MRI. METHODS: Eighteen participants underwent two separate 18F-florbetaben PET/MRI studies in which an ultra-low-dose (6.64 ± 3.57 MBq, 2.2 ± 1.3% of standard) or a standard-dose (300 ± 14 MBq) was injected. The PET counts from the standard-dose list-mode data were also undersampled to approximate an ultra-low-dose session. A pre-trained convolutional neural network was fine-tuned using MR images and either the injected or sampled ultra-low-dose PET as inputs. Image quality of the enhanced images was evaluated using three metrics (peak signal-to-noise ratio, structural similarity, and root mean square error), as well as the coefficient of variation (CV) for regional standard uptake value ratios (SUVRs). Mean cerebral uptake was correlated across image types to assess the validity of the sampled realizations. To judge clinical performance, four trained readers scored image quality on a five-point scale (using 15% non-inferiority limits for proportion of studies rated 3 or better) and classified cases into amyloid-positive and negative studies. RESULTS: The deep learning-enhanced PET images showed marked improvement on all quality metrics compared with the low-dose images as well as having generally similar regional CVs as the standard-dose. All enhanced images were non-inferior to their standard-dose counterparts. Accuracy for amyloid status was high (97.2% and 91.7% for images enhanced from injected and sampled ultra-low-dose data, respectively) which was similar to intra-reader reproducibility of standard-dose images (98.6%). CONCLUSION: Deep learning methods can synthesize diagnostic-quality PET images from ultra-low injected dose simultaneous PET/MRI data, demonstrating the general validity of sampled realizations and the potential to reduce dose significantly for amyloid imaging.
Entities:
Keywords:
Amyloid PET; Deep learning; PET/MRI; Ultra-low-dose PET
Authors: Martin S Judenhofer; Hans F Wehrl; Danny F Newport; Ciprian Catana; Stefan B Siegel; Markus Becker; Axel Thielscher; Manfred Kneilling; Matthias P Lichy; Martin Eichner; Karin Klingel; Gerald Reischl; Stefan Widmaier; Martin Röcken; Robert E Nutt; Hans-Jürgen Machulla; Kamil Uludag; Simon R Cherry; Claus D Claussen; Bernd J Pichler Journal: Nat Med Date: 2008-03-23 Impact factor: 53.440
Authors: Jeff Sevigny; Ping Chiao; Thierry Bussière; Paul H Weinreb; Leslie Williams; Marcel Maier; Robert Dunstan; Stephen Salloway; Tianle Chen; Yan Ling; John O'Gorman; Fang Qian; Mahin Arastu; Mingwei Li; Sowmya Chollate; Melanie S Brennan; Omar Quintero-Monzon; Robert H Scannevin; H Moore Arnold; Thomas Engber; Kenneth Rhodes; James Ferrero; Yaming Hang; Alvydas Mikulskis; Jan Grimm; Christoph Hock; Roger M Nitsch; Alfred Sandrock Journal: Nature Date: 2016-09-01 Impact factor: 49.962
Authors: Kyungsang Kim; Dufan Wu; Kuang Gong; Joyita Dutta; Jong Hoon Kim; Young Don Son; Hang Keun Kim; Georges El Fakhri; Quanzheng Li Journal: IEEE Trans Med Imaging Date: 2018-06 Impact factor: 10.048
Authors: Reisa A Sperling; Elizabeth C Mormino; Aaron P Schultz; Rebecca A Betensky; Kathryn V Papp; Rebecca E Amariglio; Bernard J Hanseeuw; Rachel Buckley; Jasmeer Chhatwal; Trey Hedden; Gad A Marshall; Yakeel T Quiroz; Nancy J Donovan; Jonathan Jackson; Jennifer R Gatchel; Jennifer S Rabin; Heidi Jacobs; Hyun-Sik Yang; Michael Properzi; Dylan R Kirn; Dorene M Rentz; Keith A Johnson Journal: Ann Neurol Date: 2019-01-21 Impact factor: 10.422
Authors: James Bland; Abolfazl Mehranian; Martin A Belzunce; Sam Ellis; Colm J McGinnity; Alexander Hammers; Andrew J Reader Journal: IEEE Trans Radiat Plasma Med Sci Date: 2017-11-09
Authors: Kevin T Chen; Enhao Gong; Fabiola Bezerra de Carvalho Macruz; Junshen Xu; Athanasia Boumis; Mehdi Khalighi; Kathleen L Poston; Sharon J Sha; Michael D Greicius; Elizabeth Mormino; John M Pauly; Shyam Srinivas; Greg Zaharchuk Journal: Radiology Date: 2018-12-11 Impact factor: 29.146
Authors: K T Chen; O Adeyeri; T N Toueg; M Zeineh; E Mormino; M Khalighi; G Zaharchuk Journal: AJNR Am J Neuroradiol Date: 2022-01-27 Impact factor: 3.825