PURPOSE: We aimed to evaluate the performance of deep learning-based generalization of ultra-low-count amyloid PET/MRI enhancement when applied to studies acquired with different scanning hardware and protocols. METHODS: Eighty simultaneous [18F]florbetaben PET/MRI studies were acquired, split equally between two sites (site 1: Signa PET/MRI, GE Healthcare, 39 participants, 67 ± 8 years, 23 females; site 2: mMR, Siemens Healthineers, 64 ± 11 years, 23 females) with different MRI protocols. Twenty minutes of list-mode PET data (90-110 min post-injection) were reconstructed as ground-truth. Ultra-low-count data obtained from undersampling by a factor of 100 (site 1) or the first minute of PET acquisition (site 2) were reconstructed for ultra-low-dose/ultra-short-time (1% dose and 5% time, respectively) PET images. A deep convolution neural network was pre-trained with site 1 data and either (A) directly applied or (B) trained further on site 2 data using transfer learning. Networks were also trained from scratch based on (C) site 2 data or (D) all data. Certified physicians determined amyloid uptake (+/-) status for accuracy and scored the image quality. The peak signal-to-noise ratio, structural similarity, and root-mean-squared error were calculated between images and their ground-truth counterparts. Mean regional standardized uptake value ratios (SUVR, reference region: cerebellar cortex) from 37 successful site 2 FreeSurfer segmentations were analyzed. RESULTS: All network-synthesized images had reduced noise than their ultra-low-count reconstructions. Quantitatively, image metrics improved the most using method B, where SUVRs had the least variability from the ground-truth and the highest effect size to differentiate between positive and negative images. Method A images had lower accuracy and image quality than other methods; images synthesized from methods B-D scored similarly or better than the ground-truth images. CONCLUSIONS: Deep learning can successfully produce diagnostic amyloid PET images from short frame reconstructions. Data bias should be considered when applying pre-trained deep ultra-low-count amyloid PET/MRI networks for generalization.
PURPOSE: We aimed to evaluate the performance of deep learning-based generalization of ultra-low-count amyloid PET/MRI enhancement when applied to studies acquired with different scanning hardware and protocols. METHODS: Eighty simultaneous [18F]florbetaben PET/MRI studies were acquired, split equally between two sites (site 1: Signa PET/MRI, GE Healthcare, 39 participants, 67 ± 8 years, 23 females; site 2: mMR, Siemens Healthineers, 64 ± 11 years, 23 females) with different MRI protocols. Twenty minutes of list-mode PET data (90-110 min post-injection) were reconstructed as ground-truth. Ultra-low-count data obtained from undersampling by a factor of 100 (site 1) or the first minute of PET acquisition (site 2) were reconstructed for ultra-low-dose/ultra-short-time (1% dose and 5% time, respectively) PET images. A deep convolution neural network was pre-trained with site 1 data and either (A) directly applied or (B) trained further on site 2 data using transfer learning. Networks were also trained from scratch based on (C) site 2 data or (D) all data. Certified physicians determined amyloid uptake (+/-) status for accuracy and scored the image quality. The peak signal-to-noise ratio, structural similarity, and root-mean-squared error were calculated between images and their ground-truth counterparts. Mean regional standardized uptake value ratios (SUVR, reference region: cerebellar cortex) from 37 successful site 2 FreeSurfer segmentations were analyzed. RESULTS: All network-synthesized images had reduced noise than their ultra-low-count reconstructions. Quantitatively, image metrics improved the most using method B, where SUVRs had the least variability from the ground-truth and the highest effect size to differentiate between positive and negative images. Method A images had lower accuracy and image quality than other methods; images synthesized from methods B-D scored similarly or better than the ground-truth images. CONCLUSIONS: Deep learning can successfully produce diagnostic amyloid PET images from short frame reconstructions. Data bias should be considered when applying pre-trained deep ultra-low-count amyloid PET/MRI networks for generalization.
Entities:
Keywords:
Amyloid PET; Low-count imaging; PET/MRI; Transfer learning
Authors: Sergios Gatidis; Christian Würslin; Ferdinand Seith; Jürgen F Schäfer; Christian la Fougère; Konstantin Nikolaou; Nina F Schwenzer; Holger Schmidt Journal: Hell J Nucl Med Date: 2016-03-01 Impact factor: 1.102
Authors: Clifford R Jack; David A Bennett; Kaj Blennow; Maria C Carrillo; Billy Dunn; Samantha Budd Haeberlein; David M Holtzman; William Jagust; Frank Jessen; Jason Karlawish; Enchi Liu; Jose Luis Molinuevo; Thomas Montine; Creighton Phelps; Katherine P Rankin; Christopher C Rowe; Philip Scheltens; Eric Siemers; Heather M Snyder; Reisa Sperling Journal: Alzheimers Dement Date: 2018-04 Impact factor: 21.566
Authors: Mingrui Yang; Ceylan Colak; Kishore K Chundru; Sibaji Gaj; Andreas Nanavati; Morgan H Jones; Carl S Winalski; Naveen Subhas; Xiaojuan Li Journal: Quant Imaging Med Surg Date: 2022-05
Authors: Nicolas Aide; Charline Lasnon; Adam Kesner; Craig S Levin; Irene Buvat; Andrei Iagaru; Ken Hermann; Ramsey D Badawi; Simon R Cherry; Kevin M Bradley; Daniel R McGowan Journal: Eur J Nucl Med Mol Imaging Date: 2021-06-03 Impact factor: 9.236