Generalization of deep learning models for ultra-low-count amyloid PET/MRI using transfer learning
Journal
European Journal of Nuclear Medicine and Molecular Imaging
Journal Volume
47
Journal Issue
13
Pages
2998-3007
Date Issued
2020
Author(s)
Chen K.T.
Sch?rer M.
Ouyang J.
Koran M.E.I.
Davidzon G.
Mormino E.
Tiepolt S.
Hoffmann K.-T.
Sabri O.
Zaharchuk G.
Barthel H.
Abstract
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. ? 2020, Springer-Verlag GmbH Germany, part of Springer Nature.
Subjects
amyloid
florbetaben
aged
Article
cerebellum cortex
convolutional neural network
deep learning
effect size
female
human
image quality
major clinical study
male
nuclear magnetic resonance imaging
positron emission tomography
quantitative analysis
signal noise ratio
standardized uptake value ratio
transfer of learning
image processing
x-ray computed tomography
Amyloid
Deep Learning
Female
Humans
Image Processing, Computer-Assisted
Magnetic Resonance Imaging
Positron-Emission Tomography
Tomography, X-Ray Computed
SDGs
Type
journal article