Ultra-low-dose PET reconstruction using generative adversarial network with feature matching and task-specific perceptual loss
Journal
Medical Physics
Journal Volume
46
Journal Issue
8
Pages
3555-3564
Date Issued
2019
Author(s)
Abstract
Purpose: Our goal was to use a generative adversarial network (GAN) with feature matching and task-specific perceptual loss to synthesize standard-dose amyloid Positron emission tomography (PET) images of high quality and including accurate pathological features from ultra-low-dose PET images only. Methods: Forty PET datasets from 39 participants were acquired with a simultaneous PET/MRI scanner following injection of 330?±?30?MBq of the amyloid radiotracer 18F-florbetaben. The raw list-mode PET data were reconstructed as the standard-dose ground truth and were randomly undersampled by a factor of 100 to reconstruct 1% low-dose PET scans. A 2D encoder-decoder network was implemented as the generator to synthesize a standard-dose image and a discriminator was used to evaluate them. The two networks contested with each other to achieve high-visual quality PET from the ultra-low-dose PET. Multi-slice inputs were used to reduce noise by providing the network with 2.5D information. Feature matching was applied to reduce hallucinated structures. Task-specific perceptual loss was designed to maintain the correct pathological features. The image quality was evaluated by peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and root mean square error (RMSE) metrics with and without each of these modules. Two expert radiologists were asked to score image quality on a 5-point scale and identified the amyloid status (positive or negative). Results: With only low-dose PET as input, the proposed method significantly outperformed Chen et al.'s method (Chen et al. Radiology. 2018;290:649–656) (which shows the best performance in this task) with the same input (PET-only model) by 1.87?dB in PSNR, 2.04% in SSIM, and 24.75% in RMSE. It also achieved comparable results to Chen et al.'s method which used additional magnetic resonance imaging (MRI) inputs (PET-MR model). Experts' reading results showed that the proposed method could achieve better overall image quality and maintain better pathological features indicating amyloid status than both PET-only and PET-MR models proposed by Chen et al. Conclusion: Standard-dose amyloid PET images can be synthesized from ultra-low-dose images using GAN. Applying adversarial learning, feature matching, and task-specific perceptual loss are essential to ensure image quality and the preservation of pathological features. ? 2019 American Association of Physicists in Medicine
Subjects
Deep learning
Glycoproteins
Image quality
Mean square error
Positron emission tomography
Quality control
Signal to noise ratio
Adversarial learning
Adversarial networks
Peak signal to noise ratio
PET reconstruction
Positron emission tomography (PET)
Root mean square errors
Structural similarity
Visual qualities
Magnetic resonance imaging
Article
brain cortex
classifier
clinical article
clinical evaluation
clinical feature
diagnostic accuracy
generative adversarial network
human
image quality
image reconstruction
machine learning
mean absolute error
nuclear magnetic resonance imaging
positron emission tomography
radiation dose
radiological parameters
signal noise ratio
statistical analysis
task positive network
time of flight mass spectrometry
article
deep learning
human experiment
low drug dose
radiologist
SDGs
Type
journal article