Ouyang J.Chen K.T.Gong E.Pauly J.Zaharchuk G.TZE-HSIANG CHEN2022-05-242022-05-24201900942405https://www.scopus.com/inward/record.uri?eid=2-s2.0-85067498993&doi=10.1002%2fmp.13626&partnerID=40&md5=85ed0287896a5b52e184273e8f88750fhttps://scholars.lib.ntu.edu.tw/handle/123456789/611663Purpose: 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 MedicineDeep learningGlycoproteinsImage qualityMean square errorPositron emission tomographyQuality controlSignal to noise ratioAdversarial learningAdversarial networksPeak signal to noise ratioPET reconstructionPositron emission tomography (PET)Root mean square errorsStructural similarityVisual qualitiesMagnetic resonance imagingArticlebrain cortexclassifierclinical articleclinical evaluationclinical featurediagnostic accuracygenerative adversarial networkhumanimage qualityimage reconstructionmachine learningmean absolute errornuclear magnetic resonance imagingpositron emission tomographyradiation doseradiological parameterssignal noise ratiostatistical analysistask positive networktime of flight mass spectrometryarticledeep learninghuman experimentlow drug doseradiologist[SDGs]SDG3journal article10.1002/mp.13626311319012-s2.0-85067498993