Comparative study of the quantitative accuracy of oncological PET imaging based on deep learning methods

Abstract

Background: [18F] Fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) is an important tool for tumor assessment. Shortening scanning time and reducing the amount of radioactive tracer remain the most difficult challenges. Deep learning methods have provided powerful solutions, thus making it important to choose an appropriate neural network architecture.Methods: A total of 311 tumor patients who underwent 18 F-FDG PET/CT were retrospectively collected.The PET collection time was 3 min/bed. The first 15 and 30 s of each bed collection time were selected to simulate low-dose collection, and the pre-90s was used as the clinical standard protocol. Low-dose PET was used as input, convolutional neural network (CNN, 3D Unet as representative) and generative adversarial network (GAN, P2P as representative) were used to predict the full-dose images. The image visual scores, noise levels and quantitative parameters of tumor tissue were compared.Results: There was high consistency in image quality scores among all groups [Kappa =0.719, 95% confidence interval (CI): 0.697-0.741, P<0.001]. There were 264 cases (3D Unet-15s), 311 cases (3D Unet-30s), 89 cases (P2P-15s) and 247 cases (P2P-30s) with image quality score ≥3, respectively. There was significant difference in the score composition among all groups (χ 2 =1,325.46, P<0.001). Both deep learning models reduced the standard deviation (SD) of background, and increased the signal-to-noise ratio (SNR).When 8%PET images were used as input, P2P and 3D Unet had similar enhancement effect on SNR of tumor lesions, but 3D Unet could significantly improve the contrast-noise ratio (CNR) (P<0.05). There was no significant difference in SUVmean of tumor lesions compared with s-PET group (P>0.05). When 17%PET image was used as input, SNR, CNR and SUVmax of tumor lesion of 3D Unet group had no statistical difference with those of s-PET group (P>0.05). Conclusions: Both GAN and CNN can suppress image noise to varying degrees and improve image quality. However, when 3D Unet reduces the noise of tumor lesions, it can improve the CNR of tumor lesions. Moreover, quantitative parameters of tumor tissue are similar to those under the standard acquisition protocol, which can meet the needs of clinical diagnosis. ^ ORCID: 0000-0003-0376-982X.

Deep learning-based PET image denoising and reconstruction: a review

“…In addition to adopting a network, such as a U-Net, which is capable of image-to-image translation as a generator, it can be regarded as a training method that considers the adversarial loss based on the output from the discriminator. GAN training proceeds such that the label data are no longer distinguishable from the output images of the CNN, thereby synthesizing denoised PET images with less spatial blur and better visual quality [ 114 – 116 ]. Common models for denoising by GANs include Conditional GAN [ 117 ] and Pix2Pix [ 118 ], while incorporating various network structures [ 119 , 120 ] and additional loss functions, such as least squares [ 121 , 122 ], task-specific perceptual loss [ 123 ], pixelwise loss [ 124 ], and Wasserstein distance with a gradient penalty [ 125 ], have all been reported to improve denoising performance.…”

Deep learning image reconstruction technique based on sinogram with 99m Tc-3PRGD2 chest SPECT

“…For this study, we used the MONAI deep learning framework and incorporated a 3D UNet deep neural network [14] , which is depicted in Fig. 1.…”

Investigation of PET image quality with acquisition time/bed and enhancement of lesion quantification accuracy through deep progressive learning

“…In recent years, deep learning-based approaches have shown great potential in improving PET image quality and reducing noise [ 10 – 12 ]. Hu et al [ 13 ] found that generative adversarial network (GAN) and convolutional neural network (CNN) could suppress image noise to varying degrees and improve image quality. Lu et al [ 14 ] demonstrated that fully 3D U-net could effectively reduce image noise and control bias even for sub-centimeter small lung nodules when generating standard dose PET using 10% low count down-sampled data.…”