The quantitative accuracy of positron emission tomography (PET) is affected by several factors, including the intrinsic resolution of the imaging system and inherently noisy data, which result in a low signal-to-noise ratio (SNR) of PET image. To address this problem, in this paper, we proposed a novel deep learning denoising framework aiming to enhance the quantitative accuracy of dynamic PET images via introduction of deep image prior (DIP) combined with Regularization by Denoising (RED), as such the method is labeled as DeepRED denoising. The network structure is based on encoder-decoder architecture and uses skip connections to combine hierarchical features to generate the estimated image. The network input can be random noise or other prior images (such as the patient's own static PET image), avoiding the need of high quality noiseless images, which is limited in PET clinical practice due to high radiation dose. Based on simulated data and real patient data, the quantitative performance of the proposed method was compared with conventional Gaussian filtering (GF), non-local mean (NLM), block-matching and 3D filtering (BM3D), DIP and stochastic gradient Langevin dynamics (SGLD) method. Overall, the proposed method can outperform other conventional methods in substantial visual as well as quantitative accuracy improvements (in terms of noise versus bias performance) with and without prior images.INDEX TERMS Positron emission tomography, deep neural networks, deep image prior, regularization by denoising.

Dynamic positron emission tomography (PET) imaging usually suffers from high statistical noise due to low counts of the short frames. This study aims to improve the image quality of the short frames by utilizing information from other modality. We develop a deep learning-based joint filtering framework for simultaneously incorporating information from longer acquisition PET frames and high-resolution magnetic resonance (MR) images into the short frames. The network inputs are noisy PET images and corresponding MR images while the outputs are linear coefficients of spatially variant linear representation model. The composite of all dynamic frames is used as training label in each sample, and it is down-sampled to 1/10th of counts as the training input. L1-norm combined with two gradient-based regularizations constitute the loss function during training. Ten realistic dynamic PET/MR phantoms based on BrainWeb are used for pre-training and eleven clinical subjects from Alzheimer's Disease Neuroimaging Initiative further for fine-tuning. Simulation results show that the proposed method can reduce the statistical noise while preserving image details and achieve quantitative enhancements compared with Gaussian, guided filter, and convolutional neural network trained with the mean squared error. The clinical results perform better than others in terms of the mean activity and standard deviation. All of the results indicate that the proposed deep learning-based joint filtering framework is of great potential for dynamic PET image denoising.

No abstract

Dynamic positron emission tomography (PET) image reconstruction is challenging due to the low-count statistics of individual frames. This study proposes a novel reconstruction framework aiming to enhance the quantitative accuracy of individual dynamic frames via the introduction of priors based on multiscale superpixel clusters. The clusters are derived from pre-reconstruction composite images using superpixel clustering followed by fuzzy c-means (FCM) clustering. A multiscale aggregation is exploited during the superpixel clustering to generate multiscale superpixel clusters. Then, maximum a posteriori (MAP) PET reconstruction with different-scale clusters is separately applied to individual frame and fused to generate the final result. Using realistic simulated dynamic brain PET data, the quantitative performance of the proposed method is investigated and compared with the maximum-likelihood expectationmaximization (MLEM), Bowsher method, and kernelized expectation-maximization (the kernel method). The proposed method achieves substantial improvements in both visual and quantitative accuracy (in terms of the signal-to-noise ratio and contrast versus noise performances). The method is also tested with a 60 min 18 F-FDG rat study performed with an Inveon small animal PET scanner. The proposed method is shown to outperform the other methods via improvements in visual and quantitative accuracy (in terms of noise versus the mean intensity of the region of interest). INDEX TERMS Image reconstruction, maximum a posteriori, positron emission tomography, superpixel clustering.