Dynamic PET Image Denoising Using Deep Image Prior Combined With Regularization by Denoising

Abstract

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.

Deep learning-based image reconstruction and post-processing methods in positron emission tomography for low-dose imaging and resolution enhancement

“…Results indicated superior performance compared to Gaussian smoothing, image-guided filtering and the 3D deep image prior [ 112 ]. Adding denoising regularisation to the standard DIP formulation was also investigated [ 114 ]. Other variations on spatial domain processing techniques include work from He et al [ 115 ] that trained a neural network to map dynamic PET and MR inputs to a downsampled composite of all frames with edge preserving regularisation and a combination of L 1 and L 2 loss.…”

Solar Speckle Image Deblurring With Deep Prior Constraint Based on Regularization

“…Mirza et al [21] proposed a conditional generation adversarial network, which replaced noise with other prior information as network input to improve the network prediction results. Fumio et al [22] and Sun et al [23] inputed medical noise images as prior information into generate network, and obtained better image denoising results. These methods have achieved good results in image deblurring calculation, but there are some deficiencies for solar speckle image reconstruction, such as slow network convergence and blurred local edges, which are due to the large randomness of the generated results when the network with noise as input, as well as the solar speckle images usually contain single structural features, more noise, and blurred local details.…”

Populational and individual information based PET image denoising using conditional unsupervised learning

“…Based on DIP, we have proposed an unsupervised deep learning method for static PET denoising, named conditional deep image prior (CDIP) (Cui et al 2019), which only needs the PET and anatomical pair of one patient. Some studies were also proposed using DIP for dynamic PET denoising (Hashimoto et al 2019, Sun et al 2021 and reconstruction (Yokota et al 2019).…”