Modern regularization methods for inverse problems
Regularization methods are a key tool in the solution of inverse problems. They are used to
introduce prior knowledge and allow a robust approximation of ill-posed (pseudo-) inverses …
introduce prior knowledge and allow a robust approximation of ill-posed (pseudo-) inverses …
From simultaneous to synergistic MR‐PET brain imaging: A review of hybrid MR‐PET imaging methodologies
Abstract Simultaneous Magnetic Resonance Imaging (MRI) and Positron Emission
Tomography (PET) scanning is a recent major development in biomedical imaging. The full …
Tomography (PET) scanning is a recent major development in biomedical imaging. The full …
Iterative PET image reconstruction using convolutional neural network representation
PET image reconstruction is challenging due to the ill-poseness of the inverse problem and
limited number of detected photons. Recently, the deep neural networks have been widely …
limited number of detected photons. Recently, the deep neural networks have been widely …
Higher-order total variation approaches and generalisations
Over the last decades, the total variation (TV) has evolved to be one of the most broadly-
used regularisation functionals for inverse problems, in particular for imaging applications …
used regularisation functionals for inverse problems, in particular for imaging applications …
Low rank alternating direction method of multipliers reconstruction for MR fingerprinting
Purpose The proposed reconstruction framework addresses the reconstruction accuracy,
noise propagation and computation time for magnetic resonance fingerprinting. Methods …
noise propagation and computation time for magnetic resonance fingerprinting. Methods …
Stochastic primal-dual hybrid gradient algorithm with arbitrary sampling and imaging applications
We propose a stochastic extension of the primal-dual hybrid gradient algorithm studied by
Chambolle and Pock in 2011 to solve saddle point problems that are separable in the dual …
Chambolle and Pock in 2011 to solve saddle point problems that are separable in the dual …
High‐dimensionality undersampled patch‐based reconstruction (HD‐PROST) for accelerated multi‐contrast MRI
Purpose To develop a new high‐dimensionality undersampled patch‐based reconstruction
(HD‐PROST) for highly accelerated 2D and 3D multi‐contrast MRI. Methods HD‐PROST …
(HD‐PROST) for highly accelerated 2D and 3D multi‐contrast MRI. Methods HD‐PROST …
Improving parallel imaging by jointly reconstructing multi‐contrast data
Purpose To develop parallel imaging techniques that simultaneously exploit coil sensitivity
encoding, image phase prior information, similarities across multiple images, and …
encoding, image phase prior information, similarities across multiple images, and …
[HTML][HTML] Approximating anatomically-guided PET reconstruction in image space using a convolutional neural network
In the last two decades, it has been shown that anatomically-guided PET reconstruction can
lead to improved bias-noise characteristics in brain PET imaging. However, despite …
lead to improved bias-noise characteristics in brain PET imaging. However, despite …
Dynamic PET image denoising using deep image prior combined with regularization by denoising
H Sun, L Peng, H Zhang, Y He, S Cao, L Lu - IEEE Access, 2021 - ieeexplore.ieee.org
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 …
factors, including the intrinsic resolution of the imaging system and inherently noisy data …