An up-to-date list is available on Google Scholar.
Thesis
2023
-
Development of advanced generative priors for MRI reconstruction
Guanxiong Luo
Computer Science at University of Göttingen, 2023
2019
-
The application of generative networks in MR image reconstruction
Guanxiong Luo
Radiology at University of Hong Kong, 2019
2017
-
基于压缩感知的快速磁共振成像
Guanxiong Luo
Biomedical Engineering at Xian Jiaotong University, 2017
Preprints
2023
-
Generative Image Priors for MRI Reconstruction Trained from Magnitude-Only Images
Guanxiong Luo, Xiaoqing Wang, Mortiz Blumenthal, Martin Schilling, Erik Hans Ulrich Rauf, and 3 more authors
Aug 2023
Journal Articles
2023
-
Bayesian MRI reconstruction with joint uncertainty estimation using diffusion models
Guanxiong Luo, Moritz Blumenthal, Martin Heide, and Martin Uecker
Magn. Reson. Med., Aug 2023
Purpose We introduce a framework that enables efficient sampling from learned probability distributions for MRI reconstruction. Method Samples are drawn from the posterior distribution given the measured k-space using the Markov chain Monte Carlo (MCMC) method, different from conventional deep learning-based MRI reconstruction techniques. In addition to the maximum a posteriori estimate for the image, which can be obtained by maximizing the log-likelihood indirectly or directly, the minimum mean square error estimate and uncertainty maps can also be computed from those drawn samples. The data-driven Markov chains are constructed with the score-based generative model learned from a given image database and are independent of the forward operator that is used to model the k-space measurement. Results We numerically investigate the framework from these perspectives: (1) the interpretation of the uncertainty of the image reconstructed from undersampled k-space; (2) the effect of the number of noise scales used to train the generative models; (3) using a burn-in phase in MCMC sampling to reduce computation; (4) the comparison to conventional L1-wavelet regularized reconstruction; (5) the transferability of learned information; and (6) the comparison to fastMRI challenge. Conclusion A framework is described that connects the diffusion process and advanced generative models with Markov chains. We demonstrate its flexibility in terms of contrasts and sampling patterns using advanced generative priors and the benefits of also quantifying the uncertainty for every pixel.
2022
-
Deep, deep learning with BART
Moritz Blumenthal, Guanxiong Luo, Martin Schilling, H. Christian M. Holme, and Martin Uecker
Magn. Reson. Med., Oct 2022
Purpose To develop a deep-learning-based image reconstruction framework for reproducible research in MRI. Methods The BART toolbox offers a rich set of implementations of calibration and reconstruction algorithms for parallel imaging and compressed sensing. In this work, BART was extended by a nonlinear operator framework that provides automatic differentiation to allow computation of gradients. Existing MRI-specific operators of BART, such as the nonuniform fast Fourier transform, are directly integrated into this framework and are complemented by common building blocks used in neural networks. To evaluate the use of the framework for advanced deep-learning-based reconstruction, two state-of-the-art unrolled reconstruction networks, namely the Variational Network and MoDL, were implemented. Results State-of-the-art deep image-reconstruction networks can be constructed and trained using BART’s gradient-based optimization algorithms. The BART implementation achieves a similar performance in terms of training time and reconstruction quality compared to the original implementations based on TensorFlow. Conclusion By integrating nonlinear operators and neural networks into BART, we provide a general framework for deep-learning-based reconstruction in MRI.
2020
-
MRI reconstruction using deep Bayesian estimation
Guanxiong Luo, Na Zhao, Wenhao Jiang, Edward S. Hui, and Peng Cao
Magn. Reson. Med., Apr 2020
Purpose To develop a deep learning-based Bayesian estimation for MRI reconstruction. Methods We modeled the MRI reconstruction problem with Bayes’s theorem, following the recently proposed PixelCNN++ method. The image reconstruction from incomplete k-space measurement was obtained by maximizing the posterior possibility. A generative network was utilized as the image prior, which was computationally tractable, and the k-space data fidelity was enforced by using an equality constraint. The stochastic backpropagation was utilized to calculate the descent gradient in the process of maximum a posterior, and a projected subgradient method was used to impose the equality constraint. In contrast to the other deep learning reconstruction methods, the proposed one used the likelihood of prior as the training loss and the objective function in reconstruction to improve the image quality. Results The proposed method showed an improved performance in preserving image details and reducing aliasing artifacts, compared with GRAPPA, -ESPRiT, model-based deep learning architecture for inverse problems (MODL), and variational network (VN), last two were state-of-the-art deep learning reconstruction methods. The proposed method generally achieved more than 3 dB peak signal-to-noise ratio improvement for compressed sensing and parallel imaging reconstructions compared with the other methods. Conclusions The Bayesian estimation significantly improved the reconstruction performance, compared with the conventional L1-sparsity prior in compressed sensing reconstruction tasks. More importantly, the proposed reconstruction framework can be generalized for most MRI reconstruction scenarios.
Conference Proceedings and Abstracts
2023
-
Generalized deep learning-based proximal gradient descent for MR reconstruction
Guanxiong Luo, Mengmeng Kuang, and Peng Cao
In Artificial Intelligence in Medicine, Apr 2023
The data consistency for the physical forward model is crucial in inverse problems, especially in MR imaging reconstruction. The standard way is to unroll an iterative algorithm into a neural network with a forward model embedded. The forward model always changes in clinical practice, so the learning component’s entanglement with the forward model makes the reconstruction hard to generalize. The deep learning-based proximal gradient descent was proposed and use a network as regularization term that is independent of the forward model, which makes it more generalizable for different MR acquisition settings. This one-time pre-trained regularization is applied to different MR acquisition settings and was compared to conventional L1 regularization showing ~3 dB improvement in the peak signal-to-noise ratio. We also demonstrated the flexibility of the proposed method in choosing different undersampling patterns.
2022
-
All you need are DICOM images
Guanxiong Luo, Moritz Blumenthal, Xiaoqing Wang, and Martin Uecker
In Proc. Intl. Soc. Mag. Reson. Med., Apr 2022
-
Using data-driven Markov chains for MRI reconstruction with joint uncertainty estimation
Guanxiong Luo, Martin Heide, and Martin Uecker
In Proc. Intl. Soc. Mag. Reson. Med., Apr 2022
-
NLINV-Net: self-supervised end-2-end learning for reconstructing undersampled radial cardiac real-time data
Moritz Blumenthal, Guanxiong Luo, Martin Schilling, Markus Haltmeier, and Martin Uecker
In Proc. Intl. Soc. Mag. Reson. Med., Apr 2022
2021
-
Joint estimation of coil sensitivities and image content using a deep image prior
Guanxiong Luo, Xiaoqing Wang, Volkert Roeloffs, Zhengguo Tan, and Martin Uecker
In Proc. Intl. Soc. Mag. Reson. Med., Apr 2021
-
Using data-driven image priors for image reconstruction with BART
Guanxiong Luo, Moritz Blumenthal, and Martin Uecker
In Proc. Intl. Soc. Mag. Reson. Med., Apr 2021
2020
-
MRI reconstruction using deep Bayesian inference
Guanxiong Luo, and Peng Cao
In Proc. Intl. Soc. Mag. Reson. Med., Apr 2020