Sen Jia
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Sen Jia has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Dong Liang
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences
4 shared publications - Jing Cheng
Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
4 shared publications - Zhuo-Xu Cui
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China
4 shared publications - Hairong Zheng
Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
3 shared publications - Yanjie Zhu
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
3 shared publications - Qingyong Zhu
Research Center for Medical AI, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
2 shared publications
Latest Publications
- 26 September 2026
- Published by Springer Nature
- p. 414-424
Physical-Driven Unified Implicit Regularization Network with Scan Parameter Prompts for Accelerated Multi-parametric MR Imaging
- 26 September 2026
- Published by Springer Nature
- p. 414-424
Physical-Driven Unified Implicit Regularization Network with Scan Parameter Prompts for Accelerated Multi-parametric MR Imaging
- Open Access
- 21 September 2023
- Published by MDPI AG in Bioengineering
- Vol. 10 (9) , 1107
Joint Image Reconstruction and Super-Resolution for Accelerated Magnetic Resonance Imaging
Magnetic resonance (MR) image reconstruction and super-resolution are two prominent techniques to restore high-quality images from undersampled or low-resolution k-space data to accelerate MR imaging. Combining undersampled and low-resolution acquisition can further improve the acceleration factor. Existing methods often treat the techniques of image reconstruction and super-resolution separately or combine them sequentially for image recovery, which can result in error propagation and suboptimal results. In this work, we propose a novel framework for joint image reconstruction and super-resolution, aiming to efficiently image recovery and enable fast imaging. Specifically, we designed a framework with a reconstruction module and a super-resolution module to formulate multi-task learning. The reconstruction module utilizes a model-based optimization approach, ensuring data fidelity with the acquired k-space data. Moreover, a deep spatial feature transform is employed to enhance the information transition between the two modules, facilitating better integration of image reconstruction and super-resolution. Experimental evaluations on two datasets demonstrate that our proposed method can provide superior performance both quantitatively and qualitatively.
- 21 September 2023
- Published by MDPI AG in Bioengineering
- Vol. 10 (9) , 1107
Open AccessJoint Image Reconstruction and Super-Resolution for Accelerated Magnetic Resonance Imaging
Magnetic resonance (MR) image reconstruction and super-resolution are two prominent techniques to restore high-quality images from undersampled or low-resolution k-space data to accelerate MR imaging. Combining undersampled and low-resolution acquisition can further improve the acceleration factor. Existing methods often treat the techniques of image reconstruction and super-resolution separately or combine them sequentially for image recovery, which can result in error propagation and suboptimal results. In this work, we propose a novel framework for joint image reconstruction and super-resolution, aiming to efficiently image recovery and enable fast imaging. Specifically, we designed a framework with a reconstruction module and a super-resolution module to formulate multi-task learning. The reconstruction module utilizes a model-based optimization approach, ensuring data fidelity with the acquired k-space data. Moreover, a deep spatial feature transform is employed to enhance the information transition between the two modules, facilitating better integration of image reconstruction and super-resolution. Experimental evaluations on two datasets demonstrate that our proposed method can provide superior performance both quantitatively and qualitatively.
- Open Access
SPIRiT-Diffusion: SPIRiT-driven Score-Based Generative Modeling for Vessel Wall imaging
Diffusion model is the most advanced method in image generation and has been successfully applied to MRI reconstruction. However, the existing methods do not consider the characteristics of multi-coil acquisition of MRI data. Therefore, we give a new diffusion model, called SPIRiT-Diffusion, based on the SPIRiT iterative reconstruction algorithm. Specifically, SPIRiT-Diffusion characterizes the prior distribution of coil-by-coil images by score matching and characterizes the k-space redundant prior between coils based on self-consistency. With sufficient prior constraint utilized, we achieve superior reconstruction results on the joint Intracranial and Carotid Vessel Wall imaging dataset.
Open AccessSPIRiT-Diffusion: SPIRiT-driven Score-Based Generative Modeling for Vessel Wall imaging
Diffusion model is the most advanced method in image generation and has been successfully applied to MRI reconstruction. However, the existing methods do not consider the characteristics of multi-coil acquisition of MRI data. Therefore, we give a new diffusion model, called SPIRiT-Diffusion, based on the SPIRiT iterative reconstruction algorithm. Specifically, SPIRiT-Diffusion characterizes the prior distribution of coil-by-coil images by score matching and characterizes the k-space redundant prior between coils based on self-consistency. With sufficient prior constraint utilized, we achieve superior reconstruction results on the joint Intracranial and Carotid Vessel Wall imaging dataset.
- Open Access
- 4 November 2022
- Published by MDPI AG in Bioengineering
- Vol. 9 (11) , 650
SelfCoLearn: Self-Supervised Collaborative Learning for Accelerating Dynamic MR Imaging
Lately, deep learning technology has been extensively investigated for accelerating dynamic magnetic resonance (MR) imaging, with encouraging progresses achieved. However, without fully sampled reference data for training, the current approaches may have limited abilities in recovering fine details or structures. To address this challenge, this paper proposes a self-supervised collaborative learning framework (SelfCoLearn) for accurate dynamic MR image reconstruction from undersampled k-space data directly. The proposed SelfCoLearn is equipped with three important components, namely, dual-network collaborative learning, reunderampling data augmentation and a special-designed co-training loss. The framework is flexible and can be integrated into various model-based iterative un-rolled networks. The proposed method has been evaluated on an in vivo dataset and was compared to four state-of-the-art methods. The results show that the proposed method possesses strong capabilities in capturing essential and inherent representations for direct reconstructions from the undersampled k-space data and thus enables high-quality and fast dynamic MR imaging.
- 4 November 2022
- Published by MDPI AG in Bioengineering
- Vol. 9 (11) , 650
Open AccessSelfCoLearn: Self-Supervised Collaborative Learning for Accelerating Dynamic MR Imaging
Lately, deep learning technology has been extensively investigated for accelerating dynamic magnetic resonance (MR) imaging, with encouraging progresses achieved. However, without fully sampled reference data for training, the current approaches may have limited abilities in recovering fine details or structures. To address this challenge, this paper proposes a self-supervised collaborative learning framework (SelfCoLearn) for accurate dynamic MR image reconstruction from undersampled k-space data directly. The proposed SelfCoLearn is equipped with three important components, namely, dual-network collaborative learning, reunderampling data augmentation and a special-designed co-training loss. The framework is flexible and can be integrated into various model-based iterative un-rolled networks. The proposed method has been evaluated on an in vivo dataset and was compared to four state-of-the-art methods. The results show that the proposed method possesses strong capabilities in capturing essential and inherent representations for direct reconstructions from the undersampled k-space data and thus enables high-quality and fast dynamic MR imaging.
- Open Access
Equilibrated Zeroth-Order Unrolled Deep Networks for Accelerated MRI
Recently, model-driven deep learning unrolls a certain iterative algorithm of a regularization model into a cascade network by replacing the first-order information (i.e., (sub)gradient or proximal operator) of the regularizer with a network module, which appears more explainable and predictable compared to common data-driven networks. Conversely, in theory, there is not necessarily such a functional regularizer whose first-order information matches the replaced network module, which means the network output may not be covered by the original regularization model. Moreover, up to now, there is also no theory to guarantee the global convergence and robustness (regularity) of unrolled networks under realistic assumptions. To bridge this gap, this paper propose to present a safeguarded methodology on network unrolling. Specifically, focusing on accelerated MRI, we unroll a zeroth-order algorithm, of which the network module represents the regularizer itself, so that the network output can be still covered by the regularization model. Furthermore, inspired by the ideal of deep equilibrium models, before backpropagating, we carry out the unrolled iterative network to converge to a fixed point to ensure the convergence. In case the measurement data contains noise, we prove that the proposed network is robust against noisy interference. Finally, numerical experiments show that the proposed network consistently outperforms the state-of-the-art MRI reconstruction methods including traditional regularization methods and other deep learning methods.
Open AccessEquilibrated Zeroth-Order Unrolled Deep Networks for Accelerated MRI
Recently, model-driven deep learning unrolls a certain iterative algorithm of a regularization model into a cascade network by replacing the first-order information (i.e., (sub)gradient or proximal operator) of the regularizer with a network module, which appears more explainable and predictable compared to common data-driven networks. Conversely, in theory, there is not necessarily such a functional regularizer whose first-order information matches the replaced network module, which means the network output may not be covered by the original regularization model. Moreover, up to now, there is also no theory to guarantee the global convergence and robustness (regularity) of unrolled networks under realistic assumptions. To bridge this gap, this paper propose to present a safeguarded methodology on network unrolling. Specifically, focusing on accelerated MRI, we unroll a zeroth-order algorithm, of which the network module represents the regularizer itself, so that the network output can be still covered by the regularization model. Furthermore, inspired by the ideal of deep equilibrium models, before backpropagating, we carry out the unrolled iterative network to converge to a fixed point to ensure the convergence. In case the measurement data contains noise, we prove that the proposed network is robust against noisy interference. Finally, numerical experiments show that the proposed network consistently outperforms the state-of-the-art MRI reconstruction methods including traditional regularization methods and other deep learning methods.
- 1 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Imaging
- Vol. 7 (25730436) , 1314-1327
Deep Manifold Learning for Dynamic MR Imaging
Recently, low-dimensional manifold regularization has been recognized as a competitive method for accelerated cardiac MRI, due to its ability to capture temporal correlations. However, existing methods have not been performed with the nonlinear structure of an underlying manifold. In this paper, we propose a deep learning method in an unrolling manner for accelerated cardiac MRI on a low-dimensional manifold. Specifically, a fixed low-rank tensor (Riemannian) manifold is chosen to capture the strong temporal correlations of dynamic signals; the reconstruction problem is modeled as a CS-based optimization problem on this manifold. Following the manifold structure, a Riemannian gradient descent (RGD) method is adopted to solve this problem. Finally, the RGD algorithm is unrolled into a neural network, called Manifold-Net, on the manifold to avoid the long computation time and the challenging parameter selection. The experimental results at high accelerations demonstrate that the proposed method can obtain improved reconstruction compared with three conventional methods (k-t SLR, SToRM and k-t MLSD) and three state-of-the-art deep learning-based methods (DC-CNN, CRNN, and SLR-Net). To our knowledge, this work represents the first study to unroll the iterative optimization procedure into neural networks on manifolds. Moreover, the designed Manifold-Net provides a new mechanism for low-rank priors in dynamic MRI and should also prove useful for fast reconstruction in other dynamic imaging problems.
- 1 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Imaging
- Vol. 7 (25730436) , 1314-1327
Deep Manifold Learning for Dynamic MR Imaging
Recently, low-dimensional manifold regularization has been recognized as a competitive method for accelerated cardiac MRI, due to its ability to capture temporal correlations. However, existing methods have not been performed with the nonlinear structure of an underlying manifold. In this paper, we propose a deep learning method in an unrolling manner for accelerated cardiac MRI on a low-dimensional manifold. Specifically, a fixed low-rank tensor (Riemannian) manifold is chosen to capture the strong temporal correlations of dynamic signals; the reconstruction problem is modeled as a CS-based optimization problem on this manifold. Following the manifold structure, a Riemannian gradient descent (RGD) method is adopted to solve this problem. Finally, the RGD algorithm is unrolled into a neural network, called Manifold-Net, on the manifold to avoid the long computation time and the challenging parameter selection. The experimental results at high accelerations demonstrate that the proposed method can obtain improved reconstruction compared with three conventional methods (k-t SLR, SToRM and k-t MLSD) and three state-of-the-art deep learning-based methods (DC-CNN, CRNN, and SLR-Net). To our knowledge, this work represents the first study to unroll the iterative optimization procedure into neural networks on manifolds. Moreover, the designed Manifold-Net provides a new mechanism for low-rank priors in dynamic MRI and should also prove useful for fast reconstruction in other dynamic imaging problems.
- 1 July 2019
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 64 (14) , 14NT01
Improving GRAPPA reconstruction using joint nonlinear kernel mapped and phase conjugated virtual coils
To improve the reconstruction condition and alleviate the noise amplification of GRAPPA reconstruction by aggregating the phase conjugated and nonlinear kernel mapped coils with the original physical coil. Nonlinear GRAPPA (NL-GRAPPA) is a kernel-based non-iterative approach which can reduce noise-induced error in GRAPPA reconstruction. And virtual conjugate coil (VCC) embeds the conjugate symmetric property of k -space into GRAPPA data synthesis to improve reconstruction condition. This work proposed NL-VCC-GRAPPA to jointly utilize the nonlinear mapped virtual coil and phase conjugated virtual coil to further reduce noise amplification in parallel imaging. In vivo static and dynamic 2D imaging accelerated by uniform undersampling schemes were performed to evaluate the proposed method in terms of visual image quality, root-mean-square-error (RMSE), and geometry factor ( g -factor). The effects of acceleration factors, calibration data size and kernel shape on the proposed model were also separately analyzed and discussed. The proposed method illustrated improved visual image quality evidenced by reduced retrospective RMSE and prospective g -factor comparing with conventional GRAPPA and the recently proposed iterative SENSE-LORAKS reconstructions. Although a larger amount of calibration data and smaller kernel size were required to stabilize the calibration of fourfold extended kernel for the proposed method, it was non-iterative and relatively insensitive to parameter adjustment in the applications. The proposed NL-VCC-extension to conventional GRAPPA brings visible improvements for imaging scenarios accelerated by the widely available uniform undersampling schemes in a practically efficient manner without iteration.
- 1 July 2019
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 64 (14) , 14NT01
Improving GRAPPA reconstruction using joint nonlinear kernel mapped and phase conjugated virtual coils
To improve the reconstruction condition and alleviate the noise amplification of GRAPPA reconstruction by aggregating the phase conjugated and nonlinear kernel mapped coils with the original physical coil. Nonlinear GRAPPA (NL-GRAPPA) is a kernel-based non-iterative approach which can reduce noise-induced error in GRAPPA reconstruction. And virtual conjugate coil (VCC) embeds the conjugate symmetric property of k -space into GRAPPA data synthesis to improve reconstruction condition. This work proposed NL-VCC-GRAPPA to jointly utilize the nonlinear mapped virtual coil and phase conjugated virtual coil to further reduce noise amplification in parallel imaging. In vivo static and dynamic 2D imaging accelerated by uniform undersampling schemes were performed to evaluate the proposed method in terms of visual image quality, root-mean-square-error (RMSE), and geometry factor ( g -factor). The effects of acceleration factors, calibration data size and kernel shape on the proposed model were also separately analyzed and discussed. The proposed method illustrated improved visual image quality evidenced by reduced retrospective RMSE and prospective g -factor comparing with conventional GRAPPA and the recently proposed iterative SENSE-LORAKS reconstructions. Although a larger amount of calibration data and smaller kernel size were required to stabilize the calibration of fourfold extended kernel for the proposed method, it was non-iterative and relatively insensitive to parameter adjustment in the applications. The proposed NL-VCC-extension to conventional GRAPPA brings visible improvements for imaging scenarios accelerated by the widely available uniform undersampling schemes in a practically efficient manner without iteration.