Zheng Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zheng Li has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Jun Shi
School of Communication and Information Engineering, Shanghai University, Shanghai, China
5 shared publications - Jun Wang
School of Civil and Hydraulic Engineering, Hefei University of Technology, Hefei, China
4 shared publications - Shihui Ying
Shanghai University
4 shared publications - Hongjiang Wei
School of Physics, Zhejiang University, Hangzhou, China
2 shared publications - Zhiyang Lu
Key laboratory of Specialty Fiber Optics and Optical Access Networks, Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication, Shanghai Institute for Advanced Communication and Data Science, School of Communication and Information Engineering, Shanghai University, Shanghai, China
2 shared publications - Chaofeng Wang
School of Communication and Information Engineering, Shanghai University, Shanghai China
1 shared publication
Latest Publications
- 10 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 43 (3) , 902-915
Pseudo-Data Based Self-Supervised Federated Learning for Classification of Histopathological Images
Computer-aided diagnosis (CAD) can help pathologists improve diagnostic accuracy together with consistency and repeatability for cancers. However, the CAD models trained with the histopathological images only from a single center (hospital) generally suffer from the generalization problem due to the straining inconsistencies among different centers. In this work, we propose a pseudo-data based self-supervised federated learning (FL) framework, named SSL-FT-BT, to improve both the diagnostic accuracy and generalization of CAD models. Specifically, the pseudo histopathological images are generated from each center, which contain both inherent and specific properties corresponding to the real images in this center, but do not include the privacy information. These pseudo images are then shared in the central server for self-supervised learning (SSL) to pre-train the backbone of global mode. A multi-task SSL is then designed to effectively learn both the center-specific information and common inherent representation according to the data characteristics. Moreover, a novel Barlow Twins based FL (FL-BT) algorithm is proposed to improve the local training for the CAD models in each center by conducting model contrastive learning, which benefits the optimization of the global model in the FL procedure. The experimental results on four public histopathological image datasets indicate the effectiveness of the proposed SSL-FL-BT on both diagnostic accuracy and generalization.
- 10 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 43 (3) , 902-915
Pseudo-Data Based Self-Supervised Federated Learning for Classification of Histopathological Images
Computer-aided diagnosis (CAD) can help pathologists improve diagnostic accuracy together with consistency and repeatability for cancers. However, the CAD models trained with the histopathological images only from a single center (hospital) generally suffer from the generalization problem due to the straining inconsistencies among different centers. In this work, we propose a pseudo-data based self-supervised federated learning (FL) framework, named SSL-FT-BT, to improve both the diagnostic accuracy and generalization of CAD models. Specifically, the pseudo histopathological images are generated from each center, which contain both inherent and specific properties corresponding to the real images in this center, but do not include the privacy information. These pseudo images are then shared in the central server for self-supervised learning (SSL) to pre-train the backbone of global mode. A multi-task SSL is then designed to effectively learn both the center-specific information and common inherent representation according to the data characteristics. Moreover, a novel Barlow Twins based FL (FL-BT) algorithm is proposed to improve the local training for the CAD models in each center by conducting model contrastive learning, which benefits the optimization of the global model in the FL procedure. The experimental results on four public histopathological image datasets indicate the effectiveness of the proposed SSL-FL-BT on both diagnostic accuracy and generalization.
- 1 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 27 (7) , 3337-3348
Two-Stage Self-Supervised Cycle-Consistency Transformer Network for Reducing Slice Gap in MR Images
Magnetic resonance (MR) images are usually acquired with large slice gap in clinical practice, i.e. , low resolution (LR) along the through-plane direction. It is feasible to reduce the slice gap and reconstruct high-resolution (HR) images with the deep learning (DL) methods. To this end, the paired LR and HR images are generally required to train a DL model in a popular fully supervised manner. However, since the HR images are hardly acquired in clinical routine, it is difficult to get sufficient paired samples to train a robust model. Moreover, the widely used convolutional Neural Network (CNN) still cannot capture long-range image dependencies to combine useful information of similar contents, which are often spatially far away from each other across neighboring slices. To this end, a Two-stage Self-supervised Cycle-consistency Transformer Network (TSCTNet) is proposed to reduce the slice gap for MR images in this work. A novel self-supervised learning (SSL) strategy is designed with two stages respectively for robust network pre-training and specialized network refinement based on a cycle-consistency constraint. A hybrid Transformer and CNN structure is utilized to build an interpolation model, which explores both local and global slice representations. The experimental results on two public MR image datasets indicate that TSCTNet achieves superior performance over other compared SSL-based algorithms.
- 1 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 27 (7) , 3337-3348
Two-Stage Self-Supervised Cycle-Consistency Transformer Network for Reducing Slice Gap in MR Images
Magnetic resonance (MR) images are usually acquired with large slice gap in clinical practice, i.e. , low resolution (LR) along the through-plane direction. It is feasible to reduce the slice gap and reconstruct high-resolution (HR) images with the deep learning (DL) methods. To this end, the paired LR and HR images are generally required to train a DL model in a popular fully supervised manner. However, since the HR images are hardly acquired in clinical routine, it is difficult to get sufficient paired samples to train a robust model. Moreover, the widely used convolutional Neural Network (CNN) still cannot capture long-range image dependencies to combine useful information of similar contents, which are often spatially far away from each other across neighboring slices. To this end, a Two-stage Self-supervised Cycle-consistency Transformer Network (TSCTNet) is proposed to reduce the slice gap for MR images in this work. A novel self-supervised learning (SSL) strategy is designed with two stages respectively for robust network pre-training and specialized network refinement based on a cycle-consistency constraint. A hybrid Transformer and CNN structure is utilized to build an interpolation model, which explores both local and global slice representations. The experimental results on two public MR image datasets indicate that TSCTNet achieves superior performance over other compared SSL-based algorithms.
- 23 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. PP (21682194) , 1-12
Reconstruction of Quantitative Susceptibility Mapping from Total Field Maps with Local Field Maps Guided UU-Net
Quantitative susceptibility mapping (QSM) is an emerging computational technique based on the magnetic resonance imaging (MRI) phase signal, which can provide magnetic susceptibility values of tissues. The existing deep learning-based models mainly reconstruct QSM from local field maps. However, the complicated inconsecutive reconstruction steps not only accumulate errors for inaccurate estimation, but also are inefficient in clinical practice. To this end, a novel local field maps guided UU-Net with Self- and Cross-Guided Transformer (LGUU-SCT-Net) is proposed to reconstruct QSM directly from the total field maps. Specifically, we propose to additionally generate the local field maps as the auxiliary supervision during the training stage. This strategy decomposes the more complicated mapping from total maps to QSM into two relatively easier ones, effectively alleviating the difficulty of direct mapping. Meanwhile, an improved U-Net model, named LGUU-SCT-Net, is further designed to promote the nonlinear mapping ability. The long-range connections are designed between two sequentially stacked U-Nets to bring more feature fusions and facilitate the information flow. The Self- and Cross-Guided Transformer integrated into these connections further captures multi-scale channel-wise correlations and guides the fusion of multiscale transferred features, assisting in the more accurate reconstruction. The experimental results on an in-vivo dataset demonstrate the superior reconstruction results of our proposed algorithm.
- 23 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. PP (21682194) , 1-12
Reconstruction of Quantitative Susceptibility Mapping from Total Field Maps with Local Field Maps Guided UU-Net
Quantitative susceptibility mapping (QSM) is an emerging computational technique based on the magnetic resonance imaging (MRI) phase signal, which can provide magnetic susceptibility values of tissues. The existing deep learning-based models mainly reconstruct QSM from local field maps. However, the complicated inconsecutive reconstruction steps not only accumulate errors for inaccurate estimation, but also are inefficient in clinical practice. To this end, a novel local field maps guided UU-Net with Self- and Cross-Guided Transformer (LGUU-SCT-Net) is proposed to reconstruct QSM directly from the total field maps. Specifically, we propose to additionally generate the local field maps as the auxiliary supervision during the training stage. This strategy decomposes the more complicated mapping from total maps to QSM into two relatively easier ones, effectively alleviating the difficulty of direct mapping. Meanwhile, an improved U-Net model, named LGUU-SCT-Net, is further designed to promote the nonlinear mapping ability. The long-range connections are designed between two sequentially stacked U-Nets to bring more feature fusions and facilitate the information flow. The Self- and Cross-Guided Transformer integrated into these connections further captures multi-scale channel-wise correlations and guides the fusion of multiscale transferred features, assisting in the more accurate reconstruction. The experimental results on an in-vivo dataset demonstrate the superior reconstruction results of our proposed algorithm.
- 13 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Imaging
- Vol. 7 (25730436) , 1385-1399
Meta-Learning Based Interactively Connected Clique U-Net for Quantitative Susceptibility Mapping
Quantitative susceptibility mapping (QSM) is a phase-based magnetic resonance imaging (MRI) technique that quantitatively estimates magnetic susceptibility values of tissues and has shown great potential in clinical practice. However, the ill-posed dipole inversion greatly affects the estimation accuracy of the susceptibility values. In this work, an interactively connected clique U-Net (named ICCU-Net) is proposed to perform the nonlinear mapping from single-echo phase maps to QSM maps. The interactive connection provides hierarchical feature fusions and multi-scale representations for the recovery of detailed tissue and edges, while the embedded clique block further promotes the gradients and information flow. Besides, the time-consuming data acquisition results in small amounts of in-vivo data, which degrades the performance of the deep Learning (DL) based QSM reconstruction algorithm. A novel two-stage meta-learning strategy is further proposed for the ICCU-Net to promote the reconstruction quality with limited in-vivo data. Benefiting from large quantities of self-generated synthetic data, the ICCU-Net effectively learns the nonlinear mapping through multiple meta-tasks as the prior knowledge in the first-stage meta-learning. The learned model is then further improved on the in-vivo data through the second-stage meta-learning instead of being directly applied on them to reduce the distribution differences between the in-vivo and synthetic data. This novel two-stage procedure alleviates the issue of insufficient in-vivo data and provides more accurate reconstructed QSM maps. The experimental results demonstrate that the proposed algorithm outperforms other conventional and DL-based QSM reconstruction algorithms.
- 13 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Imaging
- Vol. 7 (25730436) , 1385-1399
Meta-Learning Based Interactively Connected Clique U-Net for Quantitative Susceptibility Mapping
Quantitative susceptibility mapping (QSM) is a phase-based magnetic resonance imaging (MRI) technique that quantitatively estimates magnetic susceptibility values of tissues and has shown great potential in clinical practice. However, the ill-posed dipole inversion greatly affects the estimation accuracy of the susceptibility values. In this work, an interactively connected clique U-Net (named ICCU-Net) is proposed to perform the nonlinear mapping from single-echo phase maps to QSM maps. The interactive connection provides hierarchical feature fusions and multi-scale representations for the recovery of detailed tissue and edges, while the embedded clique block further promotes the gradients and information flow. Besides, the time-consuming data acquisition results in small amounts of in-vivo data, which degrades the performance of the deep Learning (DL) based QSM reconstruction algorithm. A novel two-stage meta-learning strategy is further proposed for the ICCU-Net to promote the reconstruction quality with limited in-vivo data. Benefiting from large quantities of self-generated synthetic data, the ICCU-Net effectively learns the nonlinear mapping through multiple meta-tasks as the prior knowledge in the first-stage meta-learning. The learned model is then further improved on the in-vivo data through the second-stage meta-learning instead of being directly applied on them to reduce the distribution differences between the in-vivo and synthetic data. This novel two-stage procedure alleviates the issue of insufficient in-vivo data and provides more accurate reconstructed QSM maps. The experimental results demonstrate that the proposed algorithm outperforms other conventional and DL-based QSM reconstruction algorithms.
- 4 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 23 (3) , 1129-1140
MR Image Super-Resolution via Wide Residual Networks With Fixed Skip Connection
Spatial resolution is a critical imaging parameter in magnetic resonance imaging (MRI). The image super-resolution (SR) is an effective and cost efficient alternative technique to improve the spatial resolution of MR images. Over the past several years, the convolutional neural networks (CNN)-based SR methods have achieved state-of-the-art performance. However, CNNs with very deep network structures usually suffer from the problems of degradation and diminishing feature reuse, which add difficulty to network training and degenerate the transmission capability of details for SR. To address these problems, in this work, a progressive wide residual network with a fixed skip connection (named FSCWRN) based SR algorithm is proposed to reconstruct MR images, which combines the global residual learning and the shallow network based local residual learning. The strategy of progressive wide networks is adopted to replace deeper networks, which can partially relax the abovementioned problems, while a fixed skip connection helps provide rich local details at high frequencies from a fixed shallow layer network to subsequent networks. The experimental results on one simulated MR image database and three real MR image databases show the effectiveness of the proposed FSCWRN SR algorithm, which achieves improved reconstruction performance compared with other algorithms.
- 4 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 23 (3) , 1129-1140
MR Image Super-Resolution via Wide Residual Networks With Fixed Skip Connection
Spatial resolution is a critical imaging parameter in magnetic resonance imaging (MRI). The image super-resolution (SR) is an effective and cost efficient alternative technique to improve the spatial resolution of MR images. Over the past several years, the convolutional neural networks (CNN)-based SR methods have achieved state-of-the-art performance. However, CNNs with very deep network structures usually suffer from the problems of degradation and diminishing feature reuse, which add difficulty to network training and degenerate the transmission capability of details for SR. To address these problems, in this work, a progressive wide residual network with a fixed skip connection (named FSCWRN) based SR algorithm is proposed to reconstruct MR images, which combines the global residual learning and the shallow network based local residual learning. The strategy of progressive wide networks is adopted to replace deeper networks, which can partially relax the abovementioned problems, while a fixed skip connection helps provide rich local details at high frequencies from a fixed shallow layer network to subsequent networks. The experimental results on one simulated MR image database and three real MR image databases show the effectiveness of the proposed FSCWRN SR algorithm, which achieves improved reconstruction performance compared with other algorithms.