Minhua Lu
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
Minhua Lu has a total of 138 co-authors. Here are the top co-authors by number of shared publications:
- Rui Mao
Shenzhen University
8 shared publications Haoteng Zheng
Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Health Science Center, Shenzhen University, 518060, China
4 shared publications- Heye Zhang
Sun Yat-sen University
4 shared publications - Jun Shi
School of Communication and Information Engineering, Shanghai University, Shanghai, China
4 shared publications - Siping Chen
Shenzhen University Medical School, Shenzhen University
4 shared publications - Xin Chen
College of Art and Design, Division of Arts, Shenzhen University
4 shared publications
Latest Publications
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 73 (10) , 3349-3359
SW-VEI-Net: A Physics-Informed Deep Neural Network for Shear Wave Viscoelasticity Imaging
Quantitative viscoelasticity imaging via shear wave elastography (SWE) remains challenging due to complex wave physics and limitations of conventional reconstruction methods. To address this, we present SW-VEI-Net, a physics-informed neural network (PINN) that simultaneously reconstructs the shear elastic modulus and viscous modulus by integrating viscoelastic wave equations into a dual-network architecture. The framework employs a dual-loss function to balance data fidelity and physics-based regularization, significantly reducing reliance on empirical data while improving interpretability. Extensive validation on tissue-mimicking phantoms, rat liver fibrosis model, and clinical cases demonstrates that SW-VEI-Net outperforms state-of-the-art SWE methods. Compared to SWENet (a PINN-based method using a linear elastic model), SW-VEI-Net not only enables simultaneous assessment of shear elastic and viscous moduli, but also achieves higher accuracy in shear elastic modulus reconstruction. Furthermore, when benchmarked against the dispersion fitting (DF) method (based on a viscoelastic model), SW-VEI-Net produces comparable viscoelastic parameter maps while exhibiting enhanced robustness and consistency. For liver fibrosis staging, SW-VEI-Net achieves AUC values of 0.85 ($\geq$F2) and 0.91 ($=$F4) based on elastic modulus classification, surpassing both SWENet (0.84, 0.85) and DF (0.78, 0.88). Additional validation in healthy volunteers shows strong agreement with a commercial ultrasound system. By synergizing deep learning with fundamental wave physics, this study represents a significant advancement in SWE, offering substantial clinical potential for early detection of hepatic fibrosis and malignant lesions through precise viscoelastic biomarker mapping.
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 73 (10) , 3349-3359
SW-VEI-Net: A Physics-Informed Deep Neural Network for Shear Wave Viscoelasticity Imaging
Quantitative viscoelasticity imaging via shear wave elastography (SWE) remains challenging due to complex wave physics and limitations of conventional reconstruction methods. To address this, we present SW-VEI-Net, a physics-informed neural network (PINN) that simultaneously reconstructs the shear elastic modulus and viscous modulus by integrating viscoelastic wave equations into a dual-network architecture. The framework employs a dual-loss function to balance data fidelity and physics-based regularization, significantly reducing reliance on empirical data while improving interpretability. Extensive validation on tissue-mimicking phantoms, rat liver fibrosis model, and clinical cases demonstrates that SW-VEI-Net outperforms state-of-the-art SWE methods. Compared to SWENet (a PINN-based method using a linear elastic model), SW-VEI-Net not only enables simultaneous assessment of shear elastic and viscous moduli, but also achieves higher accuracy in shear elastic modulus reconstruction. Furthermore, when benchmarked against the dispersion fitting (DF) method (based on a viscoelastic model), SW-VEI-Net produces comparable viscoelastic parameter maps while exhibiting enhanced robustness and consistency. For liver fibrosis staging, SW-VEI-Net achieves AUC values of 0.85 ($\geq$F2) and 0.91 ($=$F4) based on elastic modulus classification, surpassing both SWENet (0.84, 0.85) and DF (0.78, 0.88). Additional validation in healthy volunteers shows strong agreement with a commercial ultrasound system. By synergizing deep learning with fundamental wave physics, this study represents a significant advancement in SWE, offering substantial clinical potential for early detection of hepatic fibrosis and malignant lesions through precise viscoelastic biomarker mapping.
- 8 October 2025
- Published by Springer Nature
- p. 94-102
Variance-Based Pivot Selection for Metric Spaces
- 8 October 2025
- Published by Springer Nature
- p. 415-423
Memory-Constrained DiskANN: Efficient Approximate Nearest Neighbor Search Under Resource Constraints
- 8 October 2025
- Published by Springer Nature
- p. 415-423
Memory-Constrained DiskANN: Efficient Approximate Nearest Neighbor Search Under Resource Constraints
- 23 September 2025
- Published by Elsevier in Academic Radiology
- Vol. 32 (12) , 7419-7429
Quantitation of Acute Extremity Compartment Syndrome in Rabbits Using Shear-wave Elastography to Assess Viscoelasticity
- 23 September 2025
- Published by Elsevier in Academic Radiology
- Vol. 32 (12) , 7419-7429
Quantitation of Acute Extremity Compartment Syndrome in Rabbits Using Shear-wave Elastography to Assess Viscoelasticity
- Open Access
- 1 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 44 (7) , 3089-3099
High-Frequency Modulated Transformer for Multi-Contrast MRI Super-Resolution
Accelerating the MRI acquisition process is always a key issue in modern medical practice, and great efforts have been devoted to fast MR imaging. Among them, multi-contrast MR imaging is a promising and effective solution that utilizes and combines information from different contrasts. However, existing methods may ignore the importance of the high-frequency priors among different contrasts. Moreover, they may lack an efficient method to fully utilize the information from the reference contrast. In this paper, we propose a lightweight and accurate High-frequency Modulated Transformer (HFMT) for multi-contrast MRI super-resolution. The key ideas of HFMT are high-frequency prior enhancement and its fusion with global features. Specifically, we employ an enhancement module to enhance and amplify the high-frequency priors in the reference and target modalities. In addition, we utilize the Rectangle Window Transformer Block (RWTB) to capture global information in the target contrast. Meanwhile, we propose a novel cross-attention mechanism to fuse the high-frequency enhanced features with the global features sequentially, which assists the network in recovering clear texture details from the low-resolution inputs. Extensive experiments show that our proposed method can reconstruct high-quality images with fewer parameters and faster inference time.
- 1 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 44 (7) , 3089-3099
Open AccessHigh-Frequency Modulated Transformer for Multi-Contrast MRI Super-Resolution
Accelerating the MRI acquisition process is always a key issue in modern medical practice, and great efforts have been devoted to fast MR imaging. Among them, multi-contrast MR imaging is a promising and effective solution that utilizes and combines information from different contrasts. However, existing methods may ignore the importance of the high-frequency priors among different contrasts. Moreover, they may lack an efficient method to fully utilize the information from the reference contrast. In this paper, we propose a lightweight and accurate High-frequency Modulated Transformer (HFMT) for multi-contrast MRI super-resolution. The key ideas of HFMT are high-frequency prior enhancement and its fusion with global features. Specifically, we employ an enhancement module to enhance and amplify the high-frequency priors in the reference and target modalities. In addition, we utilize the Rectangle Window Transformer Block (RWTB) to capture global information in the target contrast. Meanwhile, we propose a novel cross-attention mechanism to fuse the high-frequency enhanced features with the global features sequentially, which assists the network in recovering clear texture details from the low-resolution inputs. Extensive experiments show that our proposed method can reconstruct high-quality images with fewer parameters and faster inference time.
- 25 April 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 283
Fast MRI reconstruction: A thorough survey from single-modal to multi-modal
- 25 April 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 283
Fast MRI reconstruction: A thorough survey from single-modal to multi-modal
- 20 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-15
A Novel Model-Based Conductivity Reconstruction in Magneto-Acousto-Electrical Tomography (MAET): Simulation and Experiment Study
Magneto-acousto-electrical tomography (MAET), which combines ultrasound imaging with electrical impedance tomography, offers high resolution and high contrast for mapping the internal conductivity distribution of an object. However, it is a challenge to reconstruct the conductivity distribution containing the interior information due to practical system constraints. A significant issue is the limited bandwidth of experimental systems, especially the ultrasound transducer, which can filter out low-frequency components of the measurement signal. Inspired by the multi-compartment model paradigm in diffusion MRI, we propose an innovative model-based approach to address this conductivity reconstruction challenge. The object’s conductivity is constrained by the weighted sum of shifted jump models, dramatically reducing the problem’s degrees of freedom. By deriving the measurement signal based on the proposed model, we can extract the conductivity polarity using an overdetermined linear system solved by the least-squares method. Furthermore, by integrating amplitude information from conventional conductivity parameter images with the extracted conductivity polarity, we reconstruct the final relative conductivity distribution. Our methodology has been rigorously tested through numerical simulations with various noise levels (20%, 40%, and 60%), phantom experiments, and pork tissue comparisons against the state-of-the-art method. The results demonstrate that our method offers superior accuracy and stability compared to existing techniques in case of all evaluation metrics RMSE, SSIM, PSNR. In conclusion, our proposed method is straightforward to implement and applicable in both simulations and practical experiments, providing a potential strategy for conductivity reconstruction in complex objects in the future.
- 20 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-15
A Novel Model-Based Conductivity Reconstruction in Magneto-Acousto-Electrical Tomography (MAET): Simulation and Experiment Study
Magneto-acousto-electrical tomography (MAET), which combines ultrasound imaging with electrical impedance tomography, offers high resolution and high contrast for mapping the internal conductivity distribution of an object. However, it is a challenge to reconstruct the conductivity distribution containing the interior information due to practical system constraints. A significant issue is the limited bandwidth of experimental systems, especially the ultrasound transducer, which can filter out low-frequency components of the measurement signal. Inspired by the multi-compartment model paradigm in diffusion MRI, we propose an innovative model-based approach to address this conductivity reconstruction challenge. The object’s conductivity is constrained by the weighted sum of shifted jump models, dramatically reducing the problem’s degrees of freedom. By deriving the measurement signal based on the proposed model, we can extract the conductivity polarity using an overdetermined linear system solved by the least-squares method. Furthermore, by integrating amplitude information from conventional conductivity parameter images with the extracted conductivity polarity, we reconstruct the final relative conductivity distribution. Our methodology has been rigorously tested through numerical simulations with various noise levels (20%, 40%, and 60%), phantom experiments, and pork tissue comparisons against the state-of-the-art method. The results demonstrate that our method offers superior accuracy and stability compared to existing techniques in case of all evaluation metrics RMSE, SSIM, PSNR. In conclusion, our proposed method is straightforward to implement and applicable in both simulations and practical experiments, providing a potential strategy for conductivity reconstruction in complex objects in the future.
- 26 February 2025
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 70 (5) , 055014
CycleH-CUT: an unsupervised medical image translation method based on cycle consistency and hybrid contrastive learning
Unsupervised medical image translation tasks are challenging due to the difficulty of obtaining perfectly paired medical images. CycleGAN-based methods have proven effective in unpaired medical image translation. However, these methods can produce artifacts in the generated medical images. To address this issue, we propose an unsupervised network based on cycle consistency and hybrid contrastive unpaired translation (CycleH-CUT). CycleH-CUT consists of two CUT (H-CUT) networks. In the H-CUT network, a query-selected attention mechanism is adopted to select queries with important features. The boosted contrastive learning loss is employed to reweight all negative patches via the optimal transport strategy. We further apply spectral normalization to improve training stability, allowing the generator to extract complex features. On the basis of the H-CUT network, a new CycleH-CUT framework is proposed to integrate contrastive learning and cycle consistency. Two H-CUT networks are used to reconstruct the generated images back to the source domain, facilitating effective translation between unpaired medical images. We conduct extensive experiments on three public datasets (BraTS, OASIS3, and IXI) and a private Spinal Column dataset to demonstrate the effectiveness of CycleH-CUT and H-CUT. Specifically, CycleH-CUT achieves an average SSIM of 0.926 in the BraTS dataset, an average SSIM of 0.796 on the OASIS3 dataset, an average SSIM of 0.932 on the IXI dataset, and an average SSIM of 0.890 on the private Spinal Column dataset.
- 26 February 2025
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 70 (5) , 055014
CycleH-CUT: an unsupervised medical image translation method based on cycle consistency and hybrid contrastive learning
Unsupervised medical image translation tasks are challenging due to the difficulty of obtaining perfectly paired medical images. CycleGAN-based methods have proven effective in unpaired medical image translation. However, these methods can produce artifacts in the generated medical images. To address this issue, we propose an unsupervised network based on cycle consistency and hybrid contrastive unpaired translation (CycleH-CUT). CycleH-CUT consists of two CUT (H-CUT) networks. In the H-CUT network, a query-selected attention mechanism is adopted to select queries with important features. The boosted contrastive learning loss is employed to reweight all negative patches via the optimal transport strategy. We further apply spectral normalization to improve training stability, allowing the generator to extract complex features. On the basis of the H-CUT network, a new CycleH-CUT framework is proposed to integrate contrastive learning and cycle consistency. Two H-CUT networks are used to reconstruct the generated images back to the source domain, facilitating effective translation between unpaired medical images. We conduct extensive experiments on three public datasets (BraTS, OASIS3, and IXI) and a private Spinal Column dataset to demonstrate the effectiveness of CycleH-CUT and H-CUT. Specifically, CycleH-CUT achieves an average SSIM of 0.926 in the BraTS dataset, an average SSIM of 0.796 on the OASIS3 dataset, an average SSIM of 0.932 on the IXI dataset, and an average SSIM of 0.890 on the private Spinal Column dataset.
- 3 February 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 272
A priority-guided contrastive network for delineating vascular layers in arterial ultrasound
- 3 February 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 272
A priority-guided contrastive network for delineating vascular layers in arterial ultrasound