Juexin Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Juexin Zhang has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Ying Weng
University of Nottingham Ningbo China
10 shared publications - Ke Chen
University of Nottingham Ningbo China
8 shared publications - Qifeng Zhong
University of Nottingham Ningbo China 315100 Ningbo China
2 shared publications Boding Wang
1 shared publication- Guoping Qiu
Guangdong Key Laboratory for Intelligent Information Processing, Shenzhen University, Shenzhen, China
1 shared publication Rong Huang
1 shared publication
Latest Publications
- 2 February 2027
- Published by Springer Nature
- p. 455-461
Deep Learning for Glioblastoma Morpho-Pathological Features Identification: A BraTS-Pathology Challenge Solution
- 2 February 2027
- Published by Springer Nature
- p. 455-461
Deep Learning for Glioblastoma Morpho-Pathological Features Identification: A BraTS-Pathology Challenge Solution
- 2 February 2027
- Published by Springer Nature
- p. 569-575
U-Net Based Healthy 3D Brain Tissue Inpainting
- 8 September 2026
- Published by World Scientific Pub Co Pte Ltd in International Journal of Neural Systems
- Vol. 37 (04) , 2750019
Neural Stability Enhancement Through Dynamic Lipschitz Constraints in Generative Adversarial Networks
Generative adversarial networks (GANs) are widely used for generative modeling in neural networks, yet their practical use is hindered by training instability and mode collapse. Existing stabilization approaches predominantly rely on enforcing fixed 1-Lipschitz constraints on the discriminator through techniques such as gradient penalty, spectral normalization, and gradient normalization. However, these methods fail to account for the dynamic nature of neural network training, where the appropriate Lipschitz constant target may vary with evolving system dynamics. This work challenges the conventional fixed-constraint paradigm by formalizing how the effective constraint strength and a bound-implied Lipschitz constant target can depend on architecture and training state. We provide theoretical analysis to motivate adaptive Lipschitz constraint (ALC) control and introduce ALC, a modular mechanism that adjusts the Lipschitz constant target rather than introducing another standalone regularization term. Experiments across multiple stable GAN architectures show improvements in generation quality and training stability in several evaluated settings. Our contributions advance the understanding of neural system stability in adversarial learning and provide a practical approach to ALC control in adversarial objectives.
- 8 September 2026
- Published by World Scientific Pub Co Pte Ltd in International Journal of Neural Systems
- Vol. 37 (04) , 2750019
Neural Stability Enhancement Through Dynamic Lipschitz Constraints in Generative Adversarial Networks
Generative adversarial networks (GANs) are widely used for generative modeling in neural networks, yet their practical use is hindered by training instability and mode collapse. Existing stabilization approaches predominantly rely on enforcing fixed 1-Lipschitz constraints on the discriminator through techniques such as gradient penalty, spectral normalization, and gradient normalization. However, these methods fail to account for the dynamic nature of neural network training, where the appropriate Lipschitz constant target may vary with evolving system dynamics. This work challenges the conventional fixed-constraint paradigm by formalizing how the effective constraint strength and a bound-implied Lipschitz constant target can depend on architecture and training state. We provide theoretical analysis to motivate adaptive Lipschitz constraint (ALC) control and introduce ALC, a modular mechanism that adjusts the Lipschitz constant target rather than introducing another standalone regularization term. Experiments across multiple stable GAN architectures show improvements in generation quality and training stability in several evaluated settings. Our contributions advance the understanding of neural system stability in adversarial learning and provide a practical approach to ALC control in adversarial objectives.
- Open Access
- 15 May 2026
- Published by Elsevier in Neurocomputing
- Vol. 697
Purifying medical images with generative adversarial networks
- 15 May 2026
- Published by Elsevier in Neurocomputing
- Vol. 697
Open AccessPurifying medical images with generative adversarial networks
- 1 April 2026
- Published by Springer Nature
- p. 102-109
Robust 3D Brain MRI Inpainting with Random Masking Augmentation
- 1 April 2026
- Published by Springer Nature
- p. 102-109
Robust 3D Brain MRI Inpainting with Random Masking Augmentation
- 1 April 2026
- Published by Springer Nature
- p. 193-202
Patch-Level Glioblastoma Subregion Classification with a Contrastive Learning-Based Encoder
- 1 April 2026
- Published by Springer Nature
- p. 193-202
Patch-Level Glioblastoma Subregion Classification with a Contrastive Learning-Based Encoder
- Open Access
Robust 3D Brain MRI Inpainting with Random Masking Augmentation
The ASNR-MICCAI BraTS-Inpainting Challenge was established to mitigate dataset biases that limit deep learning models in the quantitative analysis of brain tumor MRI. This paper details our submission to the 2025 challenge, a novel deep learning framework for synthesizing healthy tissue in 3D scans. The core of our method is a U-Net architecture trained to inpaint synthetically corrupted regions, enhanced with a random masking augmentation strategy to improve generalization. Quantitative evaluation confirmed the efficacy of our approach, yielding an SSIM of 0.873$\pm$0.004, a PSNR of 24.996$\pm$4.694, and an MSE of 0.005$\pm$0.087 on the validation set. On the final online test set, our method achieved an SSIM of 0.919$\pm$0.088, a PSNR of 26.932$\pm$5.057, and an RMSE of 0.052$\pm$0.026. This performance secured first place in the BraTS-Inpainting 2025 challenge and surpassed the winning solutions from the 2023 and 2024 competitions on the official leaderboard.
Open AccessRobust 3D Brain MRI Inpainting with Random Masking Augmentation
The ASNR-MICCAI BraTS-Inpainting Challenge was established to mitigate dataset biases that limit deep learning models in the quantitative analysis of brain tumor MRI. This paper details our submission to the 2025 challenge, a novel deep learning framework for synthesizing healthy tissue in 3D scans. The core of our method is a U-Net architecture trained to inpaint synthetically corrupted regions, enhanced with a random masking augmentation strategy to improve generalization. Quantitative evaluation confirmed the efficacy of our approach, yielding an SSIM of 0.873$\pm$0.004, a PSNR of 24.996$\pm$4.694, and an MSE of 0.005$\pm$0.087 on the validation set. On the final online test set, our method achieved an SSIM of 0.919$\pm$0.088, a PSNR of 26.932$\pm$5.057, and an RMSE of 0.052$\pm$0.026. This performance secured first place in the BraTS-Inpainting 2025 challenge and surpassed the winning solutions from the 2023 and 2024 competitions on the official leaderboard.
- Open Access
Patch-Level Glioblastoma Subregion Classification with a Contrastive Learning-Based Encoder
The significant molecular and pathological heterogeneity of glioblastoma, an aggressive brain tumor, complicates diagnosis and patient stratification. While traditional histopathological assessment remains the standard, deep learning offers a promising path toward objective and automated analysis of whole slide images. For the BraTS-Path 2025 Challenge, we developed a method that fine-tunes a pre-trained Vision Transformer (ViT) encoder with a dedicated classification head on the official training dataset. Our model's performance on the online validation set, evaluated via the Synapse platform, yielded a Matthews Correlation Coefficient (MCC) of 0.7064 and an F1-score of 0.7676. On the final test set, the model achieved an MCC of 0.6509 and an F1-score of 0.5330, which secured our team second place in the BraTS-Pathology 2025 Challenge. Our results establish a solid baseline for ViT-based histopathological analysis, and future efforts will focus on bridging the performance gap observed on the unseen validation data.
Open AccessPatch-Level Glioblastoma Subregion Classification with a Contrastive Learning-Based Encoder
The significant molecular and pathological heterogeneity of glioblastoma, an aggressive brain tumor, complicates diagnosis and patient stratification. While traditional histopathological assessment remains the standard, deep learning offers a promising path toward objective and automated analysis of whole slide images. For the BraTS-Path 2025 Challenge, we developed a method that fine-tunes a pre-trained Vision Transformer (ViT) encoder with a dedicated classification head on the official training dataset. Our model's performance on the online validation set, evaluated via the Synapse platform, yielded a Matthews Correlation Coefficient (MCC) of 0.7064 and an F1-score of 0.7676. On the final test set, the model achieved an MCC of 0.6509 and an F1-score of 0.5330, which secured our team second place in the BraTS-Pathology 2025 Challenge. Our results establish a solid baseline for ViT-based histopathological analysis, and future efforts will focus on bridging the performance gap observed on the unseen validation data.
- Open Access
Deep Learning for Glioblastoma Morpho-pathological Features Identification: A BraTS-Pathology Challenge Solution
Glioblastoma, a highly aggressive brain tumor with diverse molecular and pathological features, poses a diagnostic challenge due to its heterogeneity. Accurate diagnosis and assessment of this heterogeneity are essential for choosing the right treatment and improving patient outcomes. Traditional methods rely on identifying specific features in tissue samples, but deep learning offers a promising approach for improved glioblastoma diagnosis. In this paper, we present our approach to the BraTS-Path Challenge 2024. We leverage a pre-trained model and fine-tune it on the BraTS-Path training dataset. Our model demonstrates poor performance on the challenging BraTS-Path validation set, as rigorously assessed by the Synapse online platform. The model achieves an accuracy of 0.392229, a recall of 0.392229, and a F1-score of 0.392229, indicating a consistent ability to correctly identify instances under the target condition. Notably, our model exhibits perfect specificity of 0.898704, showing an exceptional capacity to correctly classify negative cases. Moreover, a Matthews Correlation Coefficient (MCC) of 0.255267 is calculated, to signify a limited positive correlation between predicted and actual values and highlight our model's overall predictive power. Our solution also achieves the second place during the testing phase.
Open AccessDeep Learning for Glioblastoma Morpho-pathological Features Identification: A BraTS-Pathology Challenge Solution
Glioblastoma, a highly aggressive brain tumor with diverse molecular and pathological features, poses a diagnostic challenge due to its heterogeneity. Accurate diagnosis and assessment of this heterogeneity are essential for choosing the right treatment and improving patient outcomes. Traditional methods rely on identifying specific features in tissue samples, but deep learning offers a promising approach for improved glioblastoma diagnosis. In this paper, we present our approach to the BraTS-Path Challenge 2024. We leverage a pre-trained model and fine-tune it on the BraTS-Path training dataset. Our model demonstrates poor performance on the challenging BraTS-Path validation set, as rigorously assessed by the Synapse online platform. The model achieves an accuracy of 0.392229, a recall of 0.392229, and a F1-score of 0.392229, indicating a consistent ability to correctly identify instances under the target condition. Notably, our model exhibits perfect specificity of 0.898704, showing an exceptional capacity to correctly classify negative cases. Moreover, a Matthews Correlation Coefficient (MCC) of 0.255267 is calculated, to signify a limited positive correlation between predicted and actual values and highlight our model's overall predictive power. Our solution also achieves the second place during the testing phase.
- 28 December 2024
- Published by Springer Nature
- p. 233-240
Synthesis of Healthy Tissue Within Tumor Area via U-Net
- 28 December 2024
- Published by Springer Nature
- p. 233-240
Synthesis of Healthy Tissue Within Tumor Area via U-Net