Moyan Cao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Moyan Cao has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Junli Zhao
College of Computer Science and Technology, Qingdao University, Qingdao, China
2 shared publications - Weibo Wei
College of Computer Science and Technology, Qingdao University, Qingdao, China
2 shared publications - Xueying Li
College of Computer Science and Technology, Qingdao University, 308 Ningxia Road, Qingdao 266071, China
2 shared publications - Zhenkuan Pan
College of Computer Science and Technology, Qingdao University, Qingdao, China
2 shared publications - Guangyu Yang
College of Computer Science and Technology, Qingdao University, 308, Ningxia Road, Qingdao 266071, China
1 shared publication - Jinming Duan
University of Birmingham
1 shared publication
Latest Publications
- Open Access
- 1 January 2026
- Published by American Institute of Mathematical Sciences (AIMS) in Mathematical Foundations of Computing
- Vol. 13, 84-106
DUM-Net: A model-driven unrolled framework for multi-modal image registration
Multi-modal image registration (MIR) remains a challenging problem due to severe appearance discrepancies across imaging modalities and the limited adaptability of handcrafted similarity measures. While deep learning methods have shown strong empirical performance, many existing architectures do not explicitly incorporate physical deformation priors. In this work, we propose DUM-Net, a model-driven deep unrolling framework for multi-modal image registration. Starting from a variational MIR model with a similarity term and a regularization term, we unroll a time-discrete gradient descent process into a layer-wise trainable architecture. DUM-Net consists of three components: an initialization module (IM), an adaptive similarity module (ASM), and a linear elasticity module (LEM). The IM provides deformation initialization to accelerate convergence. The ASM employs a deep neural network to learn an adaptive descent direction for cross-modal matching, thereby overcoming the limitations of handcrafted similarity functionals. The LEM introduces a parameterized linear-elastic prior during forward propagation to encourage smooth and physically plausible deformation fields. In this way, DUM-Net combines the flexibility of learned similarity modeling with the structural guidance of variational unrolling and explicit physical regularization. Experiments on T1/T2 MR, CT/MR, and FL/IR registration tasks demonstrate that DUM-Net consistently outperforms existing methods, achieving Dice score improvements of 3.74% for small and 6.16% for large deformations on T1/T2 MR image pairs, together with strong performance on CT/MR and FL/IR datasets. The source code is publicly available at https://github.com/QDUJackson/DUM-Net.
- 1 January 2026
- Published by American Institute of Mathematical Sciences (AIMS) in Mathematical Foundations of Computing
- Vol. 13, 84-106
Open AccessDUM-Net: A model-driven unrolled framework for multi-modal image registration
Multi-modal image registration (MIR) remains a challenging problem due to severe appearance discrepancies across imaging modalities and the limited adaptability of handcrafted similarity measures. While deep learning methods have shown strong empirical performance, many existing architectures do not explicitly incorporate physical deformation priors. In this work, we propose DUM-Net, a model-driven deep unrolling framework for multi-modal image registration. Starting from a variational MIR model with a similarity term and a regularization term, we unroll a time-discrete gradient descent process into a layer-wise trainable architecture. DUM-Net consists of three components: an initialization module (IM), an adaptive similarity module (ASM), and a linear elasticity module (LEM). The IM provides deformation initialization to accelerate convergence. The ASM employs a deep neural network to learn an adaptive descent direction for cross-modal matching, thereby overcoming the limitations of handcrafted similarity functionals. The LEM introduces a parameterized linear-elastic prior during forward propagation to encourage smooth and physically plausible deformation fields. In this way, DUM-Net combines the flexibility of learned similarity modeling with the structural guidance of variational unrolling and explicit physical regularization. Experiments on T1/T2 MR, CT/MR, and FL/IR registration tasks demonstrate that DUM-Net consistently outperforms existing methods, achieving Dice score improvements of 3.74% for small and 6.16% for large deformations on T1/T2 MR image pairs, together with strong performance on CT/MR and FL/IR datasets. The source code is publicly available at https://github.com/QDUJackson/DUM-Net.
- 1 January 2026
- Published by American Institute of Mathematical Sciences (AIMS) in Mathematical Foundations of Computing
- Vol. 11, 120-135
Sperf: A trainable smooth non-monotonic activation function with enhanced nonlinearity
ReLU, as the core nonlinear unit in numerous deep learning backbones, plays a crucial role in this field. In recent years, various smooth ReLU-Like activation functions have demonstrated superior performance across different tasks and network architectures. In this paper, we propose a novel trainable ReLU-Like activation function, Sperf, constructed by multiplying Softplus with the Gaussian error function (erf). Sperf enhances nonlinear representation capability while maintaining numerical stability. Experimental results show that networks equipped with Sperf achieve significant performance gains across diverse tasks: six image-classification datasets; Cityscapes for semantic segmentation; and MICCAI BraTS2020 for unsupervised image registration.
- 1 January 2026
- Published by American Institute of Mathematical Sciences (AIMS) in Mathematical Foundations of Computing
- Vol. 11, 120-135
Sperf: A trainable smooth non-monotonic activation function with enhanced nonlinearity
ReLU, as the core nonlinear unit in numerous deep learning backbones, plays a crucial role in this field. In recent years, various smooth ReLU-Like activation functions have demonstrated superior performance across different tasks and network architectures. In this paper, we propose a novel trainable ReLU-Like activation function, Sperf, constructed by multiplying Softplus with the Gaussian error function (erf). Sperf enhances nonlinear representation capability while maintaining numerical stability. Experimental results show that networks equipped with Sperf achieve significant performance gains across diverse tasks: six image-classification datasets; Cityscapes for semantic segmentation; and MICCAI BraTS2020 for unsupervised image registration.