2026
FACT: Fuzzy Alignment with Comorbidity Topology for Reliable Multi-Label Medical Image Diagnosis
Yingyu Chen, Yongqiang Huang, Yang Qin, Ziyuan Yang, Lang Yuan, Maosong Ran, Yi Zhang†
International Conference on Machine Learning (ICML)
This paper proposes FACT, a framework that reinterprets multi-label medical image diagnosis as a fuzzy alignment problem, leveraging vector quantization to construct atomic visual evidence and a graph convolutional network to embed comorbidity topology, with a metric-based fuzzy membership function derived from RKHS theory.
# medical analysis # multi-label learning # vision-language
FACT: Fuzzy Alignment with Comorbidity Topology for Reliable Multi-Label Medical Image Diagnosis
Yingyu Chen, Yongqiang Huang, Yang Qin, Ziyuan Yang, Lang Yuan, Maosong Ran, Yi Zhang†
International Conference on Machine Learning (ICML)
This paper proposes FACT, a framework that reinterprets multi-label medical image diagnosis as a fuzzy alignment problem, leveraging vector quantization to construct atomic visual evidence and a graph convolutional network to embed comorbidity topology, with a metric-based fuzzy membership function derived from RKHS theory.
# medical analysis # multi-label learning # vision-language
Beyond Class Boundaries: Federated Visual Primitive Sharing with Text-Guided Adaptation
Yongqiang Huang, Yingyu Chen, Tao Wang, Zexin Lu, Zerui Shao, Beibei Li, Yi Zhang†
The ACM Web Conference (WWW)
This paper introduces FedVPL, a personalized federated learning framework that shares semantically decomposed visual primitives across clients and leverages text-guided alignment to enhance feature diversity, personalization, and generalization while significantly reducing communication overhead.
# federated learning # vision-language
Beyond Class Boundaries: Federated Visual Primitive Sharing with Text-Guided Adaptation
Yongqiang Huang, Yingyu Chen, Tao Wang, Zexin Lu, Zerui Shao, Beibei Li, Yi Zhang†
The ACM Web Conference (WWW)
This paper introduces FedVPL, a personalized federated learning framework that shares semantically decomposed visual primitives across clients and leverages text-guided alignment to enhance feature diversity, personalization, and generalization while significantly reducing communication overhead.
# federated learning # vision-language
FedPalm: A General Federated Learning Framework for Closed-and Open-set Palmprint Verification
Ziyuan Yang, Yingyu Chen, Chengrui Gao, Andrew Beng Jin Teoh, Bob Zhang, Yi Zhang†
IEEE Transactions on Information Forensics and Security (IEEE T-IFS)
This paper proposes FedPalm, a unified federated learning framework for palmprint verification that combines personalized local textural experts with a shared global expert to achieve robust performance in both closed-set and open-set scenarios while preserving biometric privacy.
# federated learning # biometrics
FedPalm: A General Federated Learning Framework for Closed-and Open-set Palmprint Verification
Ziyuan Yang, Yingyu Chen, Chengrui Gao, Andrew Beng Jin Teoh, Bob Zhang, Yi Zhang†
IEEE Transactions on Information Forensics and Security (IEEE T-IFS)
This paper proposes FedPalm, a unified federated learning framework for palmprint verification that combines personalized local textural experts with a shared global expert to achieve robust performance in both closed-set and open-set scenarios while preserving biometric privacy.
# federated learning # biometrics
Double Banking on Knowledge: A Unified All-in-One Framework for Unpaired Multi-Modality Semi-supervised Medical Image Segmentation
Yingyu Chen, Ziyuan Yang, Zhongzhou Zhang, Ming Yan, Hui Yu, Yan Liu, Yi Zhang†
IEEE Transactions on Biomedical Engineering (IEEE T-BME)
This paper proposes a unified all-in-one framework for unpaired multi-modality semi-supervised medical image segmentation that leverages learnable knowledge banks, modality-adaptive weighting, and dual consistency to capture both modality-invariant and modality-specific features, enabling scalable and robust segmentation across multiple modalities.
# medical analysis # weakly-supervised learning
Double Banking on Knowledge: A Unified All-in-One Framework for Unpaired Multi-Modality Semi-supervised Medical Image Segmentation
Yingyu Chen, Ziyuan Yang, Zhongzhou Zhang, Ming Yan, Hui Yu, Yan Liu, Yi Zhang†
IEEE Transactions on Biomedical Engineering (IEEE T-BME)
This paper proposes a unified all-in-one framework for unpaired multi-modality semi-supervised medical image segmentation that leverages learnable knowledge banks, modality-adaptive weighting, and dual consistency to capture both modality-invariant and modality-specific features, enabling scalable and robust segmentation across multiple modalities.
# medical analysis # weakly-supervised learning
Multi-label Medical Diagnosis using Spatial-disease Feature Condensation and Kolmogorov–Arnold Layers
Lang Yuan*, Yingyu Chen*, Ziyuan Yang, Yi Zhang†
Physics in Medicine and Biology
This paper presents a multi-label medical diagnosis framework that combines spatial-disease feature condensation with Kolmogorov–Arnold layers to preserve disease localization and enhance modeling of inter-disease dependencies, achieving improved diagnostic accuracy and reliability.
# medical analysis # multi-label learning # kolmogorov-arnold networks
Multi-label Medical Diagnosis using Spatial-disease Feature Condensation and Kolmogorov–Arnold Layers
Lang Yuan*, Yingyu Chen*, Ziyuan Yang, Yi Zhang†
Physics in Medicine and Biology
This paper presents a multi-label medical diagnosis framework that combines spatial-disease feature condensation with Kolmogorov–Arnold layers to preserve disease localization and enhance modeling of inter-disease dependencies, achieving improved diagnostic accuracy and reliability.
# medical analysis # multi-label learning # kolmogorov-arnold networks
2025
Trustworthy Disentangled Framework for Multi-Label Medical Image Classification with Multimodal Refinement
Yingyu Chen, Ziyuan Yang, Yongqiang Huang, Xulei Yang, Siyong Yeo, Yi Zhang†
IEEE International Conference on Bioinformatics and Biomedicine (IEEE BIBM)
This paper proposes a trustworthy disentangled framework for multi-label medical image classification that uses multi-CLS token transformers with multimodal refinement and a novel evidence-based loss to capture disease-specific features, model inter-disease relationships, and provide reliable predictions with uncertainty estimates.
# medical analysis # trustworthy AI # multi-label learning
Trustworthy Disentangled Framework for Multi-Label Medical Image Classification with Multimodal Refinement
Yingyu Chen, Ziyuan Yang, Yongqiang Huang, Xulei Yang, Siyong Yeo, Yi Zhang†
IEEE International Conference on Bioinformatics and Biomedicine (IEEE BIBM)
This paper proposes a trustworthy disentangled framework for multi-label medical image classification that uses multi-CLS token transformers with multimodal refinement and a novel evidence-based loss to capture disease-specific features, model inter-disease relationships, and provide reliable predictions with uncertainty estimates.
# medical analysis # trustworthy AI # multi-label learning
Modality Modulation and Dual Consistency for Multi-Modality Semi-Supervised Medical Image Segmentation
Yingyu Chen, Ziyuan Yang, Deng Xiong, Yi Zhang†
IEEE International Conference on Acoustics, Speech and Signal Processing (IEEE ICASSP)
This paper proposes MM-DC, a multi-modality semi-supervised segmentation framework that uses modality modulation layers and dual-consistency constraints to unify features across all modalities without relying on generative methods, achieving robust segmentation across multiple modalities.
# medical image segmentation # weakly-supervised learning
Modality Modulation and Dual Consistency for Multi-Modality Semi-Supervised Medical Image Segmentation
Yingyu Chen, Ziyuan Yang, Deng Xiong, Yi Zhang†
IEEE International Conference on Acoustics, Speech and Signal Processing (IEEE ICASSP)
This paper proposes MM-DC, a multi-modality semi-supervised segmentation framework that uses modality modulation layers and dual-consistency constraints to unify features across all modalities without relying on generative methods, achieving robust segmentation across multiple modalities.
# medical image segmentation # weakly-supervised learning
Patient-Level Anatomy Meets Scanning-Level Physics: Personalized Federated Low-dose CT Denoising Empowered by Large Language Model
Ziyuan Yang, Yingyu Chen, Zhiwen Wang, Hongming Shan, Yang Chen, Yi Zhang†
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
This paper introduces SCAN-PhysFed, a personalized federated learning framework for low-dose CT denoising that leverages scanning- and anatomy-level physics-informed prompts, guided by a medical large language model, to achieve robust and generalizable reconstruction across diverse scanning protocols while preserving patient privacy.
# federated learning # medical imaging # LLM
Patient-Level Anatomy Meets Scanning-Level Physics: Personalized Federated Low-dose CT Denoising Empowered by Large Language Model
Ziyuan Yang, Yingyu Chen, Zhiwen Wang, Hongming Shan, Yang Chen, Yi Zhang†
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
This paper introduces SCAN-PhysFed, a personalized federated learning framework for low-dose CT denoising that leverages scanning- and anatomy-level physics-informed prompts, guided by a medical large language model, to achieve robust and generalizable reconstruction across diverse scanning protocols while preserving patient privacy.
# federated learning # medical imaging # LLM
2024
UniAda: Domain Unifying and Adapting Network for Generalizable Medical Image Segmentation
Zhongzhou Zhang, Yingyu Chen, Hui Yu, Zhiwen Wang, Shanshan Wang, Fenglei Fan, Hongming Shan, Yi Zhang†
IEEE Transactions on Medical Imaging (IEEE T-MI)
This paper proposes UniAda, a generalizable medical image segmentation framework that unifies multi-source domains during training and dynamically adapts to unseen target domains at test time using feature statistics and uncertainty-guided adaptation, achieving robust cross-domain performance.
# medical image segmentation # domain adaptation
UniAda: Domain Unifying and Adapting Network for Generalizable Medical Image Segmentation
Zhongzhou Zhang, Yingyu Chen, Hui Yu, Zhiwen Wang, Shanshan Wang, Fenglei Fan, Hongming Shan, Yi Zhang†
IEEE Transactions on Medical Imaging (IEEE T-MI)
This paper proposes UniAda, a generalizable medical image segmentation framework that unifies multi-source domains during training and dynamically adapts to unseen target domains at test time using feature statistics and uncertainty-guided adaptation, achieving robust cross-domain performance.
# medical image segmentation # domain adaptation
Inject Backdoor in Measured Data to Jeopardize Full-stack Medical Image Analysis System
Ziyuan Yang, Yingyu Chen, Mengyu Sun, Yi Zhang†
International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)
This paper presents a novel pre-imaging backdoor attack called LTGM that injects learnable triggers into measured medical data to compromise downstream image analysis tasks without affecting reconstruction quality, exposing vulnerabilities in full-stack medical image analysis systems.
# medical image analysis # trustworthy AI
Inject Backdoor in Measured Data to Jeopardize Full-stack Medical Image Analysis System
Ziyuan Yang, Yingyu Chen, Mengyu Sun, Yi Zhang†
International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)
This paper presents a novel pre-imaging backdoor attack called LTGM that injects learnable triggers into measured medical data to compromise downstream image analysis tasks without affecting reconstruction quality, exposing vulnerabilities in full-stack medical image analysis systems.
# medical image analysis # trustworthy AI
Test-time Adaptation via Orthogonal Meta-learning for Medical Imaging
Zhiwen Wang, Zexin Lu, Tao Wang, Ziyuan Yang, Hui Yu, Zhongxian Wang, Yinyu Chen, Jingfeng Lu, Yi Zhang†
IEEE Transactions on Radiation and Plasma Medical Sciences (IEEE T-RPMS)
This paper presents an orthogonal meta-learning framework for test-time adaptation in medical imaging, enabling deep learning models to quickly adjust to unseen domain variations and distribution mismatches, improving reconstruction performance on new MRI and CT data.
# medical imaging
Test-time Adaptation via Orthogonal Meta-learning for Medical Imaging
Zhiwen Wang, Zexin Lu, Tao Wang, Ziyuan Yang, Hui Yu, Zhongxian Wang, Yinyu Chen, Jingfeng Lu, Yi Zhang†
IEEE Transactions on Radiation and Plasma Medical Sciences (IEEE T-RPMS)
This paper presents an orthogonal meta-learning framework for test-time adaptation in medical imaging, enabling deep learning models to quickly adjust to unseen domain variations and distribution mismatches, improving reconstruction performance on new MRI and CT data.
# medical imaging
Evidence-based Uncertainty-aware Semi-supervised Medical Image Segmentation
Yingyu Chen, Ziyuan Yang, Chenyu Shen, Zhiwen Wang, Zhongzhou Zhang, Yang Qin, Xin Wei, Jingfeng Lu, Yan Liu, Yi Zhang†
Computers in Biology and Medicine
This paper introduces an uncertainty-aware semi-supervised medical image segmentation framework that integrates Dempster–Shafer evidence theory to generate reliable pseudo labels, enforce consistency across perturbed predictions, and provide principled uncertainty quantification for improved generalization.
# medical image segmentation # trustworthy AI # weakly-supervised learning
Evidence-based Uncertainty-aware Semi-supervised Medical Image Segmentation
Yingyu Chen, Ziyuan Yang, Chenyu Shen, Zhiwen Wang, Zhongzhou Zhang, Yang Qin, Xin Wei, Jingfeng Lu, Yan Liu, Yi Zhang†
Computers in Biology and Medicine
This paper introduces an uncertainty-aware semi-supervised medical image segmentation framework that integrates Dempster–Shafer evidence theory to generate reliable pseudo labels, enforce consistency across perturbed predictions, and provide principled uncertainty quantification for improved generalization.
# medical image segmentation # trustworthy AI # weakly-supervised learning
2023
SCA-Former: Transformer-like Network based on Stream-cross Attention for Medical Image Segmentation
Chengrui Gao, Junlong Cheng, Ziyuan Yang, Yingyu Chen, Min Zhu†
IEEE Transactions on Neural Networks and Learning Systems (IEEE T-NNLS)
This paper introduces SCA-Former, a Transformer-like U-shaped network for medical image segmentation that employs a stream-cross attention module to capture both local and long-range multi-scale features, achieving improved performance with a compact model size.
# federated learning # medical imaging
SCA-Former: Transformer-like Network based on Stream-cross Attention for Medical Image Segmentation
Chengrui Gao, Junlong Cheng, Ziyuan Yang, Yingyu Chen, Min Zhu†
IEEE Transactions on Neural Networks and Learning Systems (IEEE T-NNLS)
This paper introduces SCA-Former, a Transformer-like U-shaped network for medical image segmentation that employs a stream-cross attention module to capture both local and long-range multi-scale features, achieving improved performance with a compact model size.
# federated learning # medical imaging
Hypernetwork-Based Personalized Federated Learning for Multi-Institutional CT Imaging
Ziyuan Yang, Wenjun Xia, Zexin Lu, Yingyu Chen, Xiaoxiao Li, Yi Zhang†
IEEE Transactions on Neural Networks and Learning Systems (IEEE T-NNLS)
This paper presents HyperFed, a hypernetwork-based physics-driven personalized federated learning framework for CT imaging that combines institution-specific hypernetworks with a global-sharing imaging network to achieve personalized, high-quality reconstruction while preserving data privacy.
# federated learning # medical imaging
Hypernetwork-Based Personalized Federated Learning for Multi-Institutional CT Imaging
Ziyuan Yang, Wenjun Xia, Zexin Lu, Yingyu Chen, Xiaoxiao Li, Yi Zhang†
IEEE Transactions on Neural Networks and Learning Systems (IEEE T-NNLS)
This paper presents HyperFed, a hypernetwork-based physics-driven personalized federated learning framework for CT imaging that combines institution-specific hypernetworks with a global-sharing imaging network to achieve personalized, high-quality reconstruction while preserving data privacy.
# federated learning # medical imaging
SynFacePAD 2023: Competition on Face Presentation Attack Detection based on Privacy-aware Synthetic Training Data
Meiling Fang, Marco Huber, Julian Fierrez, Raghavendra Ramachandra, Naser Damer, Alhasan Alkhaddour, Maksim Kasantcev, Vasiliy Pryadchenko, Ziyuan Yang, Huijie Huangfu, Yingyu Chen, Yi Zhang, Yuchen Pan, Junjun Jiang, Xianming Liu, Xianyun Sun, Caiyong Wang, Xingyu Liu, Zhaohua Chang, Guangzhe Zhao, Juan Tapia, Lazaro Gonzalez-Soler, Carlos Aravena, Daniel Schulz
IEEE International Joint Conference on Biometrics (IEEE IJCB)
A face presentation attack detection method based on synthetic data.
# biometrics
SynFacePAD 2023: Competition on Face Presentation Attack Detection based on Privacy-aware Synthetic Training Data
Meiling Fang, Marco Huber, Julian Fierrez, Raghavendra Ramachandra, Naser Damer, Alhasan Alkhaddour, Maksim Kasantcev, Vasiliy Pryadchenko, Ziyuan Yang, Huijie Huangfu, Yingyu Chen, Yi Zhang, Yuchen Pan, Junjun Jiang, Xianming Liu, Xianyun Sun, Caiyong Wang, Xingyu Liu, Zhaohua Chang, Guangzhe Zhao, Juan Tapia, Lazaro Gonzalez-Soler, Carlos Aravena, Daniel Schulz
IEEE International Joint Conference on Biometrics (IEEE IJCB)
A face presentation attack detection method based on synthetic data.
# biometrics
Dynamic Corrected Split Federated Learning with Homomorphic Encryption for U-shaped Medical Image Networks
Ziyuan Yang Yingyu Chen Huijie Huangfu Maosong Ran Hui Wang Xiaoxiao Li Yi Zhang†,
IEEE Journal of Biomedical and Health Informatics (IEEE JBHI)
This paper proposes DC-SFL, a hybrid split-federated learning framework for U-shaped medical image networks that combines dynamic weight correction and homomorphic encryption to ensure data and model privacy, stabilize training under heterogeneous data, and achieve competitive performance across medical imaging tasks.
# federated learning # medical learning
Dynamic Corrected Split Federated Learning with Homomorphic Encryption for U-shaped Medical Image Networks
Ziyuan Yang Yingyu Chen Huijie Huangfu Maosong Ran Hui Wang Xiaoxiao Li Yi Zhang†,
IEEE Journal of Biomedical and Health Informatics (IEEE JBHI)
This paper proposes DC-SFL, a hybrid split-federated learning framework for U-shaped medical image networks that combines dynamic weight correction and homomorphic encryption to ensure data and model privacy, stabilize training under heterogeneous data, and achieve competitive performance across medical imaging tasks.
# federated learning # medical learning
SAA-NET: A Medical Image Segmentation Framework based on Stream-across Attention
Chengrui Gao, Junlong Cheng, Ziyuan Yang, Yingyu Chen, Fengjie Wang, Min Zhu†
IEEE International Symposium on Biomedical Imaging (IEEE ISBI)
This paper proposes SAA-Net, a U-shaped medical image segmentation network that uses a Stream-Across Attention module with multi-scale spatial and channel attention branches, along with DenseMLP for multi-level feature learning, to capture long-range dependencies and improve segmentation performance.
# medical image segmentation
SAA-NET: A Medical Image Segmentation Framework based on Stream-across Attention
Chengrui Gao, Junlong Cheng, Ziyuan Yang, Yingyu Chen, Fengjie Wang, Min Zhu†
IEEE International Symposium on Biomedical Imaging (IEEE ISBI)
This paper proposes SAA-Net, a U-shaped medical image segmentation network that uses a Stream-Across Attention module with multi-scale spatial and channel attention branches, along with DenseMLP for multi-level feature learning, to capture long-range dependencies and improve segmentation performance.
# medical image segmentation
EVIL: Evidential Inference Learning for Trustworthy Semi-supervised Medical Image Segmentation
Yingyu Chen, Ziyuan Yang, Chenyu Shen, Zhiwen Wang, Yang Qin, Yi Zhang†
IEEE International Symposium on Biomedical Imaging (IEEE ISBI)
This paper introduces EVIL, a semi-supervised medical image segmentation framework that leverages Dempster–Shafer evidence theory to provide accurate uncertainty quantification, generate trustworthy pseudo labels, and enforce consistency regularization for improved generalization with limited labeled data.
# medical image segmentation # weakly-supervised learning # trustworthy AI
EVIL: Evidential Inference Learning for Trustworthy Semi-supervised Medical Image Segmentation
Yingyu Chen, Ziyuan Yang, Chenyu Shen, Zhiwen Wang, Yang Qin, Yi Zhang†
IEEE International Symposium on Biomedical Imaging (IEEE ISBI)
This paper introduces EVIL, a semi-supervised medical image segmentation framework that leverages Dempster–Shafer evidence theory to provide accurate uncertainty quantification, generate trustworthy pseudo labels, and enforce consistency regularization for improved generalization with limited labeled data.
# medical image segmentation # weakly-supervised learning # trustworthy AI