科研项目：
数字健康与转化校企联合实验室，2026-2029，项目负责人
国家自然科学基金，《面向粉尘环境诱导脑功能网络异常的智能眼底影像关键预警方法研究》，2021-2024，项目负责人
复旦大学卓学人才项目，2025-2028，负责人
医院委托项目，临床研究智能体中心，2026-，项目负责人
企业委托项目，智能医疗大模型研发与应用，2026.2-2028.2，项目负责人
淮北市职业病防治院委托项目，2026.2-2028.2，项目负责人
宁夏自治区重点研发计划（社会发展领域），2023.1-2026.5，结题，课题负责人
国家级创业实践项目，融合联邦学习的多疾病智能预警技术的理论研究和系统开发，优秀结题，指导老师
复旦大学原创项目，脑胶质瘤瘤智选粒子放疗技术研究，2021.1-2021.12，结题，项目负责人
工业粉尘防控与职业安全健康教育部重点实验室开放基金，2021-202，结题，考核优秀，项目负责人
上海脑重大疾病智能影像工程技术研究中心项目，2021.1-2023.6，结题，项目骨干
企业委托项目，CBCT预测口扫点云关键技术研究，2020.7-2022.7，结题，项目负责人
中煤能源集团，深井环境作业人员身心健康智能评估关键技术研究，2024.1-2025.3，结题，项目负责人
莆田兰海核医学中心委托项目，用于重离子放疗的智能脑肿瘤辅助诊断系统，结题，项目负责人
企业委托项目，特种环境作业人员可穿戴生理信号监测预警系统，2024.5-2027.12，在研，项目负责人
成果转化项目，一种基于人工智能的健康数据管理系统，结题，项目负责人
代表性论文：
1.Ye, M., Huangfu, Y., Gao, S., Ren, W., Liu, W., & Yu, Z*. (2026). FedGSCA: Medical federated learning with global sample selector and client adaptive adjuster under label noise.IEEE journal of Biomedical and Health Informatics.
2.Niu, F., Liu, H., Liang, M., Chen, J., Yu, Z*., & Zhang, L*. (2026). HTCNet: Hierarchical Point-Graph Tooth Point Cloud Completion with Image Assistance.IEEE Transactions on Circuits and Systems for Video Technology.
3.Tang, Z., Wong, H. S*., & Yu, Z*. (2023). Privacy-preserving federated learning with domain adaptation for multi-disease ocular disease recognition. IEEE Journal of Biomedical and Health Informatics, 28(6), 3219-3227.
4.Gao, S., Wang, Y., Yang, J., Ye, M., Liu, W., & Yu, Z*. (2026). TriCSART: Semi-Supervised Medical Image Segmentation with Triple-Level Contrastive Learning and Selective Active Re-Training. IEEE Journal of Biomedical and Health Informatics.
5.Gu, Y., Guan, Y., Yu, Z*., & Dong, B*. (2023). SegCoFusion: An integrative multimodal volumetric segmentation cooperating with fusion pipeline to enhance lesion awareness. IEEE Journal of Biomedical and Health Informatics, 27(12), 5860-5871.
6.Hu, M., Li, J., Dong, Y., Zhang, Z., Liu, W., Zhang, P., ... & Yu, Z*. (2025). Mixed-GGNAS: Mixed Search-space NAS based on genetic algorithm combined with gradient descent for medical image segmentation. Expert Systems with Applications, 289, 128338
7.Yang, J., Gu, Y., Gao, S., Ren, W., & Yu, Z*. (2025). Fed-GFM-DG: A privacy-preserving framework for fundus image segmentation via generative-based feature generalization and mask-guided aggregation. Biomedical Signal Processing and Control, 106, 107725.
8.Chen, R., Nian, F., Cen, Y., Peng, Y., Wang, H., Yu, Z*., & Luo, J*. (2025). L-SSHNN: A Larger search space of Semi-Supervised Hybrid NAS Network for echocardiography segmentation. Expert Systems with Applications, 276, 127084.
9.Zhang P, Dong Y, Yu Z*.(2026).Trans-ViM: Synergistie Integration of Transforner and Vision Mamba for Hierarchical Multi-Label Visual Representation Learning。Engineering Applications of Artificial Intelligence
10.Yu, Z*., Li, X., Li, J., Chen, W., Tang, Z., & Geng, D. (2024). HSA-net with a novel CAD pipeline boosts both clinical brain tumor MR image classification and segmentation. Computers in Biology and Medicine, 170, 108039.
11.Yu, Z., Ye, M., Yang, J., Chen, W., Fu, W., Zhang, L., ... & Shi, X. (2025). Beta-amyloid deposition increases in the brain with the progression of silicosis: a [18F] AV45 PET study in mice. Environmental Research, 121898.
12.Ye, M., Huangfu, Y., Li, Y., & Yu, Z*. (2024, October). SSP-RACL: Classification of Noisy Fundus Images with Self-Supervised Pretraining and Robust Adaptive Credal Loss. In 2024 IEEE Biomedical Circuits and Systems Conference (BioCAS) (pp. 1-5). IEEE.
13.Yu, Z., Li, M., Yang, J., Chen, Z., Zhang, H., Liu, W., ... & Liu, J. (2023). A benchmark dual-modality dental imaging dataset and a novel cognitively inspired pipeline for high-resolution dental point cloud synthesis. Cognitive Computation, 15(6), 1922-1933.
14.Yang, J., Gu, Y., & Yu, Z*. (2025, October). AIGL: Adaptive Imbalance-to-Generalization Learning for Robust Multi-Label Retinal Disease Classification. In 2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC) (pp. 1972-1977). IEEE.
15.Yang, Y., Fang, X., Li, X., Han, Y., & Yu, Z*. (2025). CDSG-SAM: A cross-domain self-generating prompt few-shot brain tumor segmentation pipeline based on SAM. Biomedical Signal Processing and Control, 100, 106936.