Striving for Universal Access to High-Quality Medical Services Through Artificial Intelligence (Click to Visit the Laboratory Homepage)

Dr. Zhou Hongyu's research focuses on building scalable, trustworthy, and clinically useful medical artificial intelligence (AI) systems. He is committed to promoting the universal access of high-quality medical resources through intelligent technologies. With "data" and "knowledge" as the two pillars, he has systematically carried out research in the following directions:

Intelligent Health Ecosystem: Develop patient-centered medical AI systems, aiming to build intelligent health technologies that are trustworthy, interpretable, and usable for patients. By advancing AI-assisted health management, personalized interventions, and patient empowerment, patients are positioned as the core of health management, driving medical AI toward a more human-centric, inclusive, and trustworthy direction.

General-Purpose Medical Decision-Making Models: Promote the construction of general-purpose medical AI systems, and develop multimodal large models with integrated perceptual, reasoning, and generative capabilities. These models are designed to tackle cross-specialty and multi-scenario clinical tasks, facilitating the widespread accessibility of high-quality medical resources.

Foundation Models for Medical Imaging: Dedicate to building a new generation of self-supervised medical visual representation learning frameworks. Explore generalization mechanisms under weakly supervised and unsupervised paradigms to reduce reliance on expensive annotated data, and enhance the robustness and transferability of models across different institutions and devices.

1. Zhou, H. Y., Yu, Y., Wang, C., Zhang, S., Gao, Y., Pan, J., Shao, J., Lu, G., Zhang, K., & Li, W. (2023). A transformer-based representation-learning model with unified processing of multimodal input for clinical diagnostics. Nature Biomedical Engineering, 7, 743-755.

2. Zhou, H. Y., Chen, X., Zhang, Y., Luo, R., Wang, L., & Yu, Y.Y. (2021). Generalized radiograph representation learning via cross-supervision between images and free-text radiology reports. Nature Machine Intelligence, 4, 32 - 40.

3. Zhou, H. Y., Lu, C., Chen, C., Yang, S., & Yu, Y. (2023). A Unified Visual Information Preservation Framework for Self-supervised Pre-Training in Medical Image Analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45, 8020-8035.

4. Zhou, H. Y., Lian, C., Wang, L., & Yu, Y. Advancing Radiograph Representation Learning with Masked Record Modeling. In The Eleventh International Conference on Learning Representations.

5. Zhou, H. Y., Fu, Y., Zhang, Z., Cheng, B., & Yu, Y. (2023). Protein representation learning via knowledge enhanced primary structure reasoning. In The Eleventh international conference on learning representations.

6. Zhou, H. Y., Lu, C., Yang, S., Han, X., & Yu, Y. (2021). Preservational learning improves self-supervised medical image models by reconstructing diverse contexts. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 3499-3509).

7. Johri, S., Jeong, J., Tran, B.A., Schlessinger, D.I., Wongvibulsin, S., Barnes, L., Zhou, H. Y., Cai, Z.R., Van Allen, E.M., Kim, D.A., Daneshjou, R., & Rajpurkar, P. (2025). An evaluation framework for clinical use of large language models in patient interaction tasks. Nature Medicine, 31(1), 77-86.

8. Wang, J., Wang, K., Yu, Y., Lu, Y., Xiao, W., Sun, Z., Liu, F., Zou, Z., Gao, Y., Yang, L., Zhou, H. Y., Miao, H., Zhao, W., Huang, L., Zeng, L., Guo, R., Chong, I., Deng, B., Cheng, L., Chen, X., Luo, J., Zhu, M., Baptista‐Hon, D.T., Monteiro, O., Li, M., Ke, Y., Li, J., Zeng, S., Guan, T., Zeng, J., Xue, K., Oermann, E.K., Luo, H., Yin, Y., Zhang, K., & Qu, J. (2024). Self-improving generative foundation model for synthetic medical image generation and clinical applications. Nature Medicine, 31(2), 609-617.

9. Huang, W., Li, C., Zhou, H. Y., Yang, H., Liu, J., Liang, Y., ... & Wang, S. (2024). Enhancing representation in radiography-reports foundation model: A granular alignment algorithm using masked contrastive learning. Nature Communications, 15(1), 7620.

10. Gao, Y., Ventura-Diaz, S., Wang, X., He, M., Xu, Z., Weir, A., Zhou, H. Y., Zhang, T., Van Duijnhoven, F., Han, L., Li, X., D'Angelo, A., Longo, V., Liu, Z., Teuwen, J., Kok, M., Beets-Tan, R., Horlings, H.M., Tan, T., & Mann, R. (2024). An explainable longitudinal multi-modal fusion model for predicting neoadjuvant therapy response in women with breast cancer. Nature Communications, 15(1), 9613.

Academic Honors and Awards

1.2024 "Stanford University/Elsevier Top 2% of the World's Scientists"

2.Outstanding PhD Award, The University of Hong Kong Foundation

3.Outstanding Research Achievement Award, The University of Hong Kong Foundation

4.PhD Student Scholarship, International Chinese Medical Imaging Association (ICMA)

5.Champion of the "Precise and Automated Spinal Curvature Assessment Challenge" (among 79 participating teams, Ranked 1st)

6.Champion of the "Chest Organ at Risk (OAR) Segmentation Challenge" (among 638 participating teams, Ranked 1st)

7.Champion of the "AI4Health Global Challenge" (among 200 participating teams, Ranked 1st)