Abstract: |
This talk will cover an end-to-end discussion for applying federated learning (FL) in medical imaging – from theoretical algorithm design to practical framework implementation. Given the fundamentals of FL addressing the pivotal balance between data privacy and the collaborative enhancement of machine learning (ML) models, we will discuss the special challenges and solutions for embedding FL in medical imaging practices, with details of methods proposed for personalization, fairness, and privacy protection. We will further talk about the real-life FL study using a practical framework regarding system design and implementations. Further, we will extend the ML models from deep learning to a more general setting, and discuss the systematic requirements and features, especially in the age of LLMs. Ultimately, this talk underscores the transformative potential of FL in medical imaging, offering insights into its current achievements and future possibilities. |
Biography: |
| Dr. Ziyue Xu is a Senior Scientist at NVIDIA, before which he was a Staff Scientist and Lab Manager at National Institutes of Health, USA. His research interests lie in the area of image analysis and computer vision with applications in biomedical imaging. He has been working on medical AI over the years along with fellow researchers and clinicians for clinical applications. He is an IEEE Senior Member, Area Chair for major conferences, and Associate Editor for several journals including IEEE Transactions of Medical Imaging, and International Journal of Computer Vision. |