Federated Learning for Medical Image Analysis

55 Minutes

My research focuses on federated learning for medical image analysis. Federated learning allows multiple institutions to collaboratively train machine learning models without directly sharing sensitive patient data. However, differences in imaging conditions, patient populations, and the amount of available data can cause performance degradation and unstable training. My research aims to develop robust and efficient federated learning methods that can address these challenges. I evaluate the proposed approaches using medical image classification and segmentation tasks and compare them with existing federated learning methods. The evaluation focuses on model accuracy, training stability, convergence, and robustness under heterogeneous data distributions. Through this research, I aim to contribute to the development of reliable machine learning systems that support collaborative medical image analysis while protecting patient privacy.