This book provides a practical guide to federated deep learning for healthcare including fundamental concepts, framework, and the applications comprising of domain adaptation, model distillation, and transfer learning. It covers concerns in model fairness, data bias, regulatory compliance, and ethical dilemmas. It investigates several privacy-preserving methods like homomorphic encryption, secure multi-party computation, and differential privacy. It will enable readers to build and implement federated learning systems that safeguard private medical information.
Features:
• Offers a thorough introduction of federated deep learning methods designed exclusively for medical applications.
• Investigates privacy-preserving methods with emphasis on data security and privacy.
• Discusses healthcare scaling and resource efficiency considerations.
• Examines methods for sharing information among various healthcare organizations while retaining model performance.
This book is aimed at graduate students and researchers in federated learning, data science, AI/machine learning, and healthcare.
Author Biography:
Amandeep Kaur currently holds the position of a Professor at the Chitkara University Institute of Engineering and Technology, Chitkara University, Punjab. Her primary research areas encompass medical informatics, machine learning, IoT (Internet of Things), artificial intelligence, and cloud computing.
Chetna Kaushal is working as an Assistant Professor in Chitkara University, Punjab. She is PhD in CSE from Chitkara University, Punjab, M.Tech in CSE from DAV University, Punjab and B.Tech in IT from Punjab Technical University. Her areas of expertise are Machine learning, Soft Computing, Pattern Recognition, Image processing, and Artificial Intelligence.
Md. Mehedi Hassan is a dedicated young researcher, holding a B.Sc. Engineering degree in computer science and engineering from 2022 and currently pursuing his M.Sc. Engineering degree at Khulna University, Bangladesh. Mehedi's research interests encompass a broad spectrum, ranging from human brain imaging, neuroscience, machine learning, and artificial intelligence to software engineering.
Si Thu Aung received the B.E. degree from Technological University, Myanmar, in 2014, the Master of Engineering in Electronics from Mandalay Technological University, Myanmar, in 2017, and the Ph.D. in Biomedical Engineering from the Faculty of Engineering, Mahidol University, Thailand, in 2021. His current research interests include biomedical signal processing, digital image processing, machine learning, and deep learning.