Metalearning or learning to learn has been gaining popularity in recent years to adapt to new tasks systematically and efficiently in machine learning. In the book MetaLearning Frameworks for Imaging Applications experts from the fields of machine learning and imaging come together to explore the current state of metalearning and its application to medical imaging and health informatics. The book presents an overview of the metalearning framework including common versions such as modelagnostic learning memory augmentation prototype networks and learning to optimize. It also discusses how metalearning can be applied to address fundamental limitations of deep neural networks such as high data demand computationally expensive training and limited ability for task transfer. One critical topic in imaging is image segmentation and the book explores how a metalearningbased framework can help identify the best image segmentation algorithm which would be particularly beneficial in the healthcare domain. This book is relevant to healthcare institutes ecommerce companies and educational institutions as well as professionals and practitioners in the intelligent system computational data science network applications and biomedical applications fields. It is also useful for domain developers and project managers from diagnostic and pharmacy companies involved in the development of medical expert systems. Additionally graduate and master students in intelligent systems big data management computational intelligent approaches computer vision and biomedical science can use this book for their final projects and specific courses.