Deep Network Design for Medical Image Computing: Principles and Applications

Deep Network Design for Medical Image Computing: Principles and Applications discusses design principles of deep learning approaches for MIC tasks, such as skin disease classification, vertebrae identification, and cardiac ultrasound image segmentation. It provides a deep learning-based solution that considers medical or biological aspects and addresses architecture, techniques, and adversarial learning.

Format: Paperback / softback
Length: 264 pages
Publication date: 01 September 2022
Publisher: Elsevier Science Publishing Co Inc

Deep Network Design for Medical Image Computing: Principles and Applications delves into a comprehensive spectrum of medical image computing (MIC) tasks, exploring the design principles for leveraging deep learning approaches in medicine. Within this comprehensive framework, the book encompasses a wide array of MIC applications, including skin disease classification, vertebrae identification and localization, cardiac ultrasound image segmentation, 2D/3D medical image registration for intervention, metal artifact reduction, sparse-view artifact reduction, and more. For each specific topic, the book offers a deep learning-based solution that meticulously considers the medical or biological intricacies of the problem, as well as the various critical considerations surrounding architecture, the design of deep learning techniques, the appropriate application of adversarial learning, and other pertinent aspects. By providing a thorough exploration of these topics, this book aims to empower graduate students and researchers with a deeper understanding of the design principles of deep learning for MIC and to facilitate their application of these principles to address their medical challenges effectively.

Dimension: 235 x 191 (mm)
ISBN-13: 9780128243831