Angielski
The majority of current medical image computing (MIC) research into deep learning directly applies the techniques developed from computer vision. This book draws a distinction between computer vision and MIC and investigates what are the correct ways to leverage deep learning for medical problems.This book deliberately selects topics that cover a broad range of MIC tasks and discusses the design principles of these tasks for specialized deep learning approaches to medicine. These include 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, etc. For each topic, it provides a deep learning-based solution that takes into account the medical or biological aspect of the problem, before discussing how the solution addresses the following questions:1) what is a good network architecture for this medical application?2) what are the ways to fuse medical knowledge into the design of deep learning techniques?3) If, how, and when to introduce adversarial learning?The approach of Deep Network Design for Medical Image Computing: Principles and Applications will help graduate students and researchers develop a better understanding of the deep learning design principles for MIC and to apply them to their medical problems. Explains design principles of deep learning techniques for MIC Contains cutting-edge deep learning research on MIC Covers a broad range of MIC tasks including the classification, detection, segmentation, registration, reconstruction and synthesis of medical images
