Dedication

pp v-vi

Contents

pp vii-xiii

List of Contributors

pp xiv-xviii

Preface

pp xix-xxii

Part I - Theory of Deep Learning for Image Reconstruction

pp 1-2

1 - Formalizing Deep Neural Networks

pp 3-12

2 - Geometry of Deep Learning

pp 13-27

3 - Model-Based Reconstruction with Learning: From Unsupervised to Supervised and Beyond

pp 28-52

4 - Deep Algorithm Unrolling for Biomedical Imaging

pp 53-86

Part II - Deep-Learning Architecture for Various Imaging Architectures

pp 87-88

5 - Deep Learning for CT Image Reconstruction

pp 89-113

6 - Deep Learning in CT Reconstruction: Bringing the Measured Data to Tasks

pp 114-165

7 - Overview of the Deep-Learning Reconstruction of Accelerated MRI

pp 166-176

8 - Model-Based Deep-Learning Algorithms for Inverse Problems

pp 177-199

9 - k-Space Deep Learning for MR Reconstruction and Artifact Removal

pp 200-222

10 - Deep Learning for Ultrasound Beamforming

pp 223-251

11 - Ultrasound Image Artifact Removal using Deep Neural Networks

pp 252-276

Part III - Generative Models for Biomedical Imaging

pp 277-278

12 - Image Synthesis in Multi-Contrast MRI with Generative Adversarial Networks

pp 279-298

13 - Regularizing Deep-Neural-Network Paradigm for the Reconstruction of Dynamic Magnetic Resonance Images

pp 299-311

14 - Regularizing Neural Network for Phase Unwrapping

pp 312-324

15 - CryoGAN: A Deep Generative Adversarial Approach to Single-Particle Cryo-EM

pp 325-342