Machine Learning for Tomographic Imaging

By (author) Professor Ge Wang, Professor Yi Zhang, Professor Xiaojing Ye, Professor Xuanqin Mou

Publication date:

30 December 2019

Length of book:

411 pages

Publisher

Institute Of Physics Publishing

Dimensions:

254x178mm
7x10"

ISBN-13: 9780750322140

The area of machine learning, especially deep learning, has exploded in recent years, producing advances in everything from speech recognition and gaming to drug discovery. Tomographic imaging is another major area that is being transformed by machine learning, and its potential to revolutionise medical imaging is significant.

Written by active researchers in the field, Machine Learning for Tomographic Imaging presents a unified overview of deep-learning-based tomographic imaging. Key concepts, including classic reconstruction ideas and human vision inspired insights, are introduced as a foundation for a thorough examination of artificial neural networks and deep tomographic reconstruction. X-ray CT and MRI reconstruction methods are covered in detail, and other medical imaging applications are discussed.

An engaging and accessible style makes this book an ideal introduction for those in applied disciplines, as well as those in more theoretical fields who wish to learn about application contexts. Hands-on projects are also suggested, and links to open source software, working datasets, and network models are included.

Contents

Foreword

Preface

Acknowledgments

Author biographies

Introduction

Part I Background

1 Background knowledge

2 Tomographic reconstruction based on a learned dictionary

3 Artificial neural networks

Part II X-ray computed tomography

4 X-ray computed tomography

5 Deep CT reconstruction

Part III Magnetic resonance imaging

6 Classical methods for MRI reconstruction

7 Deep-learning-based MRI reconstruction

Part IV Others

8 Modalities and integration

9 Image quality assessment

10 Quantum computing*

Appendices

A Math and statistics basics A-1

B Hands-on networks B-1

Machine Learning for Tomographic Imaging, presents a detailed overview of the emerging discipline of deep-learning-based tomographic imaging.

The book begins with an introduction to imaging principles, tomographic reconstruction and artificial neural networks. Parts two and three provide in-depth tutorials on CT and MR image reconstruction and describe a range of recent machine learning techniques. The final part of the book covers other imaging modalities, including PET, SPECT, ultrasound and optical imaging, as well as taking a look at image quality evaluation and quantum computing. The text also includes appendices describing relevant numerical methods and suggesting hands-on projects, with sample codes and working datasets.

Tami Freeman 2020 Physics World IOP Publishing