Publisher Description

Artificial intelligence has been utilized to automate and improve various aspects of medical science. For radiotherapy treatment planning, many algorithms have been developed to better support planners. The book provides applications of artificial intelligence (AI) in radiation therapy according to the clinical radiotherapy workflow. An introductory section explains the necessity of AI regarding accuracy and efficiency in clinical settings followed by a basic learning method and introduction of potential applications in radiotherapy. Some chapters also include typical source codes which the reader may use in their original neural network. This book would be an excellent text for more experienced practitioners and researchers and members of medical physics communities, such as AAPM, ASTRO, and ESTRO. Students and graduate students who are focusing on medical physics would also benefit from this text. Key Features:

• Systematic chapters are designed over the radiotherapy workflow.

• Describes in detail how AI contributes to a perspective in the future radiotherapy.

• Typical source codes are included to implement a neural network.

• The book supports the reader as a developer of AI.

Author Biography

Iori Sumida is an invited faculty member in Osaka University, and he is a director of Physics and Clinical Support in Accuray, Japan. He received a Ph.D. in radiation oncology from Osaka University, Japan. He has published extensively on radiation therapy issues using neural network and machine learning.

Table of Contents

Preface
Acknowledgement
Author Biography
List of Contributors
1. Introduction
2. Artificial intelligence and machine learning
3. Overview of AI applications in radiation therapy
4. Introduction to CT/MR simulation in radiotherapy
5. Organ delineation
6. Automated treatment planning
7. Artificial intelligence in adaptive radiation therapy
8. Ai-augmented image guidance for radiation therapy delivery
9. AI for quality management in radiation therapy
10. Data-driven approaches in radiotherapy outcome modeling
11. Challenges in artificial intelligence development of radiotherapy

Details