1st Edition
Medical Image Synthesis Methods and Clinical Applications
Image synthesis across and within medical imaging modalities is an active area of research with broad applications in radiology and radiation oncology. This book covers the principles and methods of medical image synthesis, along with state-of-the-art research.
First, various traditional non-learning-based, traditional machine-learning-based, and recent deep-learning-based medical image synthesis methods are reviewed. Second, specific applications of different inter- and intra-modality image synthesis tasks and of synthetic image-aided segmentation and registration are introduced and summarized, listing and highlighting the proposed methods, study designs, and reported performances with the related clinical applications of representative studies. Third, the clinical usages of medical image synthesis, such as treatment planning and image-guided adaptive radiotherapy, are discussed. Last, the limitations and current challenges of various medical synthesis applications are explored, along with future trends and potential solutions to solve these difficulties.
The benefits of medical image synthesis have sparked growing interest in a number of advanced clinical applications, such as magnetic resonance imaging (MRI)-only radiation therapy treatment planning and positron emission tomography (PET)/MRI scanning. This book will be a comprehensive and exciting resource for undergraduates, graduates, researchers, and practitioners.
Introduction
Part 1: Methods and Principles
1. Non-Deep-Learning-Based Medical Image Synthesis Methods
Jing Wang, Xiaofeng Yang
2. Deep Learning-Based Medical Image Synthesis Methods
Yang Lei, Tonghe Wang, Xiaofeng Yang
Part 2: Applications of Inter-Modality Image Synthesis
3. MRI-Based Image Synthesis
Tonghe Wang, Xiaofeng Yang
4. CBCT/CT-Based Image Synthesis
Hao Zhang
5. CT-Based DVF/Ventilation/Perfusion Imaging
Ren Ge, Yu-Hua Huang, Jiarui Zhu, Wen Li, Jing Cai
6. Imaged-Based Dose Planning Prediction
Dan Nguyen
Part 3: Applications of Intra-Modality Image Synthesis
7. Medical Imaging Denoising
Yao Xiao, Kai Huang, Hely Lin, Ruogu Fang
8. Attenuation Correction for Quantitative PET/MR Imaging
Se-In Jang, Kuang Gong
9. High-Resolution Medical Image Estimation using Deep Learning
Xianjin Dai
10. 2D-3D Transformation for 3D Volumetric Imaging
Zhen Tian
11. Multimodality MRI Synthesis
Liangqiong Qu, Yongqin Zhang, Zhiming Cheng, Shuang Zeng, Xiaodan Zhang, Yuyin Zhou
12. Multi-Energy CT Transformation and Virtual Monoenergetic Imaging
Wei Zhao
13. Metal Artifact Reduction
Zhicheng Zhang, Lingting Zhu, Lei Xing, Lequan Yu
Part 4: Other Applications of Medical Image Synthesis
14. Synthetic Image-Aided Segmentation
Yang Lei, Richard L.J. Qiu and Xiaofeng Yang
15. Synthetic Image-Aided Registration
Yabo Fu, Xiaofeng Yang
16. CT Image Standardization Using Deep Image Synthesis Models
Md Selim, Jie Zhang, Jin Chen
Part 5: Clinic Usage of Medical Image Synthesis
17. Image-Guided Adaptive Radiotherapy
Yang Sheng, Jackie Wu, Taoran Li
Part 6: Perspectives
18. Validation and Evaluation Metrics
Jing Wang, Xiaofeng Yang
19. Limitation and Future Trends
Xiaofeng Yang
Biography
Xiaofeng Yang received B.S., M.S., and Ph.D. degrees in biomedical engineering from Xi’an Jiaotong University, China. He finished his Ph.D. training and thesis at Emory University. He completed his postdoctoral and medical physics residency training at the Department of Radiation Oncology, Emory University School of Medicine, where he is currently an Associate Professor. He is also an adjunct faculty in the Medical Physics Department at Georgia Institute of Technology, Biomedical Informatics Department at Emory University, and the Wallace H. Coulter Department of Biomedical Engineering at Emory University and Georgia Institute of Technology. Dr. Yang is a board-certified medical physicist with expertise in image-guided radiotherapy, deep learning, and multimodality medical imaging, as well as medical image analysis. He is the Director of the Deep Biomedical Imaging Laboratory at Emory University. His lab focuses on developing novel AI-aided analytical and computational tools to enhance the role of quantitative imaging in cancer treatment and to improve the accuracy and precision of radiation therapy. His research has been funded by the NIH, DOD, and industrial funding agencies. He has published over 180 peer-reviewed journal papers, and has received many scientific awards from SPIE Medical Imaging, AAPM, ASTRO, and SNMMI in the past several years. Dr. Yang was the recipient of the John Laughlin Young Scientist Award from the American Association of Physicists in Medicine in 2020. He currently serves as Associate Editor for Medical Physics and Journal of Applied Clinical Medical Physics.
