Deep Learning for Advanced X-ray Detection and Imaging Applications

2025
ISBN: 978-3-031-75652-8
Verlag: Springer Nature Switzerland

Buch, Englisch, 261 Seiten, Format (B × H): 160 mm x 241 mm, Gewicht: 574 g

This book provides a comprehensive overview of the latest advances in applying Artificial Intelligence (AI) to advanced X-ray imaging, with a particular focus on its medical applications. Readers will discover why AI is set to revolutionize traditional signal processing and image reconstruction with vastly improved performance. The authors illustrate how Machine Learning (ML) and Deep Learning (DL) significantly advance X-ray detection analysis, image reconstruction, and other crucial steps. This book also reveals how these technologies enable photon counting detector-based X-ray Computed Tomography (CT), which has the potential not only to improve current CT images but also enable new clinical applications, such as providing higher spatial resolution, better soft tissue contrast, K-edge imaging, and simultaneous multi-contrast agent imaging.

Zielgruppe

Research

Autoren/Hrsg.

Cai, Liang (Kevin)

Iniewski, Krzysztof (Kris)

Fachgebiete

• Technische Wissenschaften Elektronik | Nachrichtentechnik Elektronik
• Naturwissenschaften Physik Elektromagnetismus Optik
• Technische Wissenschaften Sonstige Technologien | Angewandte Technik Angewandte Optik

Inhaltsverzeichnis

Deep Learning Techniques for CT Image Denoising and Resolution Enhancement.- , Physically interpretable deep learning reconstruction for photon counting spectral CT.- , Deep learning methods in dual energy CT imaging.- , Performance Evaluation of Implicit Neural Representations in Diagnostic Fan-Beam CT Imaging.- , Learning-Based Material Decomposition for Spectral X-ray Imaging.- , Learning-Based Material Decomposition for Spectral X-ray Imaging.- , Correcting Charge Sharing Distortions in Photon Counting Detectors Utilizing a Spatial-Temporal CNN.- , Machine Learning Approaches for CdZnTe / CdTe Radiation Detectors.- , Enhanced 3D X-ray Tomography: Deep Learning-based Advanced Algorithms for Fiber Instance Segmentation.- , Machine Learning-Based Image Processing in Radiotherapy.- , Deep learning-based image reconstruction of coded-aperture imaging in nuclear security applications.- , Artificial Intelligence for X-ray Photon Counting Technology: Current Status and Future Perspectives.

Über Autor(innen)

Krzysztof (Kris) Iniewski is director of development architecture and applications at Redlen Technologies Inc. in British Columbia, Canada. During his 20 years at Redlen he has managed development of highly integrated CdZnTe detector products in medical imaging and security applications. Prior to Redlen Kris hold various management and academic positions at PMC-Sierra, University of Alberta, SFU, UBC and University of Toronto.

Dr. Iniewski has published over 150+ research papers in international journals and conferences. He holds 35+ international patents granted in USA, Canada, France, Germany, and Japan. He wrote and edited 75+ books for Wiley, Cambridge University Press, Mc-Graw Hill, CRC Press and Springer. He is a frequent invited speaker and has consulted for multiple organizations internationally.

Liang (Kevin) Cai is Manager of CT Reconstruction at Canon Medical Research USA. During his time at Canon, Dr. Cai managed several industry leading DeepLearning CT reconstruction algorithm development, including Advanced intelligent Clear-IQ Engine (AiCE), Precise IQ Engine (PIQE), and Deep Learning Spectral CT. Dr. Cai has extensive experience in X-ray and Gamma-ray imaging systems development, with broad expertise in both detection physics and reconstruction algorithms. Dr. Cai has published 50+ research papers in international journals and conferences. He is also a named inventor for 20+ granted US patents.