Artificial Intelligence/Machine Learning in Nuclear Medicine and Hybrid Imaging

ISBN-13: 9783031001215 / Miękka / 2023 / 210 str.

Spis treści

PART I: INTRODUCTION

Editorial: Benefits and challenges of AI/ML in hybrid imaging and molecular imaging

P. Veit-Haibach and Ken Herrmann

 

PART II: TECHNOLOGY   

1. Role and influence of AI/ML in healthcare and specifically hybrid imaging and molecular imaging

(Benjamin L. Franc and Guido Davidzon)

1. Radiomics, Radiogenomics, AI, Deep-Learning and Machine Learning - Definitions and Imaging Applications (Jens Kleesiek, Germany)
2. Radiomics in Nuclear Medicine - Robustness, Reproducibility, Standardisation

(Reza Rezai, Toronto)

1. Evolution of AI/ML in molecular imaging – we did this before

1. AI based applications in Hybrid Imaging – how to build smart and truly multi-parametric decision models
2. Basic principles of neural networks: types, applications and “usefulness” for molecular imaging

(Josh Kaggie, Cambridge, UK, Chitresh Bhushan, GE, Niskayuna, NY, US and Dawei Gui, GE, Waukesha, Wi, US)

 

PART III CLINICAL APPLICATIONS   

Imaging biomarkers and their meaning for molecular imaging (Angel Alberich Bayarri, Valencia, Spain)

Integration of AI/ML in Clinical Routine in Molecular Imaging

1. Structured reporting with AI/ML in Molecular Imaging in Theranostics

1. Imaging biobanks for molecular imaging – how to integrate ML/AI into our databases Angel Alberich Bayarri, Valencia, Spain)

1. AI/ML Imaging applications in head and neck diseases (neuro/onco) 

(Mijin Jun, Seoul, Korea for neurodegenerative applications)

1. AI/ML Imaging applications in body oncology (Robert Seifert et al, Muenster, Germany)

1. AI/ML imaging applications in cardiac imaging (Piotr Slomka, LA, US)

AI/ML Imaging applications in therapy follow up and therapy decision support

 

PART IV: Impact of A.I. and ML on Molecular Imaging and Theranostics   

1. AI/ML will help to improve Molecular Imaging as well as the Molecular Therapy/Theranostic – what are the biggest advantages for Imaging and Therapy?. (Benjamin L. Franc and ?)

Why imaging data is not enough – AI based integration of imaging and clinical data

Legal and ethical issues in AI/ML – why does the patient does not own his /her data? 

(Prainsack, Vienna)

The role of A.I./ML for clinical trials in molecular imaging

1. Show me the money – investor landscape in AI/ML in molecular imaging and therapy

Physician centered imaging interpretation is dying out - why should I be a radiologist/nuclear medicine physician or how do we attract the smartest people to our field (Roland Hustinx, Liege, Belgium)

1. Advantages and risks of A.I./ML for Molecular Imaging Specialists – what do we need to learn to master the “beast”

O autorze

Dr. Patrick Veit-Haibach is a dual trained radiologist and nuclear medicine physician, Associate Professor of Radiology and Molecular Imaging at the University of Toronto and the Joint Department Medical Imaging (JDMI)at the University Health Network in Toronto, Canada. He currently serves as the Director of the PET/MR Program, as Division Head Abdominal Imaging as well as the Deputy Radiologist-in-Chief at the JDMI.
He has previously been an Assistant Professor of Radiology and Nuclear Medicine at the University Hospital in Zurich, Switzerland and served as the Section Head of the PET/CT-MR and PET/MR Unit in Zurich. He completed medical school at the University of Essen, Germany. During medical school traning, he completed internships/trainings in Germany, Switzerland, New Zealand and the United States.

He has recently co-edited a supplement on artificial intelligence (AI) and radiomics in the European Journal Nuclear Medicine and Molecular Imaging togethe^ 200 publications and has edited four books. His primary research areas are in Hybrid Imaging applications (PET/CT, PET/MR and SPECT/CT) in Oncology Imaging, Cardiovascular Imaging and pre-clinical imaging. He is currently member of the PET centre of excellence at the Society of Nuclear Medicine as well as editorial board member of the European Journal of Nuclear Medicine and Journal of Nuclear Medicine.

Prof. Dr. Ken Herrmann, MBA graduated from Charite Berlin Medical School in 2004 after completing away electives and ERASMUS exchanges in France, Switzerland, Chile and the US. In 2007 he received the Doctors Degree from Humboldt Universität Berlin with his work „Expression and function of A1 adenosine receptors in gliomas“. In 2011 he completed the executive MBA program at Universität Zürich, Switzerland. Professor Herrmann completed his residency in Nuclear Medicine at Klinikum rechts der Isar, Technische Universität München, as well as his habilitation titled „In Vivo-Proliferation Imaging with 3´deoxy-3´-[¹⁸F]Fluorothymidine PET in Oncology“. In May 2011 he joined as Visiting Assistant Professor and was later promoted to tenure track Associate Professor in the Ahmanson Translational Imaging Division of the Department of Molecular and Medical Pharmacology at the University of California Los Angeles (UCLA). From August 2012 to July 2016 he served as Vice Chair of the Department of Nuclear Medicine at Universitätsklinikum Würzburg. Since August 2016 Professor Herrmann acts as Chair of the Department of Nuclear Medicine at the Universitätsklinikum Essen He also is currently the Chair of the EANM Oncology & Theranostics committee and Section Editor of the Journal of Nuclear Medicine.

 

Blurb

This book includes detailed explanations of the underlying technologies and concepts used in Artificial Intelligence (AI) and Machine Learning (ML) in the context of nuclear medicine and hybrid imaging. A diverse team of authors, including pioneers in the field and respected experts from leading international institutions, share their insights, opinions and outlooks on this exciting topic.

A wide range of clinical applications are discussed, from brain applications to body indications, as well as the applicability of AI and ML for cardio-vascular conditions. The book also considers the potential impact of theranostics. To balance the technology-heavy and disease-specific applications, it also discusses ethical / legal issues, economic realities and the human factor, the physician. Though this discussion is not based on research and outcomes, it provides important insights into the ramifications of how AI and ML could transform Nuclear Medicine and Hybrid Imaging practice.

 

As the first work highlighting the role of these concepts specifically in this field, rather than for medical imaging in general, this book offers a valuable resource for Nuclear Medicine Physicians, Radiologists, Physicists, Medical Imaging Administrators and Nuclear Medicine Technologists alike.