Generative Artificial Intelligence for Neuroimaging

Deepika Koundal currently serves as a Senior Researcher at the University of Eastern Finland, specializing in Artificial Intelligence, Machine Learning, Deep Learning, Computer Vision & Image Processing, and Cyber-Physical Systems. She holds a Ph.D. in Computer Science and Engineering and has received several prestigious accolades, including the MSCA Seal of Excellence from the European Commission. In 2023 and 2024, she was recognized as a top 2% researcher by Stanford University. She has over 13 years of teaching and research experience, having served in various academic roles including at NIT Hamirpur, Chitkara University, and UIET Panjab University. She has earned multiple research excellence awards from UPES and has published numerous research articles, edited notable books, and holds several patents. Furthermore, she contributes as a guest and associate editor for leading journals, including those published by IEEE and Elsevier. Dr. D. Jude Hemanth is currently working as a professor in Department of ECE, Karunya University, Coimbatore, India. He also holds the position of “Visiting Professor” in Faculty of Electrical Engineering and Information Technology, University of Oradea, Romania. He also serves as the “Research Scientist” of Computational Intelligence and Information Systems (CI2S) Lab, Argentina; LAPISCO research lab, Brazil; RIADI Lab, Tunisia; Research Centre for Applied Intelligence, University of Craiova, Romania and e-health and telemedicine group, University of Valladolid, Spain.Dr. Hemanth received his B.E degree in ECE from Bharathiar University in 2002, M.E degree in communication systems from Anna University in 2006 and Ph.D. from Karunya University in 2013. He has published 37 edited books with reputed publishers such as Elsevier, Springer and IET. His research areas include Computational Intelligence and Image processing. He has authored more than 200 research papers in reputed SCIE indexed International Journals and Scopus indexed International Conferences.

• Part I: Foundations 1. Introduction to Neuroscience Imaging Modalities (fMRI, EEG, MEG, etc.) and Their Challenges 2. A Primer on Generative Artificial Intelligence: Key Concepts and Architectures (GANs, VAEs, Diffusion Models, Flow-based Models, etc.). Emphasis on Explainability and Interpretability 3. Data Handling and Preprocessing in Neuroimaging for Generative AI. Dealing with Noise, Artifacts, and Variability Part II: Methodological Advancements 4. Generative Adversarial Networks (GANs) for Neuroimaging: Applications and Limitations 5. Variational Autoencoders (VAEs) for Neuroimaging: Dimensionality Reduction, Data Augmentation, and Latent Space Analysis 6. Diffusion Models for High-Fidelity Neuroimage Generation and Enhancement 7. Flow-Based Generative Models for Neuroimaging: Density Estimation and Data Augmentation 8. Hybrid and Novel Generative Models for Neuroimaging: Exploring Emerging Architectures and Combinations Part III: Applications in Neuroscience 9. Generative AI for Disease Diagnosis and Prognosis (Alzheimer's, Parkinson's, Stroke, etc.) 10. Generative AI for Personalized Medicine in Neuroscience: Tailoring Treatments and Interventions 11. Generative AI for Brain Connectivity and Network Analysis: Understanding Brain Organization and Its Alterations in Disease 12. Generative AI for Simulating Brain Development and Aging: Modeling Normal and Pathological Processes 13. Generative AI for Cognitive Neuroscience: Investigating the Neural Basis of Cognition Part IV: Challenges and Future Directions 14. Challenges and Limitations: Addressing Data Scarcity, Interpretability, Computational Costs, and Ethical Concerns 15. Future Directions and Research Opportunities: Identifying Promising Areas for Future Development and Innovation