Artificial Intelligence in Neuroscience

1. Auflage 2026
ISBN: 978-1-394-27885-5
Verlag: John Wiley & Sons Inc

Buch, Englisch, 368 Seiten

Provides comprehensive guidance on harnessing artificial intelligence for neuroscience research and clinical applications

The rapid development of artificial intelligence (AI) has created new opportunities for advancing the study of the brain. While recent scholarship has focused on how neuroscience can inform the design of AI systems, there is a growing need for resources that demonstrate how AI can be applied to support neuroscience research and practice. Artificial Intelligence in Neuroscience offers a detailed introduction to AI technologies and their transformative potential for fields ranging from neuroimaging and genetics to mental healthcare and neuro-oncology.

Structured around four major areas, the book begins by exploring the shared history of AI and neuroscience, from single-neuron modeling and action potentials to contemporary learning mechanisms. It then examines how AI can be used as a data analysis tool in genetics, proteomics, histology, cognition, and population health, before turning to clinical applications such as biologically plausible cognitive models, connectionist frameworks, and reinforcement learning. Additional chapters consider emerging applications, including robotics, drug screening, brain-computer interfaces, and language models. The volume concludes with a critical discussion of ethical and privacy issues, ensuring readers are equipped to navigate the responsibilities that accompany technological innovation.

Wide in scope and filled with practical insights, Artificial Intelligence in Neuroscience: - Explores the historical intersections between AI and neuroscience to contextualize current innovations
- Demonstrates applications of AI in neuroimaging, genetics, and population health research
- Details clinical applications of AI models, including reinforcement learning and connectionist frameworks
- Highlights novel uses of AI in robotics, brain-computer interfaces, and drug discovery
- Integrates technical depth with applied case studies for both academic and clinical contexts

Artificial Intelligence in Neuroscience is ideal for graduate students, early career researchers, and established professionals in neuroscience, psychology, computer science, and medicine. It is well-suited for courses in computational neuroscience, AI in healthcare, and neuroinformatics within advanced degree programs in neuroscience, biomedical sciences, data science, and clinical psychology.

Autoren/Hrsg.

Su, Li

Fachgebiete

• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz
• Naturwissenschaften Biowissenschaften Angewandte Biologie Biomathematik
• Naturwissenschaften Biowissenschaften Biowissenschaften Neurobiologie, Verhaltensbiologie
• Interdisziplinäres Wissenschaften Wissenschaften Interdisziplinär Neurowissenschaften, Kognitionswissenschaft

Inhaltsverzeichnis

List of Contributors xiii
About the Editor xvii

1 Introduction 1
Li Su and Xiong Xiong

1.1 Background and Rationale 1
1.2 Promising Potentials of AI in Neuroscience 6
1.3 Current Advances and Specific Topics Covered in this Book 8
1.4 Major Challenges and Limitations 16
1.5 Future Directions and Prospects 21
1.6 Overview of the Chapters 25

2 Deep Neural Networks in Brain Networks Study 29
Lu Zhang and Dajiang Zhu

2.1 Introduction 29
2.2 Brain Networks 30
2.3 Graph Neural Networks 32
2.4 GCNs in Understanding Brain Structure–Function Relationship 33
2.5 GCNs in Investigating Brain Disease 33
2.6 Future Work 35

3 Cerebrovascular Disease and Cognitive Function 39
Zhongzhao Teng

3.1 The Close Relationship Between the Cerebrovascular System and Cognitive Function 39
3.2 Neurovascular Physiology and the Neurobiological Basis of Cognition 42
3.3 Mechanisms of Cognitive Impairment Caused by Cerebrovascular Pathological Changes 45
3.4 Clinical Spectrum of Cerebrovascular Disease and Cognitive Impairment 56
3.5 Diagnosis and Assessment of VCI and Dementia 65
3.6 Neuropsychological Characteristics and Patterns of Cognitive Impairment 68
3.7 Intervention Strategies: Prevention, Management and Treatment 78
3.8 Challenges, Future Directions and Conclusions 81

4 Multilayer Networks in Neuroimaging 103
Vesna Vuksanovic

4.1 Introduction 103
4.2 Multilayer Networks: The Theoretical Background 104
4.3 Multilayer Networks in Neuroimaging 109
4.4 Multimodal, Multiscale Neuroimaging Data: A Multilayer Network Approach 114
4.5 Application of Multilayer Networks in Modelling Neurodegenerative Disorders 115
4.6 Conclusion and Future Directions 117

5 Artificial Intelligence-inspired Subtype Analysis for Brain Imaging 125
Yong Liu and Kun Zhao

5.1 Introduction 125
5.2 Clustering Methods 126

6 Computer-aided Diagnosis Systems in Neuroscience Based on Responsible Artificial Intelligence 139
Carmen Jimenez-Mesa, David Loìpez, Juan E Arco, Francisco J Martiìnez-Murcia, Javier Ramiìrez, Mariìa Ruz, and Juan M Goìrriz

6.1 Introduction 139

6.2 Neuroimaging Techniques 141
6.3 Machine Learning in Neuroimaging 147
6.4 Small Sample Size in Neuroimaging 151
6.5 Pathologies and Case Studies 156
6.6 Challenges and Trends in Neuroimaging 159

7 Artificial Intelligence in Neurodegenerative Disorders 173
Timothy Rittman

7.1 Introduction 173

8 Applications of Machine Learning in the Genetics of Brain Disorders 205
Matthew Bracher-Smith and Valentina Escott-Price

8.1 Introduction 205
8.2 Genetic Prediction 208
8.3 ML Approaches 211
8.4 Prominent ML Models Applied to Brain Disorders 213
8.5 Challenges and Opportunities in ML Applications 217
8.6 Conclusion 222

9 Multiscale AI for Precision Neuro-oncology 231
Ruodan Yan, Xiaofei Wang, Hao Chen, and Chao Li

9.1 Introduction 231
9.2 AI-based Brain Mapping for Neuro-oncology 232
9.3 AI-based Tissue Mapping for Neuro-oncology 245
9.4 Generalisable AI for Clinical Translation 259
9.5 Conclusion 269

10 Using AI to Detect Alzheimer's Disease from Speech: The Ethical Questions 285
Ulla Petti, Rune Nyrup, Jeffrey M Skopek, and Anna Korhonen

10.1 Introduction 285
10.2 Autonomy 286
10.3 Privacy and Data Protection 289
10.4 Welfare 292
10.5 Transparency 297
10.6 Fairness and Inclusion 299
10.7 Conclusion 300

11 Privacy-preserving AI Methods to Protect Patient Privacy 307
Lewis Hotchkiss

11.1 Introduction 307
11.2 Anonymisation 308
11.3 Privacy Concerns in AI Models 312
11.4 Privacy-preserving Techniques 321
11.5 Conclusion 331

References 331
Index 335

Über Autor(innen)

PROFESSOR LI SU is the Head of the Artificial Intelligence and Computational Neuroscience Lab at the University of Cambridge. He is also Chair of Neuroimaging at the Sheffield Institute of Translational Neuroscience, University of Sheffield. He serves as a panel member for UKRI’s AI for Health initiative and sits on the National Institute for Health and Care Excellence (NICE) Specialist Committee. He is a regional co-lead for the National Network for the Application of Data Science and AI to Dementia Research (DEMON), a member of the Alzheimer’s Society’s Research Strategy Council, and a reviewer for many research funders. He is also Associate Editor for Frontiers in Computational Neuroscience.