Next Article in Journal
Enhancing Hand Sensorimotor Function in Individuals with Cervical Spinal Cord Injury: A Novel Tactile Discrimination Feedback Approach Using a Multiple-Baseline Design
Previous Article in Journal
Real-World Case Series of Ravulizumab Use in Patients with Myasthenia Gravis in Romania
Previous Article in Special Issue
Low-Rank Tensor Fusion for Enhanced Deep Learning-Based Multimodal Brain Age Estimation
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Editorial

Advances of Artificial Intelligence in Neuroimaging

by
Iman Beheshti
1,*,
Daichi Sone
2 and
Carson K. Leung
3
1
Department of Human Anatomy and Cell Science, University of Manitoba, Winnipeg, MB R3E 0J9, Canada
2
Department of Psychiatry, Jikei University School of Medicine, Tokyo 105-8461, Japan
3
Department of Computer Science, University of Manitoba, Winnipeg, MB R3T 2N2, Canada
*
Author to whom correspondence should be addressed.
Brain Sci. 2025, 15(4), 351; https://doi.org/10.3390/brainsci15040351
Submission received: 10 February 2025 / Accepted: 5 March 2025 / Published: 28 March 2025
(This article belongs to the Special Issue Advances of AI in Neuroimaging)

1. Introduction

Neuroimaging [1,2,3] is a rapidly evolving field that involves the use of non-invasive imaging techniques to visualize and study the structure and function of the human brain. This field has experienced transformative progress—as well as significant breakthroughs in terms of the accuracy, speed, and efficiency of identifying various brain disorders—over the past decade, largely driven by technological advancements and computational innovations. Among these, artificial intelligence (AI) has emerged as a pivotal tool, offering researchers and clinicians novel approaches to explore the brain’s structure and function [4,5,6,7,8,9,10]. AI models have been widely applied in the analysis and interpretation of neuroimaging data, aiding researchers and clinicians in diagnosing, treating, and monitoring patients with neurological and psychiatric disorders. This Special Issue, titled “Advances of AI in Neuroimaging”, was conceived to provide a platform for cutting-edge research at the intersection of AI and neuroimaging, aiming to revolutionize neuroscience and healthcare.
The primary motivation behind this Special Issue was the increasing demand for innovative solutions to address the complexity of neuroimaging data, especially in the context of neurological and psychiatric disorders. AI techniques, such as machine learning (ML) [11,12] and deep learning (DL) [13], offer unparalleled potential for biomarker discovery, disease prediction, and personalized treatment strategies. With the prevalence of brain disorders increasing, the need for accurate and efficient diagnostic tools is more pressing than ever.
This Special Issue sought to highlight both technical advancements and their practical implications for patient care and healthcare systems. The contributions span a range of neuroimaging modalities, including magnetic resonance imaging (MRI), positron emission tomography (PET), computed tomography (CT), and electroencephalography (EEG). By addressing challenges such as data complexity, model interpretability, and cost-efficiency, the featured research underscores the indispensable role of AI in advancing neuroimaging and its applications.

2. Summary of Accepted Papers

This Special Issue attracted widespread attention, receiving over 30 submissions from researchers from around the world. Each submission underwent rigorous quality control by the editorial team and the journal, ensuring adherence to the highest academic standards. The final selection of 17 accepted papers—consisting of 14 research articles, 1 review, 1 perspective, and 1 systematic review—represents cutting-edge research that successfully passed evaluations by expert peer reviewers in the field. Below is a synthesized overview of the published works.
Several studies (Contributions 1–3) focused on the application of ML and DL in medical imaging and surgical outcomes. For example, Ghanem et al. (Contribution 1) produced a systematic review examining the use of ML and DL models in predicting outcomes such as length of stay, readmissions, and mortality in spine surgery, revealing data imbalances and variations in evaluation metrics. Similarly, Rasheed et al. (Contribution 2) introduced a novel image enhancement methodology to improve the classification of brain tumors, achieving superior results compared with pre-trained models such as VGG16 and ResNet50, which are convolutional neural networks (CNNs) made up of 16 and 50 layers, respectively. The review by Shah and Heiss (Contribution 3) provided an in-depth look at AI’s applications in neurology, emphasizing its potential to predict neurological impairments, intracranial hemorrhage expansion, and outcomes for comatose patients, showcasing its diagnostic utility across diverse data sources.
Neuroimaging played a pivotal role in several contributions (Contributions 4–8). For instance, Rudroff (Contribution 4) provided his perspective on AI’s potential to analyze neuroimaging data, such as PET scans, to optimize treatment protocols and contribute to Long Coronavirus Disease (long COVID) research. Xiong et al. (Contribution 5) utilized support vector machines (SVMs) to classify Parkinson’s disease subtypes using arterial spin labeling MRI, while Wang et al. (Contribution 6) proposed a diagnostic model integrating multiple imaging modalities—namely, diffusion tensor imaging (DTI), structural MRI (sMRI), and functional MRI (fMRI)—to enhance the diagnosis of major depressive disorder (MDD). Similarly, Liu et al. (Contribution 7) introduced a low-rank tensor fusion algorithm to improve brain age estimation by integrating multimodal neuroimaging data, demonstrating enhanced accuracy. Yamao et al. (Contribution 8) proposed a deep learning method for directly predicting the centiloid scale based on amyloid PET images.
Several papers addressed neurodegenerative diseases and cognitive impairment (Contributions 9–12). For example, Saha et al. (Contribution 9) investigated baseline MRI data to predict the response of Alzheimer’s disease patients to repetitive transcranial magnetic stimulation (rTMS) treatment, while Grigas et al. (Contribution 10) demonstrated how super-resolved MRI images and optimized DL models improved mild cognitive impairment detection. Cerna et al. (Contribution 11) explored the neural mechanisms underlying Tai Chi’s benefits for cognitive and physical function, highlighting its potential to mitigate age-related declines in functional connectivity. Sone et al. (Contribution 12) examined disease progression patterns in temporal lobe epilepsy by using diffusion tensor imaging, revealing associations between white matter damage and clinical metrics.
Advancements in virtual reality (VR) and collaborative technologies also featured prominently. For instance, Tadayyoni et al. (Contribution 13) examined EEG data to classify user immersion in VR training environments, achieving high accuracy rates in distinguishing cognitive states and offering insights into real-time user engagement. Similarly, Shih et al. (Contribution 14) assessed inter-brain synchrony patterns in collaborative design tasks, comparing co-located and distributed settings to better understand team performance dynamics. This Special Issue also delves into cutting-edge methodologies, such as generative adversarial networks (GANs) (Contribution 15) and novel brain activity mapping (Contribution 16). Huynh et al. (Contribution 15) applied GANs to diagnose neurological conditions using functional connectivity data, while Huang (Contribution 16) introduced a method for analyzing task-evoked whole-brain activity, providing a unique lens to study individual brain variability during tasks. Lastly, Manabe et al. (Contribution 17) focused on skill assessment in laparoscopic surgery by comparing EEG-based models, revealing that a three-dimensional CNN approach significantly outperformed traditional methods in classifying expertise levels. This curated collection of papers underscores the transformative potential of AI-driven research in neuroimaging and its ability to address clinical and scientific challenges.

3. Statistics on the Special Issue

The accepted papers were authored by 67 researchers from 14 countries, emphasizing the global collaboration underlying these advancements (Figure 1). Submissions were led by contributors from the USA (43 authors), China (22 authors), and Canada (16 authors), among others. The selected studies reflect diverse areas of expertise and applications, unified by their focus on leveraging AI to advance neuroimaging. The research featured in this Special Issue reflects prominent themes through its keywords: ML (17 keywords), neuroimaging techniques (8 keywords), brain functions and disorders (9 keywords), advanced methodologies (10 keywords), and practical applications (12 keywords) (Figure 2). Together, these works illustrate the breadth and depth of interdisciplinary innovation showcased in this Special Issue.

4. Conclusions

This Special Issue received significant attention, with the volume of submissions and the quality of accepted papers far exceeding our initial expectations. The rigorous selection process and peer review ensured that only the most impactful and innovative contributions were published. By highlighting the convergence of AI and neuroimaging, this issue lays the groundwork for future breakthroughs, fostering collaboration and advancing research at the intersection of neuroscience and technology.

Author Contributions

I.B., D.S. and C.K.L. have all significantly contributed to the development of this Special Issue, providing meaningful, direct, and intellectual input equally. All authors have read and agreed to the published version of the manuscript.

Funding

This research was partially supported by the Natural Sciences and Engineering Research Council of Canada (NSERC) (C.K.L.) and the University of Manitoba (C.K.L.).

Acknowledgments

As Guest Editors of this Special Issue, we had the privilege of evaluating an array of compelling articles. We extend our heartfelt gratitude to the authors for their valuable submissions and to the reviewers for their thorough and constructive evaluations of the manuscripts. We also thank editors and staff at MDPI for their assistance in processing this Special Issue.

Conflicts of Interest

The authors confirm that this research was carried out without any commercial or financial interests.

Abbreviations

The following abbreviations are used in this manuscript:
AIArtificial intelligence
CNNConvolutional neural network
COVIDCoronavirus disease
CTComputed tomography
DLDeep learning
DTIDiffusion tensor imaging
EEGElectroencephalography
fMRIFunctional magnetic resonance imaging
GANGenerative adversarial network
MDDMajor depressive disorder
MLMachine learning
MRIMagnetic resonance imaging
PETPositron emission tomography
rTMSRepetitive transcranial magnetic stimulation
sMRIStructural magnetic resonance imaging
SVMsSupport vector machines
VRVirtual reality

List of Contributions

  • Ghanem, M.; Ghaith, A.K.; El-Hajj, V.G.; Bhandarkar, A.; de Giorgio, A.; Elmi-Terander, A.; Bydon, M. Limitations in evaluating machine learning models for imbalanced binary outcome classification in spine surgery: A systematic review. Brain Sci. 2023, 13, 1723. https://doi.org/10.3390/brainsci13121723.
  • Rasheed, Z.; Ma, Y.-K.; Ullah, I.; Ghadi, Y.Y.; Khan, M.Z.; Khan, M.A.; Abdusalomov, A.; Alqahtani, F.; Shehata, A.M. Brain tumor classification from MRI using image enhancement and convolutional neural network techniques. Brain Sci. 2023, 13, 1320. https://doi.org/10.3390/brainsci13091320.
  • Shah, S.P.; Heiss, J.D. Artificial intelligence as a complementary tool for clincal [clinical] decision-making in stroke and epilepsy. Brain Sci. 2024, 14, 228. https://doi.org/10.3390/brainsci14030228.
  • Rudroff, T. Artificial intelligence’s transformative role in illuminating brain function in long COVID patients using PET/FDG. Brain Sci. 2024, 14, 73. https://doi.org/10.3390/brainsci14010073.
  • Xiong, J.; Zhu, H.; Li, X.; Hao, S.; Zhang, Y.; Wang, Z.; Xi, Q. Auto-classification of Parkinson’s disease with different motor subtypes using arterial spin labelling MRI based on machine learning. Brain Sci. 2023, 13, 1524. https://doi.org/10.3390/brainsci13111524.
  • Wang, J.; Li, T.; Sun, Q.; Guo, Y.; Yu, J.; Yao, Z.; Hou, N.; Hu, B. Automatic diagnosis of major depressive disorder using a high- and low-frequency feature fusion framework. Brain Sci. 2023, 13, 1590. https://doi.org/10.3390/brainsci13111590.
  • Liu, X.; Zheng, G.; Beheshti, I.; Ji, S.; Gou, Z.; Cui, W. Low-rank tensor fusion for enhanced deep learning-based multimodal brain age estimation. Brain Sci. 2024, 14, 1252. https://doi.org/10.3390/brainsci14121252.
  • Yamao, T.; Miwa, K.; Kaneko, Y.; Takahashi, N.; Miyaji, N.; Hasegawa, K.; Wagatsuma, K.; Kamitaka, Y.; Ito, H.; Matsuda, H. Deep learning-driven estimation of centiloid scales from amyloid pet images with 11C-PiB and 18F-labeled tracers in Alzheimer’s disease. Brain Sci. 2024, 14, 406. https://doi.org/10.3390/brainsci14040406.
  • Saha, C.; Figley, C.R.; Lithgow, B.; Fitzgerald, P.B.; Koski, L.; Mansouri, B.; Anssari, N.; Wang, X.; Moussavi, Z. Can brain volume-driven characteristic features predict the response of Alzheimer’s patients to repetitive transcranial magnetic stimulation? a pilot study. Brain Sci. 2024, 14, 226. https://doi.org/10.3390/brainsci14030226.
  • Grigas, O.; Damaševičius, R.; Maskeliūnas, R. Positive effect of super-resolved structural magnetic resonance imaging for mild cognitive impairment detection. Brain Sci. 2024, 14, 381. https://doi.org/10.3390/brainsci14040381.
  • Cerna, J.; Gupta, P.; He, M.; Ziegelman, L.; Hu, Y.; Hernandez, M.E. Tai chi practice buffers aging effects in functional brain connectivity. Brain Sci. 2024, 14, 901. https://doi.org/10.3390/brainsci14090901.
  • Sone, D.; Sato, N.; Shigemoto, Y.; Beheshti, I.; Kimura, Y.; Matsuda, H. Estimated disease progression trajectory of white matter disruption in unilateral temporal lobe epilepsy: A data-driven machine learning approach. Brain Sci. 2024, 14, 992. https://doi.org/10.3390/brainsci14100992.
  • Tadayyoni, H.; Campos, M.S.R.; Quevedo, A.J.U.; Murphy, B.A. Biomarkers of immersion in virtual reality based on features extracted from the EEG signals: A machine learning approach. Brain Sci. 2024, 14, 470. https://doi.org/10.3390/brainsci14050470.
  • Shih, Y.-T.; Wang, L.; Wong, C.H.Y.; Sin, E.L.L.; Rauterberg, M.; Yuan, Z.; Chang, L. The effects of distancing design collaboration necessitated by COVID-19 on brain synchrony in teams compared to co-located design collaboration: A preliminary study. Brain Sci. 2024, 14, 60. https://doi.org/10.3390/brainsci14010060.
  • Huynh, N.; Yan, D.; Ma, Y.; Wu, S.; Long, C.; Sami, M.T.; Almudaifer, A.; Jiang, Z.; Chen, H.; Dretsch, M.N.; et al. The use of generative adversarial network and graph convolution network for neuroimaging-based diagnostic classification. Brain Sci. 2024, 14, 456. https://doi.org/10.3390/brainsci14050456.
  • Huang, J. The commonality and individuality of human brains when performing tasks. Brain Sci. 2024, 14, 125. https://doi.org/10.3390/brainsci14020125.
  • Manabe, T.; Rahul, F.N.U.; Fu, Y.; Intes, X.; Schwaitzberg, S.D.; De, S.; Cavuoto, L.; Dutta, A. Distinguishing laparoscopic surgery experts from novices using EEG topographic features. Brain Sci. 2023, 13, 1706. https://doi.org/10.3390/brainsci13121706.

References

  1. Ombao, H.; Lindquist, M.; Thompson, W.; Aston, J. (Eds.) Handbook of Neuroimaging Data Analysis; Chapman and Hall/CRC: New York, NY, USA, 2016. [Google Scholar]
  2. Scott, M. (Ed.) Encyclopedia of Neuroimaging: Volume VI (Advances and New Frontiers); Hayle Medical: New York, NY, USA, 2015. [Google Scholar]
  3. Yen, C.; Lin, C.-L.; Chiang, M.-C. Exploring the frontiers of neuroimaging: A review of recent advances in understanding brain functioning and disorders. Life 2023, 13, 1472. [Google Scholar] [CrossRef] [PubMed]
  4. Berson, E.R.; Aboian, M.S.; Malhotra, A.; Payabvash, S. Artificial intelligence for neuroimaging and musculoskeletal radiology: Overview of current commercial algorithms. Semin. Roentgenol. 2023, 58, 178–183. [Google Scholar] [CrossRef] [PubMed]
  5. Borchert, R.J.; Azevedo, T.; Badhwar, A.; Bernal, J.; Betts, M.; Bruffaerts, R.; Burkhart, M.C.; Dewachter, I.; Gellersen, H.M.; Low, A.; et al. Artificial intelligence for diagnostic and prognostic neuroimaging in dementia: A systematic review. Alzheimer’s Dement. 2023, 19, 5885–5904. [Google Scholar] [CrossRef] [PubMed]
  6. Brahma, N.; Vimal, S. Artificial intelligence in neuroimaging: Opportunities and ethical challenges. Brain Spine 2024, 4, 102919. [Google Scholar] [CrossRef] [PubMed]
  7. Choi, K.S.; Sunwoo, L. Artificial intelligence in neuroimaging: Clinical applications. Investig. Magn. Reson. Imaging (iMRI) 2022, 26, 1–9. [Google Scholar] [CrossRef]
  8. Dalboni da Rocha, J.L.; Lai, J.; Pandey, P.; Myat, P.S.M.; Loschinskey, Z.; Bag, A.K.; Sitaram, R. Artificial intelligence for neuroimaging in pediatric cancer. Cancers 2025, 17, 622. [Google Scholar] [CrossRef] [PubMed]
  9. Hao, B.; Leung, C.K.; Camorlinga, S.; Reed, M.H.; Bunge, M.K.; Wrogemann, J.; Higgins, R.J. A computer-aided change detection system for paediatric acute intracranial haemorrhage. In Proceedings of the C3S2E 2008, Montreal, QC, Canada, 12–13 May 2008; pp. 109–111. [Google Scholar] [CrossRef]
  10. Monsour, R.; Dutta, M.; Mohamed, A.-Z.; Borkowski, A.; Viswanadhan, N.A. Neuroimaging in the era of artificial intelligence: Current applications. Fed. Pract. 2022, 39 (Suppl. S1), S14–S20. [Google Scholar] [CrossRef] [PubMed]
  11. Damer, A.; Chaudry, E.; Eftekhari, D.; Benseler, S.M.; Safi, F.; Aviv, R.I.; Tyrrell, P.N. Neuroimaging scoring tools to differentiate inflammatory central nervous system small-vessel vasculitis: A need for artificial intelligence/machine learning?—A scoping review. Tomography 2023, 9, 1811–1828. [Google Scholar] [CrossRef] [PubMed]
  12. Pierre, K.; Turetsky, J.; Raviprasad, A.; Razavi, S.M.S.; Mathelier, M.; Patel, A.; Lucke-Wold, B. Machine learning in neuroimaging of traumatic brain injury: Current landscape, research gaps, and future directions. Trauma Care 2024, 4, 31–43. [Google Scholar] [CrossRef]
  13. Xu, M.; Ouyang, Y.; Yuan, Z. Deep learning aided neuroimaging and brain regulation. Sensors 2023, 23, 4993. [Google Scholar] [CrossRef] [PubMed]
Figure 1. Geographic distribution of authors contributing to this Special Issue.
Figure 1. Geographic distribution of authors contributing to this Special Issue.
Brainsci 15 00351 g001
Figure 2. Distribution of keywords across research categories in this Special Issue.
Figure 2. Distribution of keywords across research categories in this Special Issue.
Brainsci 15 00351 g002
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Share and Cite

MDPI and ACS Style

Beheshti, I.; Sone, D.; Leung, C.K. Advances of Artificial Intelligence in Neuroimaging. Brain Sci. 2025, 15, 351. https://doi.org/10.3390/brainsci15040351

AMA Style

Beheshti I, Sone D, Leung CK. Advances of Artificial Intelligence in Neuroimaging. Brain Sciences. 2025; 15(4):351. https://doi.org/10.3390/brainsci15040351

Chicago/Turabian Style

Beheshti, Iman, Daichi Sone, and Carson K. Leung. 2025. "Advances of Artificial Intelligence in Neuroimaging" Brain Sciences 15, no. 4: 351. https://doi.org/10.3390/brainsci15040351

APA Style

Beheshti, I., Sone, D., & Leung, C. K. (2025). Advances of Artificial Intelligence in Neuroimaging. Brain Sciences, 15(4), 351. https://doi.org/10.3390/brainsci15040351

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop