Early Detection of Schizophrenia Using a Hybrid Swin Transformer and GNN Model on Graph-Based fMRI Analysis
محورهای موضوعی : Electrical Engineeringنفیسه فوادیان 1 , مهدیه علیان نژادی 2
1 - گروه مهندسی پزشکی
2 - گروه مهندسی پزشکی
کلید واژه: Schizophrenia, fMRI (Functional Magnetic Resonance Imaging) Deep Learning, ,
چکیده مقاله :
Early detection of schizophrenia remains a significant challenge in the field of
neuroscience, primarily due to the complex and subtle alterations in brain
activity associated with the disorder. These changes are often difficult to
detect using conventional MRI analysis techniques. Schizophrenia is
characterized by disrupted patterns of neural connectivity and functional
dynamics, which require advanced computational methods for accurate
identification. In this study, we propose a novel hybrid framework that
integrates Vision Transformers (ViTs) and Graph Neural Networks (GNNs) to
analyze functional MRI (fMRI) data. This combined approach aims to enhance
the detection and classification of schizophrenia by capturing both local
visual patterns in brain scans and the global functional connectivity structure
of the brain.
[1] Ghanbari, M., Pilevar, A. H., & Bathaeian, N. (2022). Diagnosis of schizophrenia using brain resting-state fMRI with activity maps based on deep learning. Signal, Image and Video Processing, 17, 267–275. (Springer(.
[2] Algumaei, A. H., Algunaid, R. F., Rushdi, M. A., & Yassine, I. A. (2022). Feature and decision-level fusion for schizophrenia detection based on resting-state fMRI data. PLOS One, 17(5). (PLOS).
[3] Wikipedia. (2025). Functional MRI methods and findings in schizophrenia. (Wikipedia) .
[4] Henry, E. U., Emebob, O., & Omonhinmin, C. A. (2022). Vision Transformers in Medical Imaging: A Review. arXiv preprint, arXiv:2211.10043. (arXiv)
[5] Aburass, S., Dorgham, O., Al Shaqsi, J., Abu Rumman, M., & Al-Kadi, O. (2025). Vision Transformers in Medical Imaging: A Comprehensive Review of Advancements and Applications Across Multiple Diseases. Journal of Imaging Informatics in Medicine. (Springer)
[6] Zhang, Y., Wang, J., Gorriz, J. M., & Wang, S. (2023). Deep Learning and Vision Transformer for Medical Image Analysis. MDPI Journal of Imaging, 9(7), 147. (MDPI)
[7] Mohammadi, H., & Karwowski, W. (2025). Graph Neural Networks in Brain Connectivity Studies: Methods, Challenges, and Future Directions. Brain Sciences, 15(1), 17. (MDPI)
[8] Lioi, G., Gripon, V., Brahim, A., Rousseau, F., & Farrugia, N. (2021). Gradients of connectivity as graph Fourier bases of brain activity. Network Neuroscience, 5(2), 322–336. (MIT Press)
[9] Bessadok, A., Mahjoub, M. A., & Rekik, I. (2021). Graph Neural Networks in Network Neuroscience. arXiv preprint, arXiv:2106.03535. (arXiv)
[10] Li, Y., & Zhong, Z. (2024). Decoding the application of deep learning in neuroscience: A bibliometric analysis. Frontiers in Computational Neuroscience, 18. (Frontiers)
[11] Van, H. (2023). Deep learning and neuroscience: The intersection of AI and brain research. Allied Academies Cognitive Neuroscience Journal. (Allied Academies)
[12] Richards, B. A., Lillicrap, T. P., Beaudoin, P., Bengio, Y., et al. (2023). A deep learning framework for neuroscience. University College London Research Paper. (UCL Discovery)
