Ensemble Graph Attention Network with Deep U-Net for Alzheimer’s Disease Detection

Alzheimer’s disease (AD) serves as a rising global health concern further complicated by current limitations early diagnostic accuracy using standard imaging methods. This proposal will investigate an enhanced ensemble deep learning framework that integrates U-Net medical image segmentation capacity to Graph Attention Networks in order to improve the diagnosis of varying levels of Alzheimer’s disease from MRI scans. U-Net allows for the extraction of spatial compressions and urges the GAT to accurate measure fluctuations potently stated through relational connections between areas of the brain in order to measure and assess the change of the structural and relational occurrences in the progression of Alzheimer’s disease. The simulation of the proposed study will use the OASIS-1 benchmark dataset, which includes 86,000 MRI scans from patients with varying levels of dementia. The simulation study will also deploy data augmentation strategies to mitigate the class imbalance specific to the dataset. Sequentially, the proposed combined study will focus on improving the recognition rate in segmented data compared to more traditional forms of convolutional learning. The experiments in this study will yield remarkable performance results incorporating an accuracy of 96%, which will outperform standards and current models accounting for CNN, VGG19, EfficientNet, and those developed by Vision Transformer. The simulation of this proposed study will provide spatial and relational learning processes to further improve the performance of the diagnosis and classification of the stages of Alzheimer’s disease as early on as possible.

Alzheimer detection; Graph attention network; Healthcare; Health risks; UNET

Abunadi, I. (2022). Deep and hybrid learning of mri diagnosis for early detection of the progression stages in alzheimer’s disease. Connection Science, 34 (1), 2395–2430. https://doi.org/10.1080/09540091.2022.2123450

Albishri, A. A., Shah, S. H., Kang, S. S., & Lee, Y. (2022). Am-unet: Automated mini 3d end-to-end u-net based network for brain claustrum segmentation. Multimedia Tools and Applications, 81 (25), 36171–36194. https://doi.org/10.1007/s11042-021-11568-7

Ali, H. (2025). A meta-review of computational intelligence techniques for early autism disorder diagnosis. International Journal of Theoretical and Applied Computational Intelligence, 2025, 1–21. https://doi.org/https://doi.org/10.65278/IJTACI.2025.1

Aliyu, B. S., Isuwa, J., Abdulrahim, A., Abdullsahi, M., & Hassan, I. H. (2025). Enhanced feature selection for imbalanced microarray cancer gene classification using chaotic salp swarm algorithm. International Journal of Theoretical and Applied Computational Intelligence, 2025, 258–283. https://doi.org/https://doi.org/10.65278/IJTACI.2025.16

Al-Selwi, H. F., Aziz, A. A., Abas, F. B., Kayani, A., & Noor, N. M. (2023). Attention based spatial-temporal gcn with kalman filter for traffic flow prediction. International Journal of Technology, 14 (6), 1299. https://doi.org/10.14716/ijtech.v14i6.6646

Ara ?ujo, T., Teixeira, J. P., & Rodrigues, P. M. (2022). Smart-data-driven system for Alzheimer disease detection through electroencephalographic signals. Bioengineering, 9 (4), 141. https://doi.org/10.3390/bioengineering9040141

Ayub, N., Shah, S. Z. A., & Assad, D. A. (2024). Leveraging deep learning for precise alzheimer’s disease detection via mri image segmentation: A technical study [SSRN preprint]. https://doi.org/10.2139/ssrn.4974345

Bootun, D., Auzine, M. M., Ayesha, N., Idris, S., Saba, T., & Khan, M. H. M. (2025). Adamaex—alzheimer’s disease classification via attention-enhanced autoencoders and xai. Egyptian Informatics Journal, 30, 100688.

Chandra, A., Verma, S., Raghuvanshi, A. S., & Bodhey, N. K. (2023). Pccs-rau-net: Automated parcellated corpus callosum segmentation from brain mri images using modified residual attention u-net. Biocybernetics and Biomedical Engineering, 43 (2), 403–427. https://doi.org/10.1016/j.bbe.2023.02.003

Chen, K., Weng, Y., Hosseini, A. A., Dening, T., Zuo, G., & Zhang, Y. (2024). A comparative study of gnn and mlp based machine learning for the diagnosis of alzheimer’s disease involving data synthesis. Neural Networks, 169, 442–452. https://doi.org/10.1016/j.neunet.2023.10.040

Duarte, K. T. N., Sidhu, A. S., Barros, M. C., Gobbi, D. G., McCreary, C. R., Saad, F., Camicioli, R., Smith, E. E., Bento, M. P., & Frayne, R. (2024). Multi-stage semi-supervised learning enhances white matter hyperintensity segmentation. Frontiers in Computational Neuroscience, 18, 1487877. https://doi.org/10.3389/fncom.2024.1487877

Ebrahimi, A., Luo, S., & Chiong, R. (2021). Deep sequence modelling for alzheimer’s disease detection using mri. Computers in Biology and Medicine, 134, 104537. https://doi.org/10.1016/j.compbiomed.2021.104537

Firdos, S. M., Mehack, Z., Muskan, S. A., BibiNadeefa, A., & Kamepalli, S. (2024). Enhancing alzheimer’s disease prediction through deep learning models: A comparative study of googlenet, lenet, and unet. Proceedings of the First International Conference on Innovations in Communications, Electrical and Computer Engineering, 1–7. https://doi.org/10.1109/ICICEC62498.2024.10808306

Gajjar, D. B., Faldu, P., Kothadiya, D. R., Chaudhari, A. P., & Bhatt, N. M. (2025). Devitc: Deep-vision transformer to recognize originality of currency. Computer, 58 (5), 48–56. https://doi.org/10.1109/MC.2024.3514151

Hasan, M. E., & Wagler, A. (2024). A novel deep learning graph attention network for alzheimer’s disease image segmentation. Healthcare Analytics, 5, 100310. https://doi.org/10.1016/j.health.2024.100310

Hazarika, R. A., Maji, A. K., Syiem, R., Sur, S. N., & Kandar, D. (2022). Hippocampus segmentation using u-net convolutional network from brain magnetic resonance imaging. Journal of Digital Imaging, 35 (4), 893–909. https://doi.org/10.1007/s10278-022-00613-y

Helaly, H. A., Badawy, M., & Haikal, A. Y. (2022). Deep learning approach for early detection of alzheimer’s disease. Cognitive Computation, 14 (5), 1711–1727. https://doi.org/10.1007/s12559-021-09946-2

Ishtiaq, U., Abdullah, E. R. M. F., Ishtiaque, Z., Nayer, F. K., Idris, S., & Rehman, A. (2025). Lung cancer classification via entropy-driven feature selection and deep learning architectures on multi-modal imaging data. International Journal of Technology.

Kalluvila, A. (2023). Super-resolution of brain mri via u-net architecture. International Journal of Advanced Computer Science and Applications, 14 (5). Kamal, M. S., & Nimmy, S. F. (2024). Interpretable transformers for alzheimer disease diagnosis on multi-modal data. Proceedings of the International Joint Conference on Neural Networks, 1–8. https://doi.org/10.1109/IJCNN60899.2024.10651416

Karimi, M., Karimi, Z., Khosravi, M., Delaram, Z., Dehsheikhim, M. H., Najafabadi, S. A., & Tavakoli, N. (2025). Feature selection methods in big medical databases: A comprehensive survey. International Journal of Theoretical and Applied Computational Intelligence, 2025, 181–209. https://doi.org/https://doi.org/10.65278/IJTACI.2025.21

Khan, A., Akbar, S., Alghanim, A., Hassan, S. A., & Ayesha, N. (2023). Automated hybrid model for detection and classification of brain tumor. Proceedings of the Sixth International Conference of Women in Data Science at Prince Sultan University, 79–84.

Kothadiya, D., Bhatt, C., Soni, D., Gadhe, K., Patel, S., Bruno, A., & Mazzeo, P. L. (2023). Enhancing fingerprint liveness detection accuracy using deep learning: A comprehensive study and novel approach. Journal of Imaging, 9 (8), 158. https: //doi.org/10.3390/jimaging9080158

Kothadiya, D., Rehman, A., AlGhofaily, B., Bhatt, C., Ayesha, N., & Saba, T. (2025). Vgx: Vgg19-based gradient explainer interpretable architecture for brain tumor detection in microscopy magnetic resonance imaging. Microscopy Research and Technique, 88 (5), 1544–1554. https://doi.org/10.1002/jemt.24809

Kumari, R., Kohli, A., Sunil, A., Dadhich, A., Das, S., & Singh, R. K. (2024). Empirical evaluation of deep learning architectures in the early detection of alzheimer’s disease through mri data analysis. Proceedings of the International Conference on Intelligent Systems and New Applications, 1. https://doi.org/10.58190/icisna.2024.85

Lee, B., Yamanakkanavar, N., & Choi, J. Y. (2020). Automatic segmentation of brain mri using a novel patch-wise u-net deep architecture. PLOS ONE, 15 (8), e0236493. https://doi.org/10.1371/journal.pone.0236493

Li, M., Magnusson, M., van Eimeren, T., & Ellingsen, L. M. (2024). Region-based u-net for accelerated training and enhanced precision in deep brain segmentation. arXiv preprint. https://doi.org/10.48550/ARXIV.2403.09414

Li, Z., Yao, T., Kanakaraj, P., Gao, C., Bao, S., Zuo, L., Kim, M. E., Newlin, N. R., Rudravaram, G., Khairi, N. M., Huo, Y., Schilling, K. G., Kukull, W. A., Toga, A. W., Archer, D. B., Hohman, T. J., & Landman, B. A. (2024). Multi-modality conditioned variational u-net for field-of-view extension in brain diffusion mri. arXiv preprint. https://doi.org/10.48550/ARXIV.2409.13846

Liu, S., Masurkar, A. V., Rusinek, H., Chen, J., Zhang, B., Zhu, W., Fernandez-Granda, C., & Razavian, N. (2022). Generalizable deep learning model for early alzheimer’s disease detection from structural mris. Scientific Reports, 12 (1), 17106. https://doi.org/10.1038/s41598-022-20674-x

Manjupriya, R., & Leema, A. A. (2025). Efficient epileptic seizure detection with optimal channel selection and fixuppactbi-lstm deep learning model. International Journal of Technology, 16 (2), 706. https://doi.org/10.14716/ijtech.v16i2.7333

Minh, T. C., Quoc, N. K., Vinh, P. C., Phu, D. N., Chi, V. X., & Tan, H. M. (2024). Uggnet: Bridging u-net and vgg for advanced breast cancer diagnosis. arXiv preprint. https://doi.org/10.48550/ARXIV.2401.03173

Mohammed, H., Majeed, H., Al-mafrachi, B. A. R., Al-Khaffaf, M. S., & Saad, A. (2025). A novel deep learning approach for classification of abnormal teeth in panoramic x-rays. International Journal of Theoretical & Applied Computational Intelligence, 22–34.

Nugroho, H. A., Subiantoro, A., & Kusumoputro, B. (2023). Performance analysis of ensemble deep learning narx system for estimating the earthquake occurrences in the subduction zone of java island. International Journal of Technology, 14 (7), 1517. https://doi.org/10.14716/ijtech.v14i7.6702

Orouskhani, M., Zhu, C., Rostamian, S., ShomalZadeh, F., Shafiei, M., & Orouskhani, Y. (2022). Alzheimer’s disease detection from structural mri using conditional deep triplet network. Neuroscience Informatics, 2 (4), 100066. https://doi.org/10.1016/j.neuri.2022.100066

Pandey, P. K., Pruthi, J., Alzahrani, S., Verma, A., & Zohra, B. (2024). Enhancing healthcare recommendation: Transfer learning in deep convolutional neural networks for Alzheimer disease detection. Frontiers in Medicine, 11, 1445325. https://doi.org/10.3389/fmed.2024.1445325

Praschl, C., Zopf, L. M., Kiemeyer, E., Langthallner, I., Ritzberger, D., Slowak, A., Weigl, M., Blueml, V., Nesic, N., Stojmenovic, M., Kniewallner, K. M., Aigner, L., Winkler, S., & Walter, A. (2023). U-net based vessel segmentation for murine brains with small micro-magnetic resonance imaging reference datasets. PLOS ONE, 18 (10), e0291946. https://doi.org/10.1371/journal.pone.0291946

Rehman, A. (2023). Brain stroke prediction through deep learning techniques with adasyn strategy. Proceedings of the 16th International Conference on Developments in eSystems Engineering, 679–684.

Shukla, A., Tiwari, R., & Tiwari, S. (2023). Review on alzheimer disease detection methods: Automatic pipelines and machine learning techniques. Sci, 5 (1), 13. https://doi.org/10.3390/sci5010013

Sun, N., Yuan, Y., Zhang, L., & Han, Z. (2024). Convolutional neural network image segmentation of alzheimer’s disease based on multi-order 3d u-net. In A. Tall ?on-Ballesteros, E. Cort ?es-Ancos, & D. L ?opez-Garc ??a (Eds.), Frontiers in artificial intelligence and applications. IOS Press.

Sun, X., & Huo, X. (2022). Word-level and pinyin-level based chinese short text classification. IEEE Access, 10, 125552–125563.

Udayaraju, P., & Jeyanthi, P. (2024). Advances in alzheimer’s detection: A multi-learning fusion approach using choroidal neovascularization analysis. Proceedings of the International Conference on IoT Based Control Networks and Intelligent Systems, 1497–1503. https://doi.org/10.1109/ICICNIS64247.2024.10823111

Vaiyapuri, T., & Sbai, Z. (2025). Bayesian optimized boosted ensemble models for hr analytics adopting green human resource management practices. International Journal of Technology, 16 (2), 561. https://doi.org/10.14716/ijtech.v16i2.7277

Xie, L., Yushkevich, P. A., Das, S. R., Wolk, D. A., & Gibson, E. (2024). Utilizing advanced artificial intelligence for automated detection and segmentation of amyloid-related imaging abnormality (aria). Alzheimer’s & Dementia, 20 (S9), e093974.

Xun, S., Zhang, Y., Duan, S., Wang, M., Chen, J., Tong, T., Gao, Q., Lam, C., Hu, M., & Tan, T. (2024). Arga-unet: Advanced u-net segmentation model using residual grouped convolution and attention mechanism for brain tumor mri image segmentation. Virtual Reality & Intelligent Hardware, 6 (3), 203–216. https://doi.org/10.1016/j.vrih.2023.05.001

Yoon, H., Park, M., Yeom, S., Kirkcaldie, M. T. K., Summons, P., & Lee, S. H. (2021). Automatic detection of amyloid beta plaques in somatosensory cortex of an alzheimer’s disease mouse using deep learning. IEEE Access, 9, 161926–161936. https://doi.org/10.1109/ACCESS.2021.3132401

Zhang, Q., Yuan, Q., Lv, P., Zhang, M., & Lv, L. (2022). Research on medical text classification based on improved capsule network. Electronics, 11 (14), 2229. https://doi.org/10.3390/electronics11142229