Abstract

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder that affects millions worldwide. Early detection is critical for effective intervention, but current diagnostic methods often rely on subjective clinical assessments or invasive procedures. This paper proposes a novel deep learning-based approach for the early detection of Alzheimer’s disease using multi-view MRI image fusion and explainable artificial intelligence (XAI). The proposed method integrates structural MRI (sMRI) and functional MRI (fMRI) data to capture both anatomical and functional brain changes associated with AD. A multi-stream convolutional neural network (CNN) architecture is designed to process sMRI and fMRI data separately, followed by a fusion module that combines features from both modalities. To enhance efficiency, gradient-weighted class activation mapping (Grad-CAM) to visualize regions of interest (ROIs) contributing to the diagnosis was employed. Experiments on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset demonstrate that our approach achieves superior performance compared to state-of-the-art methods, with an accuracy of 95.3%, sensitivity of 94.7%, and specificity of 95.8%. This paper provides a novel approach for early AD detection, which improved clinical decision-making.

References

• R. Chamakuri and H. Janapana, “A systematic review on recent methods on deep learning for automatic detection of Alzheimer’s disease,” Medicine in Novel Technology and Devices, vol. 25, p. 100343, Mar. 2025, doi: 10.1016/j.medntd.2024.100343.
• H. A. Raza et al., “A proficient approach for the classification of Alzheimer’s disease using a hybridization of machine learning and deep learning,” Sci Rep, vol. 14, no. 1, p. 30925, Dec. 2024, doi: 10.1038/s41598-024-81563-z.
• G. B. Frisoni, N. C. Fox, C. R. Jack, P. Scheltens, and P. M. Thompson, “The clinical use of structural MRI in Alzheimer disease,” Nat Rev Neurol, vol. 6, no. 2, pp. 67–77, Feb. 2010, doi: 10.1038/nrneurol.2009.215.
• “Functional connectivity in the resting brain: a network analysis of the default mode hypothesis - PubMed.” Accessed: Feb. 05, 2025. [Online]. Available: https://pubmed.ncbi.nlm.nih.gov/12506194/
• G. Shen, F. Ye, W. Cheng, and Q. Li, “A modified deep learning method for Alzheimer’s disease detection based on the facial submicroscopic features in mice,” BioMedical Engineering OnLine, vol. 23, no. 1, p. 109, Oct. 2024, doi: 10.1186/s12938-024-01305-0.
• “Alzheimer’s disease diagnostics by a 3D deeply supervised adaptable convolutional network - PubMed.” Accessed: Feb. 05, 2025. [Online]. Available: https://pubmed.ncbi.nlm.nih.gov/28930562/
• O. Altwijri et al., “Novel Deep-Learning Approach for Automatic Diagnosis of Alzheimer’s Disease from MRI,” Applied Sciences, vol. 13, no. 24, p. 13051, Dec. 2023, doi: 10.3390/app132413051.
• A. Payan and G. Montana, “Predicting Alzheimer’s disease: a neuroimaging study with 3D convolutional neural networks,” Feb. 09, 2015, arXiv: arXiv:1502.02506. doi: 10.48550/arXiv.1502.02506.
• “Alzheimer’s disease diagnostics by adaptation of 3D convolutional network | IEEE Conference Publication | IEEE Xplore.” Accessed: Feb. 05, 2025. [Online]. Available: https://ieeexplore.ieee.org/document/7532332
• S. Parisot et al., “Disease prediction using graph convolutional networks: Application to Autism Spectrum Disorder and Alzheimer’s disease,” Med Image Anal, vol. 48, pp. 117–130, Aug. 2018, doi: 10.1016/j.media.2018.06.001.
• S. Saravanan, K. Muthumanickam, N. Subha, and P. C. S. Mahesh, “Diagnosing Alzheimer Disease Using MRI Scan: A Deep Learning Approach,” in 2024 2nd International Conference on Sustainable Computing and Smart Systems (ICSCSS), Jul. 2024, pp. 1047–1052. doi: 10.1109/ICSCSS60660.2024.10624909.
• Y. Chen et al., “Automated Alzheimer’s disease classification using deep learning models with Soft-NMS and improved ResNet50 integration,” Journal of Radiation Research and Applied Sciences, vol. 17, no. 1, p. 100782, Mar. 2024, doi: 10.1016/j.jrras.2023.100782.
• Ö. Özaltın, “Early Detection of Alzheimer’s Disease from MR Images Using Fine-Tuning Neighborhood Component Analysis and Convolutional Neural Networks,” Arab J Sci Eng, Jan. 2025, doi: 10.1007/s13369-024-09954-y.
• M. U. Ali, S. J. Hussain, M. Khalid, M. Farrash, H. F. M. Lahza, and A. Zafar, “MRI-Driven Alzheimer’s Disease Diagnosis Using Deep Network Fusion and Optimal Selection of Feature,” Bioengineering, vol. 11, no. 11, Art. no. 11, Nov. 2024, doi: 10.3390/bioengineering11111076.
• F. Zhang, Z. Li, B. Zhang, H. Du, B. Wang, and X. Zhang, “Multi-modal deep learning model for auxiliary diagnosis of Alzheimer’s disease,” Neurocomputing, vol. 361, pp. 185–195, Oct. 2019, doi: 10.1016/j.neucom.2019.04.093.
• T. Zhang and M. Shi, “Multi-modal neuroimaging feature fusion for diagnosis of Alzheimer’s disease,” Journal of Neuroscience Methods, vol. 341, p. 108795, Jul. 2020, doi: 10.1016/j.jneumeth.2020.108795.
• S. Qiu et al., “Multimodal deep learning for Alzheimer’s disease dementia assessment,” Nat Commun, vol. 13, no. 1, p. 3404, Jun. 2022, doi: 10.1038/s41467-022-31037-5.
• Zia‐ur‐Rehman, M. K. Awang, G. Ali, and M. Faheem, “Deep learning techniques for Alzheimer’s disease detection in 3D imaging: A systematic review,” Health Sci Rep, vol. 7, no. 9, p. e70025, Sep. 2024, doi: 10.1002/hsr2.70025.
• “Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization | IEEE Conference Publication | IEEE Xplore.” Accessed: Feb. 05, 2025. [Online]. Available: https://ieeexplore.ieee.org/document/8237336
• “On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation | PLOS ONE.” Accessed: Feb. 05, 2025. [Online]. Available: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0130140
• J. Rieke, F. Eitel, M. Weygandt, J.-D. Haynes, and K. Ritter, “Visualizing Convolutional Networks for MRI-based Diagnosis of Alzheimer’s Disease,” vol. 11038, 2018, pp. 24–31. doi: 10.1007/978-3-030-02628-8_3.
• “Alzheimer’s Disease Neuroimaging Initiative,” ADNI. Accessed: Feb. 05, 2025. [Online]. Available: https://adni-lde.loni.usc.edu/
• “SPM - Statistical Parametric Mapping.” Accessed: Feb. 05, 2025. [Online]. Available: https://www.fil.ion.ucl.ac.uk/spm/
• “Alzheimer’s Disease Neuroimaging Initiative,” ADNI. Accessed: Feb. 05, 2025. [Online]. Available: https://adni-lde.loni.usc.edu/
• “Open Access Series of Imaging Studies (OASIS),” Open Access Series of Imaging Studies (OASIS). Accessed: Feb. 05, 2025. [Online]. Available: https://sites.wustl.edu/oasisbrains/
• “AIBL Study ADNI Data.” Accessed: Feb. 05, 2025. [Online]. Available: https://aibl.csiro.au/adni/index.html