AN EXPLAINABLE DEEP LEARNING MODEL FOR ALZHEIMER’S DIAGNOSIS
Abstract
Alzheimer’s disease is a neurodegenerative disorder causing cognitive decline and memory loss. This study proposes XAI-NET, a deep learning model leveraging architectures such as EfficientNet_V2, MobileNet_V2, and Xception for MRI-based diagnosis. Explainable AI techniques, including SHAP and LIME, are applied to enhance model transparency and interpretability. Experimental results on the ADNI dataset demonstrate high accuracy and robustness, supporting early and reliable Alzheimer’s diagnosis.
Tài liệu tham khảo
[1] “Dementia.” Accessed: May 19, 2026. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/dementia?
[2] S. Ben Hassen, M. Neji, Z. Hussain, A. Hussain, A. M. Alimi, and M. Frikha, “Deep learning methods for early detection of Alzheimer’s disease using structural MR images: a survey,” Neurocomputing, vol. 576, p. 127325, Apr. 2024, doi: 10.1016/J.NEUCOM.2024.127325.
[3] V. Viswan, N. Shaffi, M. Mahmud, K. Subramanian, and F. Hajamohideen, “Explaina-ble Artificial Intelligence in Alzheimer’s Disease Classification: A Systematic Review,” Cognitive Computation 2023 16:1, vol. 16, no. 1, pp. 1–44, Nov. 2023, doi: 10.1007/S12559-023-10192-X.
[4] H. Saif et al., “Explainable AI for Alzheimer Detection: A Review of Current Methods and Applications,” Applied Sciences 2024, Vol. 14, Page 10121, vol. 14, no. 22, p. 10121, Nov. 2024, doi: 10.3390/APP142210121.
[5] D. Bootun, M. M. Auzine, N. Ayesha, S. Idris, T. Saba, and M. Heenaye-Mamode Khan, “ADAMAEX—Alzheimer’s disease classification via attention-enhanced auto-encoders and XAI,” Egyptian Informatics Journal, vol. 30, p. 100688, Jun. 2025, doi: 10.1016/J.EIJ.2025.100688.
[6] M. Odusami, R. Maskeliūnas, R. Damaševičius, and S. Misra, “Explainable Deep-Learning-Based Diagnosis of Alzheimer’s Disease Using Multimodal Input Fusion of PET and MRI Images,” Journal of Medical and Biological Engineering 2023 43:3, vol. 43, no. 3, pp. 291–302, Jun. 2023, doi: 10.1007/S40846-023-00801-3.
[7] M. Hernandez, U. Ramon-Julvez, and F. Ferraz, “Explainable AI toward understanding the performance of the top three TADPOLE Challenge methods in the forecast of Alz-heimer’s disease diagnosis,” PLoS One, vol. 17, no. 5, p. e0264695, May 2022, doi: 10.1371/JOURNAL.PONE.0264695.
[8] H. Saif et al., “Explainable AI for Alzheimer Detection: A Review of Current Methods and Applications,” Applied Sciences 2024, Vol. 14, Page 10121, vol. 14, no. 22, p. 10121, Nov. 2024, doi: 10.3390/APP142210121.
[9] 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.
[10] J. Wen et al., “Convolutional neural networks for classification of Alzheimer’s disease: Overview and reproducible evaluation,” Med. Image Anal., vol. 63, Jul. 2020, doi: 10.1016/J.MEDIA.2020.101694.
[11] Y. Li, B. Xu, Q. Bai, Z. Liu, J. Zhu, and Q. Chen, “Vision Transformer-Based Identifi-cation for Early Alzheimer’s Disease and Mild Cognitive Impairment,” Information 2026, Vol. 17, Page 129, vol. 17, no. 2, p. 129, Jan. 2026, doi: 10.3390/INFO17020129.
[12] J. Cummings, G. Lee, A. Ritter, M. Sabbagh, and K. Zhong, “Alzheimer’s disease drug development pipeline: 2020,” Alzheimer’s and Dementia: Translational Research and Clinical Interventions, vol. 6, no. 1, 2020, doi: 10.1002/TRC2.12050.
[13] C. R. Jack et al., “NIA-AA Research Framework: Toward a biological definition of Alzheimer’s disease,” Alzheimer’s and Dementia, vol. 14, no. 4, pp. 535–562, Apr. 2018, doi: 10.1016/J.JALZ.2018.02.018;SUBPAGE:STRING:FULL.
[14] Sapna Nigam and Rajni Jain and Vaibhav Kumar Singh and Sudeep Marwaha and Alka Arora and Samyak Jain, “EfficientNet architecture and attention mechanism-based wheat disease identification model,” International Conference on Machine Learning and Data Engineering (ICMLDE 2023), vol. 2-June, 2024, pp. 383-393, doi: https://doi.org/10.1016/j.procs.2024.04.038
[15] F. Chollet, “Xception: Deep Learning with Depthwise Separable Convolutions,” Pro-ceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, vol. 2017-January, pp. 1800–1807, Oct. 2016, doi: 10.1109/CVPR.2017.195.
[16] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L. C. Chen, “MobileNetV2: In-verted Residuals and Linear Bottlenecks,” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 4510–4520, Jan. 2018, doi: 10.1109/CVPR.2018.00474.
[17] H. Saif et al., “Explainable AI for Alzheimer Detection: A Review of Current Methods and Applications,” Applied Sciences 2024, Vol. 14, Page 10121, vol. 14, no. 22, p. 10121, Nov. 2024, doi: 10.3390/APP142210121.
[18] A. Shrikumar, P. Greenside, and A. Kundaje, “Learning important features through propagating activation differences,” 34th International Conference on Machine Learn-ing, ICML 2017, vol. 7, pp. 4844–4866, 2017.
[19] M. T. Ribeiro, S. Singh, and C. Guestrin, “‘why should i trust you?’ explaining the pre-dictions of any classifier,” NAACL-HLT 2016 - 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technolo-gies, Proceedings of the Demonstrations Session, pp. 97–101, 2016, doi: 10.18653/v1/n16-3020.
[20] “ADNI | Alzheimer’s Disease Neuroimaging Initiative.” Accessed: May 19, 2026. [Online]. Available: https://adni.loni.usc.edu/