Alzheimer’s Disease Classification using Lightweight Network MobileNet-V3
DOI:
https://doi.org/10.21063/jtif.2026.V14.1.47-58Keywords:
Alzheimer’s Disease, Classification, Deep Learning, Convolutional Neural NetworksAbstract
Alzheimer’s disease is a major public health concern characterized by progressive cognitive decline due to irreversible neuronal damage. Alzheimer’s disease represents a major global health concern in the twenty-first century. Although magnetic resonance imaging (MRI) is widely used for early diagnosis, manual interpretation is time-consuming and subject to variability. This study proposes an automated classification system based on the lightweight MobileNetV3 architecture to improve diagnostic efficiency. The model leverages depthwise separable convolutions to reduce computational complexity while maintaining high performance. MobileNetV3 models is then evaluated using appropriate metrics to assess the effectiveness of the proposed classification approach. Data augmentation techniques, including random rotation and flipping, are applied to enhance model generalization. Experimental results demonstrate that the MobileNetV3 Small model achieves superior performance, with an accuracy and F1-score of approximately 0.94, compared to 0.90 for the MobileNetV3 Large model. These findings indicate that the compact architecture provides better efficiency and reliability for Alzheimer’s disease classification. The proposed approach is suitable for deployment in resource-constrained medical environments.
References
[1] Iman Beheshti, Norihide Maikusa, Morteza Daneshmand, Hiroshi Matsuda, Hasan Demirel, and Gholamreza Anbarjafari, “Classification of Alzheimer’s Disease and Prediction of Mild Cognitive Impairment Conversion Using Histogram-Based Analysis of Patient-Specific Anatomical Brain Connectivity Networks,” Journal of Alzheimer’s Disease, vol. 60, no. 1, pp. 295–304, Aug. 2017, doi: 10.3233/JAD-161080.
[2] A. Association, “2014 Alzheimer’s disease facts and figures,” Alzheimer’s & Dementia, vol. 10, no. 2, pp. e47–e92, Mar. 2014, doi: https://doi.org/10.1016/j.jalz.2014.02.001.
[3] E. Hogervorst, E. Schröder-Butterfill, Y. S. Handajani, P. Kreager, and T. B. W. Rahardjo, “Dementia and dependency vs. proxy indicators of the active ageing index in Indonesia,” Int. J. Environ. Res. Public Health, vol. 18, no. 16, p. 8235, 2021.
[4] I. Theresia, T. P. Sani, S. Evans‐Lacko, N. Farina, L. Augustina, and Y. Turana, “Experiences of caregivers of people with dementia in Indonesia: A focus group study,” Int. J. Geriatr. Psychiatry, vol. 38, no. 12, p. e6038, 2023.
[5] E. S. van der Ploeg, Y. S. Handajani, and E. Schröder-Butterfill, “Dementia Care in Indonesia: Care Networks, Awareness & Perception,” J. Cross. Cult. Gerontol., vol. 40, no. 4, pp. 441–461, 2025, doi: 10.1007/s10823-025-09544-x.
[6] A. Association, “Changing the trajectory of Alzheimer’s disease: How a treatment by 2025 saves lives and dollars,” Chicago: Alzheimer’s Association, 2015.
[7] W. Jagust, “Imaging the evolution and pathophysiology of Alzheimer disease,” Nat. Rev. Neurosci., vol. 19, no. 11, pp. 687–700, 2018.
[8] K. J. Singer, “Unraveling the Neurocognitive Effects of Caregiver Stress Recall: An fNIRS Investigation,” 2024.
[9] S. S. A. Ali, K. Memon, N. Yahya, and S. Khan, “Deep learning frameworks for MRI-based diagnosis of neurological disorders: A systematic review and meta-analysis,” Artif. Intell. Rev., vol. 58, no. 6, p. 171, 2025.
[10] T. Tong et al., “A novel grading biomarker for the prediction of conversion from mild cognitive impairment to Alzheimer’s disease,” IEEE Trans. Biomed. Eng., vol. 64, no. 1, pp. 155–165, 2016.
[11] A. Haleem, M. Javaid, and I. H. Khan, “Current status and applications of Artificial Intelligence (AI) in medical field: An overview,” Curr. Med. Res. Pract., vol. 9, no. 6, pp. 231–237, 2019.
[12] J. Yun, S. Cao, T. Shengxin, and H. Zhang, “Skin Lesion Segmentation Based on Multi-Scale Attention Convolutional Neural Network,” IEEE Access, vol. PP, p. 1, Jul. 2020, doi: 10.1109/ACCESS.2020.3007512.
[13] C. Feng et al., “Deep Learning Framework for Alzheimer’s Disease Diagnosis via 3D-CNN and FSBi-LSTM,” IEEE Access, vol. PP, p. 1, Apr. 2019, doi: 10.1109/ACCESS.2019.2913847.
[14] S. Regmi, A. Subedi, N. K. Tomar, U. Bagci, and D. Jha, “Vision transformer for efficient chest x-ray and gastrointestinal image classification,” in Medical Imaging 2025: Computer-Aided Diagnosis, SPIE, 2025, pp. 912–923.
[15] N. Shelke, R. Somkunwar, A. Pimpalkar, S. Maurya, and S. Chhabria, “Ensemble EfficientNet: a novel technique for identification, classification and prediction of diabetic retinopathy,” Automatika, vol. 66, no. 3, pp. 543–558, Jul. 2025, doi: 10.1080/00051144.2025.2514884.
[16] P. Baglat, A. W. Salehi, A. Gupta, and G. Gupta, “Multiple Machine Learning Models for Detection of Alzheimer’s Disease Using OASIS Dataset,” in Re-imagining Diffusion and Adoption of Information Technology and Systems: A Continuing Conversation, S. K. Sharma, Y. K. Dwivedi, B. Metri, and N. P. Rana, Eds., Cham: Springer International Publishing, 2020, pp. 614–622.
[17] A. M. El-Assy, H. M. Amer, H. M. Ibrahim, and M. A. Mohamed, “A novel CNN architecture for accurate early detection and classification of Alzheimer’s disease using MRI data,” Sci. Rep., vol. 14, no. 1, p. 3463, 2024, doi: 10.1038/s41598-024-53733-6.
[18] “Klasifikasi Penyakit Alzheimer Dari Scan Mri Otak Menggunakan Convnext,” Jurnal Teknologi Informasi dan Ilmu Komputer, vol. 11, no. 6, pp. 1223–1232, Dec. 2024, doi: 10.25126/jtiik.2024118117.
[19] H.-I. Liu et al., “Lightweight deep learning for resource-constrained environments: A survey,” ACM Comput. Surv., vol. 56, no. 10, pp. 1–42, 2024.
[20] A. Howard et al., “Searching for mobilenetv3,” in Proceedings of the IEEE/CVF international conference on computer vision, 2019, pp. 1314–1324.
[21] L. Zhao and L. Wang, “A new lightweight network based on MobileNetV3,” KSII Transactions on Internet and Information Systems (TIIS), vol. 16, no. 1, pp. 1–15, 2022.
[22] X. Liang, J. Liang, T. Yin, and X. Tang, “A lightweight method for face expression recognition based on improved MobileNetV3,” IET Image Process., vol. 17, no. 8, pp. 2375–2384, Jun. 2023, doi: https://doi.org/10.1049/ipr2.12798.
[23] A. F. Majeed, P. Salehpour, L. Farzinvash, and S. Pashazadeh, “Multi-Class Brain Lesion Classification Using Deep Transfer Learning With MobileNetV3,” IEEE Access, vol. 12, pp. 155295–155308, 2024, doi: 10.1109/ACCESS.2024.3413008.
[24] S. G. Mueller et al., “Ways toward an early diagnosis in Alzheimer’s disease: the Alzheimer’s Disease Neuroimaging Initiative (ADNI),” Alzheimer’s & Dementia, vol. 1, no. 1, pp. 55–66, 2005.
[25] C. R. Jack Jr. et al., “The Alzheimer’s disease neuroimaging initiative (ADNI): MRI methods,” Journal of Magnetic Resonance Imaging, vol. 27, no. 4, pp. 685–691, Apr. 2008, doi: https://doi.org/10.1002/jmri.21049.
[26] M. Asaduzzaman, Md. K. Alom, and Md. E. Karim, “ALZENET: Deep learning-based early prediction of Alzheimer’s disease through magnetic resonance imaging analysis,” Telematics and Informatics Reports, vol. 17, p. 100189, 2025, doi: https://doi.org/10.1016/j.teler.2025.100189.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Muhammad Sadewa Wicaksana Wibowo, M Cahyo Kriswantoro, Neni Purwati
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
This journal is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License (CC BY-SA 4.0).
Authors retain copyright and grant the journal the right of first publication.
The work may be shared and adapted, even for commercial purposes, as long as appropriate credit is given and any new creations are licensed under the identical terms.
