Nhat-Kha Nguyen; Thi-Thu-Hien Pham; Nhat-Minh Nguyen; Tan-Nhu Nguyen; Ngoc-Bich Le

Transformer-Based vs. CNN-Based Deep Learning for Alzheimer’s Disease Classification: Performance and Deployment

PDF (1021KB), PP.44-63

Views: 0 Downloads: 0

Author(s)

Nhat-Kha Nguyen ¹ Thi-Thu-Hien Pham ¹ Nhat-Minh Nguyen ¹ Tan-Nhu Nguyen ¹ Ngoc-Bich Le ^1,*

1. School of Biomedical Engineering, International University, Vietnam National University HCM City, HCM City, 70000, Vietnam

* Corresponding author.

DOI: https://doi.org/10.5815/ijisa.2026.02.04

Received: 10 Nov. 2025 / Revised: 4 Jan. 2026 / Accepted: 6 Feb. 2026 / Published: 8 Apr. 2026

Index Terms

Convolutional Neural Networks, Alzheimer’s Disease, Deep Learning, EfficientNet, Vision Transformer, Web Application, Early Diagnosis

Abstract

It is well known that diagnosing Alzheimer's disease (AD) accurately and early is a major clinical challenge, especially when using brain MRI data to differentiate between subtle stages of cognitive decline. This study investigated the efficacy of two deep learning models for the classification of AD stages: Vision Transformer (ViT), a transformer-based architecture, and EfficientNetB7, a convolutional neural network. To enhance classification performance and address class imbalance, extensive data preprocessing and augmentation techniques were employed on the publicly accessible 'Alzheimer’s Dataset (4 class of Images)' from Kaggle. This dataset comprises 6,400 brain MRI images categorized into four AD stages: Non-Demented, Very Mild Demented, Mild Demented, and Moderate Demented. Techniques applied included cropping, horizontal and vertical flipping, 20-degree rotations, histogram equalization, Gaussian noise addition, Gaussian blurring, and thresholding, aimed at improving the representation of underrepresented classes. Hyperparameter optimization was executed via a two-phase methodology: an initial grid search to determine parameter ranges, succeeded by Bayesian optimization employing an upper confidence bound acquisition function to refine learning rates, batch sizes, momentum, and weight decay values. Experimental results indicated that EfficientNetB7 attained a classification accuracy of 93.5% with F1-scores surpassing 92% for early-stage classes, whereas Vision Transformer (ViT) recorded a lower accuracy of 88.7% and exhibited diminished sensitivity to early-stage instances. The performance disparity is due to ViT's dependence on extensive training datasets, which may restrict its generalization when utilized on comparatively smaller medical imaging datasets. The results indicate that, in dataset-constrained
scenarios, CNN-based architectures such as EfficientNetB7 may provide more consistent and effective performance. Using distinct training, validation, and test datasets, the model's generalization, training stability, and computational efficiency were assessed. With an intuitive user interface, the top-performing model, EfficientNetB7, was implemented as a web-based application to facilitate real-time supportive predictions for research demonstration. This comparative analysis demonstrated that the CNN-based EfficientNetB7 exhibited more robustness with constrained medical imaging data and was computationally economical, but the transformer-based ViT displayed increased sensitivity to dataset size and necessitated extended training to attain similar convergence. The development of a validated and deployable AI-based Alzheimer's disease diagnostic solution showed great promise for clinical use.

Cite This Paper

Nhat-Kha Nguyen, Thi-Thu-Hien Pham, Nhat-Minh Nguyen, Tan-Nhu Nguyen, Ngoc-Bich Le, "Transformer-Based vs. CNN-Based Deep Learning for Alzheimer’s Disease Classification: Performance and Deployment", International Journal of Intelligent Systems and Applications(IJISA), Vol.18, No.2, pp.44-63, 2026. DOI:10.5815/ijisa.2026.02.04

Reference

[1]Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, May 2015, doi: 10.1038/nature14539.
[2]A. Feroui, M. Saim, M. E. A. Lazouni, S. A. Lazzouni, Z. A. Elaouaber, and M. Messadi, “Improved diagnosis of lung cancer classification based on deep learning method,” Int. J. Biomed. Eng. Technol., vol. 46, no. 2, pp. 138–159, 2024, doi: 10.1504/IJBET.2024.141571.
[3]C. Hu, “An investigation into deep learning for the analysis of medical images,” Applied and Computational Engineering, vol. 54, no. 1, pp. 7–13, Mar. 2024, doi: 10.54254/2755-2721/54/20241121.
[4]F. R. da Silva, R. Camacho, and J. M. R. S. Tavares, “Federated Learning in Medical Image Analysis: A Systematic Survey,” Electronics (Basel)., vol. 13, no. 1, p. 47, Dec. 2023, doi: 10.3390/electronics13010047.
[5]P. R. Kharote, M. S. Sankhe, and D. Patkar, “Automated detection and grading of prostate cancer in multiparametric MRI,” Int. J. Biomed. Eng. Technol., vol. 40, no. 4, p. 372, 2022, doi: 10.1504/IJBET.2022.128088.
[6]G. K. Mourya, S. Paul, A. Handique, U. Baid, P. V. Dutande, and S. N. Talbar, “Modified U-Net for fully automatic liver segmentation from abdominal CT-image,” Int. J. Biomed. Eng. Technol., vol. 40, no. 1, p. 1, 2022, doi: 10.1504/IJBET.2022.125099.
[7]T.-N. Vo, N.-B. Le, Q.-H. Phan, T.-H. Le, and T.-T.-H. Pham, “Detection of COVID-19 from chest X-rays using deep transfer learning,” Health Informatics J., vol. 30, no. 4, Oct. 2024, doi: 10.1177/14604582241290724.
[8]B. H. T. Nguyen, B. N. Le, N. H. Trinh, H. T. Le, and T. H. T. Pham, “Breast cancer diagnosis based on detecting lymph node metastases using deep learning,” Science and Technology Development Journal, 2022, doi: 10.32508/stdj.v25i2.3894.
[9]Z. Lu, G. Qiao, and S. Zhang, “Research Advanced in Technology and Applications of Image Recognition Based on Deep Learning,” Highlights in Science, Engineering and Technology, vol. 85, pp. 418–425, Mar. 2024, doi: 10.54097/5zyqe776.
[10]A. Gupta, D. Gupta, M. Pathak, and S. K. Wagh, “The advancement of ensemble deep learning architecture for the detection and classification of brain tumours with MRI images,” Int. J. Biomed. Eng. Technol., vol. 45, no. 1, pp. 27–44, 2024, doi: 10.1504/IJBET.2024.138619.
[11]H. Shi, N. Zhang, X. Wu, and Y. Zhang, “Multimodal lung tumor image recognition algorithm based on integrated convolutional neural network,” Concurr. Comput., vol. 32, no. 21, Nov. 2020, doi: 10.1002/cpe.4965.
[12]J. Huang, “COVID-19 CT Image Detection Based on Convolutional Neural Network,” in 2023 IEEE 11th Joint International Information Technology and Artificial Intelligence Conference (ITAIC), IEEE, Dec. 2023, pp. 532–541. doi: 10.1109/ITAIC58329.2023.10409115.
[13]R. Murugesan, G. A. T., V. A., B. Azhaganathan, and P. D. D. Domnic, “Instance segmentation of neuronal cells using U-Net, mask R-CNN, and Detectron2,” Int. J. Biomed. Eng. Technol., vol. 45, no. 2, pp. 129–149, 2024, doi: 10.1504/IJBET.2024.138735.
[14]A. Hechri, A. Hamed, and A. Boudaka, “An efficient brain tumour segmentation approach using cascade convolutional neural networks,” Int. J. Biomed. Eng. Technol., vol. 44, no. 3, pp. 226–241, 2024, doi: 10.1504/IJBET.2024.137343.
[15]N. Ambily and K. Suresh, “MRI segmentation using deep learning network for brain tumour detection,” Int. J. Biomed. Eng. Technol., vol. 43, no. 4, pp. 378–389, 2023, doi: 10.1504/IJBET.2023.135398.
[16]Basavaraj Mali Patil, Megha Rani Raigonda, Sudhir Anakal, Ambresh Bhadrashetty, "Early Detection of Dementia using Deep Learning and Image Processing", International Journal of Engineering and Manufacturing, Vol.13, No.1, pp. 14-22, 2023.
[17]Markos Wondim Walle, Kula Kakeba Tune, Natnael Tilahun Sinshaw, Sudhir Kumar Mohapatra, "Transfer Learning based Breast Cancer Classification via Deep Convolutional Neural Network", International Journal of Engineering and Manufacturing, Vol.13, No.4, pp. 34-43, 2023.
[18]Prateek Keserwani, V. S. Chandrasekhar Pammi, Om Prakash, Ashish Khare, Moongu Jeon,"Classification of Alzheimer Disease using Gabor Texture Feature of Hippocampus Region", International Journal of Image, Graphics and Signal Processing, Vol.8, No.6, pp.13-20, 2016.
[19]Anil Kumar Pallikonda, P Suresh Varma, B. Vivekanandam, "Mask Region-based Convolution Neural Network (Mask R-CNN) Classification of Alzheimer’s Disease Based on Magnetic Resonance Imaging (MRI)", International Journal of Image, Graphics and Signal Processing, Vol.15, No.6, pp. 54-66, 2023.
[20]Michael Chi Seng Tang, Huong Yong Ting, Abdulwahab Funsho Atanda, Kee Chuong Ting, "Transfer Learning with EfficientNetV2 for Diabetic Retinopathy Detection", International Journal of Engineering and Manufacturing, Vol.14, No.6, pp. 54-60, 2024.
[21]Rathin Halder, Nusrat Sharmin, "Brain Ischemic Stroke Detection through Deep Learning: A Systematic Review on CT vs MRI vs CTA Images", International Journal of Education and Management Engineering, Vol.14, No.5, pp. 23-34, 2024.
[22]Saloni, R. K. Sharma, Anil K. Gupta,"Classification of High Blood Pressure Persons Vs Normal Blood Pressure Persons Using Voice Analysis", International Journal of Image, Graphics and Signal Processing, vol.6, no.1, pp.47-52, 2014.
[23]Hossein. Abbasi, Ahmed. Alshaeeb, Yasin. Orouskhani, Behrouz. Rahimi, Mostafa. Shomalzadeh, "Advanced Deep Learning Models for Accurate Retinal Disease State Detection", International Journal of Information Technology and Computer Science, Vol.16, No.3, pp.61-71, 2024.
[24]B. Vijayakumari, S. Vidhya, and J. Saranya, “Deep learning-based gender classification with dental X-ray images,” Int. J. Biomed. Eng. Technol., vol. 42, no. 1, pp. 109–121, 2023, doi: 10.1504/IJBET.2023.131694.
[25]Ahmad Ilham Gustisyaf, Ardiles Sinaga, " Implementation of Convolutional Neural Network to Classification Gender based on Fingerprint ", International Journal of Modern Education and Computer Science Vol.13, No.4, pp. 55-67, 2021.
[26]Ishwari Singh Rajput, Sonam Tyagi, Aditya Gupta, Vibha Jain, "Advances in Medical Imaging: Using Convolutional Neural Networks for White Blood Cell Identification", International Journal of Image, Graphics and Signal Processing, Vol.16, No.1, pp. 108-125, 2024.
[27]Abdullah Walid, Md. Mehedi Hasan, Tonmoy Roy, Md. Selim Hossain, Nasrin Sultana, "Deep Learning-Based Potato Leaf Disease Detection Using CNN in the Agricultural System", International Journal of Engineering and Manufacturing, Vol.13, No.6, pp. 9-22, 2023.
[28]Q.-H. Phan, V.-T. Nguyen, C.-H. Lien, T.-P. Duong, M. T.-K. Hou, and N.-B. Le, “Classification of Tomato Fruit Using Yolov5 and Convolutional Neural Network Models,” Plants, vol. 12, no. 4, p. 790, Feb. 2023, doi: 10.3390/plants12040790.
[29]Banothu Balaji, T. Satyanarayana Murthy, Ramu Kuchipudi, "A Comparative Study on Plant Disease Detection and Classification Using Deep Learning Approaches", International Journal of Image, Graphics and Signal Processing, Vol.15, No.3, pp. 48-59, 2023.
[30]S. Panigrahi, U. S. N. Raju, D. Pathak, K. V. Kadambari, and H. Ala, “Rapid detection of COVID-19 from chest X-ray images using deep convolutional neural networks,” Int. J. Biomed. Eng. Technol., vol. 41, no. 1, p. 1, 2023, doi: 10.1504/IJBET.2023.128510.
[31]M. Tan and Q. V. Le, “EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks,” May 2019.
[32]A. Dosovitskiy et al., “An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale,” Oct. 2020.
[33]Z. Cui, Z. Gao, J. Leng, T. Zhang, P. Quan, and W. Zhao, “Alzheimer’s Disease Diagnosis Using Enhanced Inception Network Based on Brain Magnetic Resonance Image,” in 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), IEEE, Nov. 2019, pp. 2324–2330. doi: 10.1109/BIBM47256.2019.8983046.
[34]A. Ebrahimi, S. Luo, and R. Chiong, “Deep sequence modelling for Alzheimer’s disease detection using MRI,” Comput. Biol. Med., vol. 134, p. 104537, Jul. 2021, doi: 10.1016/j.compbiomed.2021.104537.
[35]W. Al Shehri, “Alzheimer’s disease diagnosis and classification using deep learning techniques,” PeerJ Comput. Sci., vol. 8, p. e1177, Dec. 2022, doi: 10.7717/peerj-cs.1177.
[36]M. Yildirim and A. Cinar, “Classification of Alzheimer’s Disease MRI Images with CNN Based Hybrid Method,” Ingénierie des systèmes d information, vol. 25, no. 4, pp. 413–418, Sep. 2020, doi: 10.18280/isi.250402.
[37]B. A. Mohammed et al., “Multi-Method Analysis of Medical Records and MRI Images for Early Diagnosis of Dementia and Alzheimer’s Disease Based on Deep Learning and Hybrid Methods,” Electronics (Basel)., vol. 10, no. 22, p. 2860, Nov. 2021, doi: 10.3390/electronics10222860.
[38]M. Gharaibeh et al., “Early Diagnosis of Alzheimer’s Disease Using Cerebral Catheter Angiogram Neuroimaging: A Novel Model Based on Deep Learning Approaches,” Big Data and Cognitive Computing, vol. 6, no. 1, p. 2, Dec. 2021, doi: 10.3390/bdcc6010002.
[39]S. Liu, S. Liu, W. Cai, S. Pujol, R. Kikinis, and D. Feng, “Early diagnosis of Alzheimer’s disease with deep learning,” in 2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI), IEEE, Apr. 2014, pp. 1015–1018. doi: 10.1109/ISBI.2014.6868045.
[40]Y. Asim, B. Raza, A. K. Malik, S. Rathore, L. Hussain, and M. A. Iftikhar, “A multi‐modal, multi‐atlas‐based approach for Alzheimer detection via machine learning,” Int. J. Imaging Syst. Technol., vol. 28, no. 2, pp. 113–123, Jun. 2018, doi: 10.1002/ima.22263.
[41]P. S. Sisodia, G. K. Ameta, Y. Kumar, and N. Chaplot, “A Review of Deep Transfer Learning Approaches for Class-Wise Prediction of Alzheimer’s Disease Using MRI Images,” Archives of Computational Methods in Engineering, vol. 30, no. 4, pp. 2409–2429, May 2023, doi: 10.1007/s11831-022-09870-0.
[42]“Alzheimer’s dataset (4 class of Images).” Accessed: Jan. 20, 2022. [Online]. Available: https://www.kaggle.com/tourist55/alzheimers-dataset-4-class-of-images
[43]K. Zhang, Z. Zhang, Z. Li, and Y. Qiao, “Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks,” IEEE Signal Process. Lett., vol. 23, no. 10, pp. 1499–1503, Oct. 2016, doi: 10.1109/LSP.2016.2603342.

International Journal of Intelligent Systems and Applications (IJISA)