Journal of Soft Computing Paradigm
IRO Journals
Volume 7 — Issue 1 — March 2025

Deep Learning-Driven Alzheimer’s Disease Classification: Custom CNN and Pretrained Architectures for Accurate MRI Analysis

https://doi.org/10.36548/jscp.2025.1.003
VijayaLakshmy S M.
Department of Computer Science and Engineering, Kathir College of Engineering, Coimbatore, India
Kanimozhi D.
Department of Computer Science and Engineering, Kathir College of Engineering, Coimbatore, India
Nathiya V C.
Department of Computer Science and Engineering, Kathir College of Engineering, Coimbatore, India
PDF
PDF

How to Cite

M., VijayaLakshmy S, Kanimozhi D., and Nathiya V C. 2025. “Deep Learning-Driven Alzheimer’s Disease Classification: Custom CNN and Pretrained Architectures for Accurate MRI Analysis”. Journal of Soft Computing Paradigm 7 (1): 31-43. https://doi.org/10.36548/jscp.2025.1.003.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

— Alzheimer's Disease
— Deep Learning
— Custom Convolutional Neural Networks (CNN)
— Dementia
— Hybrid Model
— Pretrained Models
Published: 19-04-2025

Abstract

Millions of people worldwide suffer from Alzheimer's Disease (AD), a progressive neurological disorder. An early and accurate diagnosis is necessary to treat the disease more effectively. This study investigates the application of deep learning methods in classifying the Alzheimer's disease using medical imaging data. A Custom Convolutional Neural Network (CNN) was developed, and it outperformed the performance of the several state-of-the-art pre-trained models, including DenseNet121, VGG16, InceptionV3, and ResNet50, with an exceptional accuracy of 98.18%. The research demonstrates the potential of deep learning algorithms in improving the medical diagnoses by using both transfer learning techniques and custom designed architectures.

References

  1. Ge, Chenjie, Qixun Qu, Irene Yu-Hua Gu, and Asgeir Store Jakola. "Multi-stream multi-scale deep convolutional networks for Alzheimer’s disease detection using MR images." Neurocomputing 350 (2019): 60-69.
  2. Deepanshi, Ishan Budhiraja, and Deepak Garg. "Alzheimer’s disease classification using transfer learning." In International Advanced Computing Conference, pp. 73-81. Cham: Springer International Publishing, 2021.
  3. Dua, Mohit, Drishti Makhija, P. Y. L. Manasa, and Prashant Mishra. "A CNN–RNN–LSTM based amalgamation for Alzheimer’s disease detection." Journal of Medical and Biological Engineering 40, no. 5 (2020): 688-706.
  4. Solano-Rojas, Braulio, Ricardo Villalón-Fonseca, and Gabriela Marín-Raventós. "Alzheimer’s disease early detection using a low cost three-dimensional densenet-121 architecture." In The Impact of Digital Technologies on Public Health in Developed and Developing Countries: 18th International Conference, ICOST 2020, Hammamet, Tunisia, June 24–26, 2020, Proceedings 18, pp. 3-15. Springer International Publishing, 2020.
  5. Dev, Krishna, Zubair Ashraf, Pranab K. Muhuri, and Sandeep Kumar. "Deep autoencoder based domain adaptation for transfer learning." Multimedia tools and applications 81, no. 16 (2022): 22379-22405.
  6. Janghel, R. R., and Y. K. Rathore. "Deep convolution neural network based system for early diagnosis of Alzheimer's disease." Irbm 42, no. 4 (2021): 258-267.
  7. Alyahyan, Saleh. "FusionNet remote a hybrid deep learning ensemble model for remote image classification in multispectral images." Discover Computing 28, no. 1 (2025): 3.
  8. Pattanayak, Binod Kumar, Padmini Mansingh, Bibudhendu Pati, Bibhuti Bhusan Dash, Mahendra Kumar Gourisaria, and Sudhansu Shekhar Patra. "Alzheimer's Disease Classification using Capsule Network." In 2024 International Conference on Expert Clouds and Applications (ICOECA), pp. 644-649. IEEE, 2024.
  9. Khatri, Uttam, and Goo-Rak Kwon. "Diagnosis of Alzheimer's disease via optimized lightweight convolution-attention and structural MRI." Computers in Biology and Medicine 171 (2024): 108116.
  10. Laino, Maria Elena, Pierandrea Cancian, Letterio Salvatore Politi, Matteo Giovanni Della Porta, Luca Saba, and Victor Savevski. "Generative adversarial networks in brain imaging: A narrative review." Journal of imaging 8, no. 4 (2022): 83.
  11. https://www.kaggle.com/datasets/marcopinamonti/alzheimer-mri-4-classes-dataset