EUVIMEDEUVIMED entdecken
Crossref

Intelligent MRI-Based Neurocognitive Stage Classification System Using Custom CNN for Alzheimer’s Disease Diagnosis

Prem Selva S, Kesavan V, Sivasurya J, Deepak M, R. Sivasubramani

International Journal of Engineering & Extended Technologies Research · 28.03.2026 · 08 (02)

DOI: 10.15662/ijeetr.2026.0802160 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Engineering & Extended Technologies Research, online erschienen am 28.03.2026. Verfasst von Prem Selva S und 4 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The increasing prevalence of Alzheimer’s disease (AD), a progressive neurodegenerative disorder that impairs memory, cognition, and daily functioning, has created an urgent need for accurate and early-stage diagnostic systems. Traditional clinical diagnosis often depends on manual interpretation of brain scans, which can be time-consuming and prone to variability. In response, Artificial Intelligence (AI), particularly Deep Learning (DL), has emerged as a powerful tool for automated medical image analysis and disease stage classification. This paper presents an intelligent MRI-based Alzheimer’s disease stage classification system using a compact Convolutional Neural Network (CNN). The proposed framework is designed to classify brain MRI scans into four clinically significant categories: Non-Demented, Very Mild Demented, Mild Demented, and Moderate Demented. To improve model robustness and generalization, multiple preprocessing and data augmentation techniques were applied to enhance image quality and increase dataset diversity. A lightweight four-layer CNN architecture was developed to automatically extract discriminative spatial features from MRI images while maintaining computational efficiency. The dataset was systematically divided into training, validation, and testing subsets to ensure reliable and unbiased performance evaluation. Experimental analysis demonstrates that the proposed model achieved a classification accuracy of 99.07%, indicating strong capability in recognizing previously unseen MRI scans. To improve the transparency and trustworthiness of the system, heatmap-based visualization techniques were incorporated to highlight the brain regions contributing to model predictions. Furthermore, a user-friendly web-based interface was developed to enable easy MRI image upload and instant disease stage prediction. The findings suggest that the proposed AI-driven framework can serve as an effective decision-support tool for healthcare professionals in the early detection and progression analysis of Alzheimer’s disease.

Zitieren

APA

S, P. S., V, K., J, S., M, D., & Sivasubramani, R. (2026). Intelligent MRI-Based Neurocognitive Stage Classification System Using Custom CNN for Alzheimer’s Disease Diagnosis. International Journal of Engineering & Extended Technologies Research, 08(02). https://doi.org/10.15662/ijeetr.2026.0802160

Vancouver

S PS, V K, J S, M D, Sivasubramani R. Intelligent MRI-Based Neurocognitive Stage Classification System Using Custom CNN for Alzheimer’s Disease Diagnosis. International Journal of Engineering & Extended Technologies Research. 2026;08(02). doi:10.15662/ijeetr.2026.0802160

BibTeX
@article{S2026,
  author = {S, Prem Selva and V, Kesavan and J, Sivasurya and M, Deepak and Sivasubramani, R.},
  title = {Intelligent MRI-Based Neurocognitive Stage Classification System Using Custom CNN for Alzheimer’s Disease Diagnosis},
  journal = {International Journal of Engineering & Extended Technologies Research},
  year = {2026},
  volume = {08},
  number = {02},
  doi = {10.15662/ijeetr.2026.0802160}
}
Kostenlos starten →