A Deep Learning-Based Approach for Alzheimer’s Disease Detection Using MRI Imaging

Abstract

Alzheimer’s disease is a progressive neurodegenerative disorder that affects memory and cognitive functions. Early detection is essential for effective treatment and management of the disease. This paper presents NeuroLens AI, a deep learning-based system designed to detect Alzheimer’s disease using MRI brain images. The proposed system utilizes a Convolutional Neural Network (CNN) model to classify MRI scans into four stages: NonDemented, VeryMildDemented, MildDemented, and ModerateDemented. The system integrates a React-based frontend, FastAPI backend, and TensorFlow model to provide a complete end-to-end solution. MRI images are preprocessed and passed through the CNN model for feature extraction and classification. The model is trained on Kaggle and OASIS datasets and achieves an accuracy of 92%. The system also includes user authentication, image upload functionality, and a real-time prediction dashboard. The results demonstrate that the proposed approach is efficient, accurate, and scalable for medical image analysis. NeuroLens AI can assist healthcare professionals in early diagnosis and decision-making.

Introduction

The document presents “NeuroLens AI,” an AI-based system designed to detect and classify Alzheimer’s disease using MRI brain images. Alzheimer’s is a progressive neurological disorder that affects memory and cognition, and early detection is important for slowing its progression. Traditional diagnostic methods rely on manual interpretation of MRI scans, which are time-consuming and prone to human error, motivating the need for automated solutions.

NeuroLens AI uses deep learning, specifically Convolutional Neural Networks (CNNs), to classify MRI images into four stages: Non-Demented, Very Mild Demented, Mild Demented, and Moderate Demented. The system is built as a full-stack application using FastAPI for the backend and React for the frontend, enabling real-time predictions through a user-friendly web interface. It also includes authentication, dataset management, and a dashboard for visualization.

The model is trained on publicly available datasets such as Kaggle and OASIS, and uses preprocessing and data augmentation techniques to improve accuracy and handle class imbalance. Advanced methods like Vision Transformers are also considered to improve performance by capturing complex patterns in MRI scans.

The literature review shows that deep learning models, especially CNNs and hybrid approaches, outperform traditional machine learning methods like SVM and logistic regression in Alzheimer’s detection. However, challenges like class imbalance and early-stage detection remain important research areas.

Conclusion

In this paper, an intelligent and scalable system, NeuroLens AI, has been proposed for the detection and classification of Alzheimer’s disease using MRI brain images. The system integrates deep learning techniques with a full-stack web application to provide an end-to-end solution for automated diagnosis. The proposed approach utilizes a Convolutional Neural Network (CNN) to perform multi-class classification of MRI images into four stages: NonDemented, VeryMildDemented, MildDemented, and ModerateDemented. The model is trained on publicly available datasets such as Kaggle and OASIS, ensuring diversity and robustness in learning. Through effective preprocessing, data augmentation, and optimized hyperparameter configuration, the model achieves an overall accuracy of approximately 92%, demonstrating its capability to accurately identify different stages of Alzheimer’s disease. One of the key contributions of this work is the integration of the trained model into a web-based platform using FastAPI and React. This allows users to upload MRI images and receive predictions in real time, making the system practical and accessible. The implementation highlights the feasibility of deploying AI-driven solutions in healthcare environments, reducing dependency on manual analysis and minimizing diagnostic errors.

References

[1] A. Dosovitskiy, L. Beyer, A. Kolesnikov et al., \"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale,\" in Proc. ICLR, 2021. [2] M. Caron, H. Touvron, I. Misra et al., \"Emerging Properties in Self-Supervised Vision Transformers,\" Proc. ICCV, 2021. [3] K. He, X. Zhang, S. Ren, and J. Sun, \"Deep Residual Learning for Image Recognition,\" in Proc. CVPR, 2016. [4] D. P. Kingma and J. Ba, \"Adam: A Method for Stochastic Optimization,\" in Proc. ICLR, 2015. [5] I. Goodfellow, Y. Bengio, and A. Courville, \"Deep Learning,\" MIT Press, 2016. [5] OASIS Brains Dataset, \"Open Access Series of Imaging Studies,” [6] Kaggle, \"Alzheimer’s Dataset (4 Class of Images),\" Available: https://www.kaggle.com [7] R. S. Desikan et al., \"Automated MRI Measures Identify Individuals with Mild Cognitive Impairment and Alzheimer’s Disease,\" Brain, vol. 132, no. 8, pp. 2048–2057, 2009. [8] A. Krizhevsky, I. Sutskever, and G. E. Hinton, \"ImageNet Classification with Deep Convolutional Neural Networks,\" in Proc. NIPS, 2012. [9] Z. Liu, Y. Lin, Y. Cao et al., \"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows,\" in Proc. ICCV, 2021. [10] J. Chen, Y. Lu, Q. Yu et al., \"TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation,\" arXiv:2102.04306, 2021. [11] T. Chen, S. Kornblith, M. Norouzi, and G. Hinton, \"A Simple Framework for Contrastive Learning of Visual Representations (SimCLR),\" in Proc. ICML, 2020. [12] R. R. Selvaraju, M. Cogswell, A. Das et al., \"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization,\" in Proc. ICCV, 2017. [13] TensorFlow, \"TensorFlow: An End-to-End Open Source Machine Learning Platform,\" Available: https://www.tensorflow.org [14] FastAPI, \"FastAPI Framework Documentation,\" Available: https://fastapi.tiangolo.com [15] React, \"React JavaScript Library Documentation,\" Available: https://react.dev [17] World Health Organization, \"Dementia Fact Sheet,\" WHO, 2023. [16] N. Gessert et al., \"Deep Learning for Alzheimer’s Disease Classification Using MRI,\" IEEE Trans. Med. Imaging, 2020. [17] S. Basaia et al., \"Automated Classification of Alzheimer’s Disease Using MRI Data and Deep Learning,\" NeuroImage: Clinical, vol. 26, 2020.

Copyright

Copyright © 2026 Varikuti Ramesh , Mr. P. Yugandar Reddy , Naguboyina Sai Ganesh, Yamarthi Stephen, Panchireddy Yuvaraju. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.