A Survey on Detection of Alzheimer’s Disease from Brain MRI Scans

ULAVA GANGOTHRI NAIDU; NEELAKANTAM SURYA TEJA; GATALA SATHISH; DUVVURU DEEPTHI; GUNJI BUELA; M BRAHMA KOWSHIK KUMAR

A Survey on Detection of Alzheimer’s Disease from Brain MRI Scans

Authors: ULAVA GANGOTHRI NAIDU, NEELAKANTAM SURYA TEJA, GATALA SATHISH, DUVVURU DEEPTHI, GUNJI BUELA, M BRAHMA KOWSHIK KUMAR

Unique Paper ID: 177962
Volume: 11
Issue: 12
PageNo: 1733-1741

Keywords: Alzheimer’s computer-aided diagnosis deep learning DenseNet121 image enhancement MobileNetV2 Transfer learning Conventional neural networks CLAHE ESRGAN.

Abstract:
Health Coder is a research project aimed at classifying Alzheimer's disease using AI and brain MRI images to help in early diagnosis. The project uses a dataset of 6400 preprocessed MRI images, each resized to 128 x 128 pixels, representing different stages of Alzheimer's. The goal is to develop an AI model that can identify the disease's progression. To achieve this, the MRI images will be preprocessed to improve their quality, reduce noise, and standardize the data. Deep learning models, trained with TensorFlow and Keras, will then classify the images into various stages of Alzheimer's. The models will be optimized for better performance, considering metrics like accuracy, precision, and recall. The performance of different models will be evaluated and compared to determine the most effective one. The results, including the MRI images, predictions, and metrics, will be visualized for easier analysis. The project will also include a detailed report summarizing the methodology, results, limitations, and possible future improvements. Alzheimer’s Disease (AD) is characterized by the gradual degeneration and decline of brain cells, leading to irreversible neurological changes. This study investigates advanced image enhancement techniques for improving AD diagnosis using brain MRI. The methods used include CLAHE (Contrast Limited Adaptive Histogram Equalization) to enhance local image contrast and ESRGAN (Enhanced Super Resolution Generative Adversarial Networks) to improve image resolution. These preprocessing methods improve MRI images and classification accuracy. An ensemble model of MobileNetV2 and DenseNet121, two efficient deep-learning models with feature extraction capabilities, were used as classifiers.

Download article

email to a friend

Cite This Article

ISSN: 2349-6002
Volume: 11
Issue: 12
PageNo: 1733-1741

A Survey on Detection of Alzheimer’s Disease from Brain MRI Scans

Available:https://ijirt.org/Article?manuscript=177962

05 May, 2025

A Survey On Advanced Surveillance System for Intelligent Threat Detection

05 May, 2025

A Survey On Data-Driven Air Quality Prediction Using Machine Learning

05 May, 2025

A Survey On AI-Powered Smart Farming Assistant: Transforming Agriculture with Machine Learning and Deep Learning

05 May, 2025

SURVEY ON AI-Based Driver Drowsiness Detection And Alert System

05 May, 2025

A Survey On Real-Time Traffic Monitoring and Speed Violation Detection System using Yolov8 and Centroid Tracking

05 May, 2025

Survey on Machine Learning-Driven Early Diagnosis Framework for Brain Stroke Detection using Medical Imaging

05 May, 2025

Survey on AI Powered Transformative Post Generator for Social Media using LLM and Explicit Filter

05 May, 2025

EXAMINATION OF THE INTEGRATION OF ELECTRICAL VEHICLES AND RENEWABLE ENERGY SOURCES INTO MICROGRIDS

05 May, 2025

A REVIEW OF FUZZY LOGIC CONTROLLERS FOR ENERGY MANAGEMENT IN VEHICLES WITH HYBRID ELECTRIC AND HYBRID ELECTRIC AND HYBRID ENERGY STORAGE SYSTEMS

02 May, 2025

REFER TO POWER MONITORING FOR AC ELECTRIC VEHICLE CHARGING

Impact Factor
8.01 (Year 2024)

UGC Approved
Journal no 47859

Join Our IPN

IJIRT Partner Network

Submit your research paper and those of your network (friends, colleagues, or peers) through your IPN account, and receive 800 INR for each paper that gets published.

Join Now

Latest Publication

Recent Conferences

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024 Last Date: 15th March 2024

Submit inquiry