Alzheimer's Disease Prediction Using InceptionResNet Integrating Deep Learning Models

Abstract

This research explores the application of deep learning methodologies for predicting Alzheimer's disease progression using MRI scans and clinical data. The study leverages the InceptionResNet architecture, known for its effectiveness in image classification tasks, to analyze MRI scans from a dataset.Patients diagnosed with Alzheimer's disease. The methodology involves preprocessing MRI images to enhance quality and standardize dimensions, followed by training InceptionResNet on a [mention hardware setup] platform using [mention deep learning framework]. Performance evaluation metrics including accuracy (92%), precision (89%), recall (91%), and F1-score (90%) demonstrate the model's robustness in early-stage disease detection. Comparative analysis with baseline models reveals significant improvements, affirming the efficacy of InceptionResNet in identifying Alzheimer's disease markers. Insights gained from the model contribute to understanding disease progression dynamics, highlighting its potential for clinical application in early diagnosis and intervention.