Jul 2026· International Journal of Research Publication and Reviews· Vol 7, pp. 4923-4928· 0 citations
TL;DR
A multiclass Alzheimer’s disease diagnosis methodology is proposed using Explainable Artificial Intelligence (XAI) and magnetic resonance imaging (MRI) brain scans, which provides high accuracy with explainability.
Abstract
Alzheimer’s disease is a brain illness that gradually destroys the ability to think, remember and do the normal things of daily life. Effective therapy and patient care depend on early and accurate diagnosis. In this study, a multiclass Alzheimer’s disease diagnosis methodology is proposed using Explainable Artificial Intelligence (XAI) and magnetic resonance imaging (MRI) brain scans. The proposed system classifies the MRI scans into four classes such as Non-Demented, Very Mild Demented, Mild Demented and Moderate Demented. The performance of five deep learning architectures such as ResNet-18, ResNet-50, ResNet-101, DenseNet-121 and U-Net with ResNet50 are tested in the system. For better transparency of prediction, this approach uses Gradient-weighted Class Activation Mapping (or Grad-CAM) for highlighting the brain areas that contributed to the model's decision. Users can upload MRI images, classify images, display Grad-CAM heatmaps, and get confidence scores and prediction results on a Gradio-based dashboard. Experimental evaluation reveals that ResNet-101 achieves the highest classification accuracy among the evaluated models, while exhibiting reliable prediction performance. The proposed framework is a useful decision support tool for researchers and medical professionals in the diagnosis of Alzheimer’s disease, as it provides high accuracy with explainability.
An advanced DL-powered framework for the early prediction of AD using MRI data demonstrates high accuracy, robustness, and interpretability, supporting its potential for reliable early AD diagnosis in clinical settings.
K. V. S. V. Trinadh Reddy, Gundeboyina Srinivasalu, T. V. Rao et al.· Archives of Medical Research· 0 citations
A key finding documented in this work is the difficulty of classifying the transition from Non-Demented to Very Mild Demented stages, observed consistently across all ten CNN architectures.
Alzheimer's disease (AD) is a progressive neurodegenerative condition where early detection can delay the disease progression and improve the quality of life of the people concerned. Features like hippocampal atrophy, cortical thinning, and ventricular enlargement are captured by structural MRI for AI-assisted diagnosi...
S. K, N. K, K. I. Ratthi· International Conference Com...· 0 citations
The results suggest that combining EEG data with clinical and demographic information can improve the accuracy of AD and FTD diagnosis, providing a promising tool for early detection.
A. Seçkin, Fatih Soygazi· Neural computing & applicati...· 0 citations
Alzheimer’s disease (AD) classification from structural magnetic resonance imaging (MRI) may benefit from weak supervision that uses clinically meaningful but imperfect supervisory signals. We evaluated a weakly supervised framework in which a multilayer perceptron (MLP) trained on age, sex, and Mini-Mental State Exami...
Rong Xiao, T. Quan, Xing-Long Wu et al.· The Neuroscientist· 0 citations
This study presents a deep learning framework for PD classification from structural brain MRI using six complementary architectures: EfficientNetV2-S, DenseNet-169, ConvNeXt-Small, ViT-B/16, Swin-Small, and MaxViT-Tiny.