CLAHE-Augmented MRI Dementia Classification via Soft-Voting Ensemble with Gradient-Based Analysis and Dementia Correlation
Open Access
- 1 February 2026
- book chapter
- Published by Springer Nature
- p. 87-96
Abstract
Dense and accurate automated dementia stage classification from MRI scans is still a challenging task because of the inconsistencies in structural pat- terns and the inability of current deep learning models to manage both local and global feature representations effectively. In this work, a new hybrid ensemble model is proposed that combines CNN-based (ResNet-50, ConvNeXt, DenseNet-121) and transformer-based (Swin Transformer, ViT) models to synergistically extract their complementary strengths for effective dementia classification. An explicitly crafted preprocessing pipeline, including N4 bias field correction, CLAHE, non-local means denoising, Sobel edge detection, and K-means segmentation, provides high-quality input for enhanced feature extraction. The model was tested on a dataset of 87,000 MRI scans with 8500 images independently tested. Experiment results show Swin Transformer obtained AUC-ROC scores of 0.99 for Mild Dementia and 0.97 for Moderate Dementia, and the ensemble model delivered balanced decisions for all stages of dementia. Cohen’s Kappa (0.57) and Matthews Correlation Coefficient (0.60) established model reliability, and class-wise precision-recall substantiated its discrimination capacity. Furthermore, Grad-CAM and attention maps enabled model interpretability by emphasizing primary regions driving predictions, thereby improving clinical relevance. The results highlight the effectiveness of transformer-CNN ensembles in neuroimaging-based dementia diagnosis and promise their suitability for use in real-world diagnostic assistance.Keywords
This publication has 15 references indexed in Scilit:
- Objectively measured environmental features and their association with cognition and dementia: A systematic review and meta-analysisAgeing Research Reviews, 2024
- A systematic review on recent methods on deep learning for automatic detection of Alzheimer's diseaseMedicine in Novel Technology and Devices, 2024
- Design of EEG based thought identification system using EMD & deep neural networkScientific Reports, 2024
- Point biserial correlation symbiotic organism search nanoengineering based drug delivery for tumor diagnosisScientific Reports, 2024
- An explainable machine learning approach for Alzheimer’s disease classificationScientific Reports, 2024
- Automatic assessment of Alzheimer’s disease diagnosis based on deep learning techniquesComputers in Biology and Medicine, 2020
- Detecting Alzheimer's disease Based on 4D fMRI: An exploration under deep learning frameworkNeurocomputing, 2020
- Analysis of brain sub regions using optimization techniques and deep learning method in Alzheimer diseaseApplied Soft Computing, 2020
- Diagnosis and monitoring of Alzheimer's patients using classical and deep learning techniquesExpert Systems with Applications, 2019
- Multi-modal deep learning model for auxiliary diagnosis of Alzheimer’s diseaseNeurocomputing, 2019