Hybrid Deep Learning Architecture with Adaptive Feature Fusion for Multi-Stage Alzheimer’s Disease Classification

Background/Objectives: Alzheimer’s disease (AD), a progressive neurodegenerative disorder, demands precise early diagnosis to enable timely interventions. Traditional convolutional neural networks (CNNs) and deep learning models often fail to effectively integrate localized brain changes with global...

Full description

Saved in:
Bibliographic Details
Main Authors: Ahmad Muhammad, Qi Jin, Osman Elwasila, Yonis Gulzar
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Brain Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3425/15/6/612
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850156982394159104
author Ahmad Muhammad
Qi Jin
Osman Elwasila
Yonis Gulzar
author_facet Ahmad Muhammad
Qi Jin
Osman Elwasila
Yonis Gulzar
author_sort Ahmad Muhammad
collection DOAJ
description Background/Objectives: Alzheimer’s disease (AD), a progressive neurodegenerative disorder, demands precise early diagnosis to enable timely interventions. Traditional convolutional neural networks (CNNs) and deep learning models often fail to effectively integrate localized brain changes with global connectivity patterns, limiting their efficacy in Alzheimer’s disease (AD) classification. Methods: This research proposes a novel deep learning framework for multi-stage Alzheimer’s disease (AD) classification using T1-weighted MRI scans. The adaptive feature fusion layer, a pivotal advancement, facilitates the dynamic integration of features extracted from a ResNet50-based CNN and a vision transformer (ViT). Unlike static fusion methods, our adaptive feature fusion layer employs an attention mechanism to dynamically integrate ResNet50’s localized structural features and vision transformer (ViT) global connectivity patterns, significantly enhancing stage-specific Alzheimer’s disease classification accuracy. Results: Evaluated on the Alzheimer’s 5-Class (AD5C) dataset comprising 2380 MRI scans, the framework achieves an accuracy of 99.42% (precision: 99.55%; recall: 99.46%; F1-score: 99.50%), surpassing the prior benchmark of 98.24% by 1.18%. Ablation studies underscore the essential role of adaptive feature fusion in minimizing misclassifications, while external validation on a four-class dataset confirms robust generalizability. Conclusions: This framework enables precise early Alzheimer’s disease (AD) diagnosis by integrating multi-scale neuroimaging features, empowering clinicians to optimize patient care through timely and targeted interventions.
format Article
id doaj-art-360c747e3ea74f5db51a08ed248ef2b9
institution OA Journals
issn 2076-3425
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Brain Sciences
spelling doaj-art-360c747e3ea74f5db51a08ed248ef2b92025-08-20T02:24:18ZengMDPI AGBrain Sciences2076-34252025-06-0115661210.3390/brainsci15060612Hybrid Deep Learning Architecture with Adaptive Feature Fusion for Multi-Stage Alzheimer’s Disease ClassificationAhmad Muhammad0Qi Jin1Osman Elwasila2Yonis Gulzar3School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaDepartment of Management Information Systems, College of Business Administration, King Faisal University, Al-Ahsa 31982, Saudi ArabiaDepartment of Management Information Systems, College of Business Administration, King Faisal University, Al-Ahsa 31982, Saudi ArabiaBackground/Objectives: Alzheimer’s disease (AD), a progressive neurodegenerative disorder, demands precise early diagnosis to enable timely interventions. Traditional convolutional neural networks (CNNs) and deep learning models often fail to effectively integrate localized brain changes with global connectivity patterns, limiting their efficacy in Alzheimer’s disease (AD) classification. Methods: This research proposes a novel deep learning framework for multi-stage Alzheimer’s disease (AD) classification using T1-weighted MRI scans. The adaptive feature fusion layer, a pivotal advancement, facilitates the dynamic integration of features extracted from a ResNet50-based CNN and a vision transformer (ViT). Unlike static fusion methods, our adaptive feature fusion layer employs an attention mechanism to dynamically integrate ResNet50’s localized structural features and vision transformer (ViT) global connectivity patterns, significantly enhancing stage-specific Alzheimer’s disease classification accuracy. Results: Evaluated on the Alzheimer’s 5-Class (AD5C) dataset comprising 2380 MRI scans, the framework achieves an accuracy of 99.42% (precision: 99.55%; recall: 99.46%; F1-score: 99.50%), surpassing the prior benchmark of 98.24% by 1.18%. Ablation studies underscore the essential role of adaptive feature fusion in minimizing misclassifications, while external validation on a four-class dataset confirms robust generalizability. Conclusions: This framework enables precise early Alzheimer’s disease (AD) diagnosis by integrating multi-scale neuroimaging features, empowering clinicians to optimize patient care through timely and targeted interventions.https://www.mdpi.com/2076-3425/15/6/612Alzheimer’s diseasedeep learningconvolutional neural networksvision transformersadaptive feature fusionMRI classification
spellingShingle Ahmad Muhammad
Qi Jin
Osman Elwasila
Yonis Gulzar
Hybrid Deep Learning Architecture with Adaptive Feature Fusion for Multi-Stage Alzheimer’s Disease Classification
Brain Sciences
Alzheimer’s disease
deep learning
convolutional neural networks
vision transformers
adaptive feature fusion
MRI classification
title Hybrid Deep Learning Architecture with Adaptive Feature Fusion for Multi-Stage Alzheimer’s Disease Classification
title_full Hybrid Deep Learning Architecture with Adaptive Feature Fusion for Multi-Stage Alzheimer’s Disease Classification
title_fullStr Hybrid Deep Learning Architecture with Adaptive Feature Fusion for Multi-Stage Alzheimer’s Disease Classification
title_full_unstemmed Hybrid Deep Learning Architecture with Adaptive Feature Fusion for Multi-Stage Alzheimer’s Disease Classification
title_short Hybrid Deep Learning Architecture with Adaptive Feature Fusion for Multi-Stage Alzheimer’s Disease Classification
title_sort hybrid deep learning architecture with adaptive feature fusion for multi stage alzheimer s disease classification
topic Alzheimer’s disease
deep learning
convolutional neural networks
vision transformers
adaptive feature fusion
MRI classification
url https://www.mdpi.com/2076-3425/15/6/612
work_keys_str_mv AT ahmadmuhammad hybriddeeplearningarchitecturewithadaptivefeaturefusionformultistagealzheimersdiseaseclassification
AT qijin hybriddeeplearningarchitecturewithadaptivefeaturefusionformultistagealzheimersdiseaseclassification
AT osmanelwasila hybriddeeplearningarchitecturewithadaptivefeaturefusionformultistagealzheimersdiseaseclassification
AT yonisgulzar hybriddeeplearningarchitecturewithadaptivefeaturefusionformultistagealzheimersdiseaseclassification