A hybrid CNN–BiLSTM network with additive attention for automated four-stage classification of Alzheimer's disease from brain MRI
- 1School of Computer Science Engineering and Information Systems, Vellore Institute of Technology (VIT) , ,
Abstract
AD is a progressive and irreversible neurodegenerative disorder. Because the structural changes that accompany the earliest stages of the disease are subtle and easily overlooked, manual interpretation of MRI is time-consuming and prone to inter-observer disagreement. This study presents an end-to-end deep learning framework that fuses spatial and sequential reasoning to classify brain MRI into four clinically meaningful stages: Person with no dementia, Person with very mild dementia, Person with mild dementia, and Person with moderate dementia. An additive attention mechanism subsequently weights the most informative positions before a compact dense head produces the final decision. Class imbalance is addressed by capped oversampling of real minority slices combined with residual cost-sensitive weighting, applied to the training fold only; pixel-space SMOTE is deliberately avoided because interpolating between two unregistered MRI slices produces images without an anatomical referent. Exact-duplicate screening is applied prior to partitioning, and a quantitative near-duplicate audit is reported for the fixed folds. Trained on 6,400 grayscale MRI slices under a stratified 70/15/15 protocol, the proposed CNN-BiLSTM-Attention model attains a test accuracy of 95.94%, a balanced accuracy of 96.08%, an MCC of 0.9334, a Cohen's kappa of 0.9325 and a macro-averaged one-vs.-rest AUC of 0.9954, on a slice-level held-out test fold. Per-class analysis shows strong sensitivity and specificity for the three better-represented stages; the extremely rare Person with moderate dementia class (nine test images) shows a favorable point estimate but is too small to support a claim of robust detection on its own. Attention maps and Grad-CAM overlays localize the evidence the network uses, and an error-structure analysis shows that no misclassification spans more than two stages. Because the corpus carries no subject identifiers, patient-grouped partitioning is not possible and the reported accuracies should be interpreted as an upper bound attainable under a slice-level split; this constraint is quantified explicitly and motivates the external-validation study outlined in the manuscript. Overall, the results highlight the methodological value of coupling convolutional feature extraction with bidirectional sequence modeling and additive attention under a leakage-aware, imbalance-aware evaluation protocol for multi-stage AD staging.
Related
- Feature-aware attention convolutional neural network for efficient pulmonary fibrosis classification from chest CT images with FPGA deployment
- A trustworthy anatomically-guided region-aware deep learning framework for automated Alzheimer’s disease classification from brain MRI
- An attention-guided dense convolutional network for automated diabetic foot ulcer segmentation
- HierTAC-Net: a robust and explainable hierarchical attention network for multi-configuration gastrointestinal endoscopic image classification
- UAC-Net: a unified multi-task network with aggregated contextual attention and cross-layer fusion for brain tumor segmentation and classification
BibTeX
@article{deenadayalan2026hybrid,
title = {{A hybrid CNN–BiLSTM network with additive attention for automated four-stage classification of Alzheimer's disease from brain MRI}},
author = {T. Deenadayalan and S. P. Shantharajah and Swarna Priya Ramu},
journal = {Frontiers in artificial intelligence},
year = {2026},
month = oct,
doi = {10.3389/frai.2026.1948601},
url = {https://europepmc.org/article/PMC/PMC13725815},
note = {CC BY},
}
RIS
TY - JOUR
TI - A hybrid CNN–BiLSTM network with additive attention for automated four-stage classification of Alzheimer's disease from brain MRI
AU - T. Deenadayalan
AU - S. P. Shantharajah
AU - Swarna Priya Ramu
PY - 2026
DA - 2026/10/16
JO - Frontiers in artificial intelligence
DO - 10.3389/frai.2026.1948601
UR - https://europepmc.org/article/PMC/PMC13725815
AB - AD is a progressive and irreversible neurodegenerative disorder. Because the structural changes that accompany the earliest stages of the disease are subtle and easily overlooked, manual interpretation of MRI is time-consuming and prone to inter-observer disagreement. This study presents an end-to-end deep learning framework that fuses spatial and sequential reasoning to classify brain MRI into four clinically meaningful stages: Person with no dementia, Person with very mild dementia, Person with mild dementia, and Person with moderate dementia. An additive attention mechanism subsequently weights the most informative positions before a compact dense head produces the final decision. Class imbalance is addressed by capped oversampling of real minority slices combined with residual cost-sensitive weighting, applied to the training fold only; pixel-space SMOTE is deliberately avoided because interpolating between two unregistered MRI slices produces images without an anatomical referent. Exact-duplicate screening is applied prior to partitioning, and a quantitative near-duplicate audit is reported for the fixed folds. Trained on 6,400 grayscale MRI slices under a stratified 70/15/15 protocol, the proposed CNN-BiLSTM-Attention model attains a test accuracy of 95.94%, a balanced accuracy of 96.08%, an MCC of 0.9334, a Cohen's kappa of 0.9325 and a macro-averaged one-vs.-rest AUC of 0.9954, on a slice-level held-out test fold. Per-class analysis shows strong sensitivity and specificity for the three better-represented stages; the extremely rare Person with moderate dementia class (nine test images) shows a favorable point estimate but is too small to support a claim of robust detection on its own. Attention maps and Grad-CAM overlays localize the evidence the network uses, and an error-structure analysis shows that no misclassification spans more than two stages. Because the corpus carries no subject identifiers, patient-grouped partitioning is not possible and the reported accuracies should be interpreted as an upper bound attainable under a slice-level split; this constraint is quantified explicitly and motivates the external-validation study outlined in the manuscript. Overall, the results highlight the methodological value of coupling convolutional feature extraction with bidirectional sequence modeling and additive attention under a leakage-aware, imbalance-aware evaluation protocol for multi-stage AD staging.
SN - 2624-8212
ER -