A hybrid CNN–BiLSTM network with additive attention for automated four-stage classification of Alzheimer's disease from brain MRI

Overview

1. School of Computer Science Engineering and Information Systems, Vellore Institute of Technology (VIT), Vellore, India

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.

Reproduced under the paper's license (CC BY), from the paper cited above.

Code

The paper links to its data and to no code of its authors: see the Data section.

Tracing map

A tracing map links a paper to the code its authors published: this paper has none, so it has no map.

Data

Datasets cited

• data.mendeley.com/datasets/ch87yswbz4, at Mendeley Data; found in “Data availability statement”
• doi:10.17632/ch87yswbz4.1, at the source; found in “Data availability statement”

Data availability statement

Publicly available datasets were analyzed in this study. The Alzheimer's disease MRI dataset is available from Mendeley Data: Yakkundi, Ananya (2023), Alzheimer's disease dataset, Version 1. https://data.mendeley.com/datasets/ch87yswbz4/1. DOI: 10.17632/ch87yswbz4.1 (https://doi.org/10.17632/ch87yswbz4.1). Further details about the dataset are available in the repository.

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 3 November 2026: the first record

Recorded: type, language, journal, volume, pages, dates, 3 authors, 8 keywords, 51 references.

Cite

This paper

Deenadayalan, T., Shantharajah, S. P., & Ramu, S. P. (2026). A hybrid CNN–BiLSTM network with additive attention for automated four-stage classification of Alzheimer's disease from brain MRI. Frontiers in artificial intelligence, 9, 1948601.

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.1155/2024/6111483

Implications of Convolutional Neural Network for Brain MRI Image Classification to Identify Alzheimer's Disease.

Journal: Parkinson's disease

In common: DOI 10.17632/ch87yswbz4.1, Alzheimer's / dementia, structural MRI / diffusion, 2 references

[2] doi:10.1038/s41598-026-36037-9

Alzheimer's related dementia severity classification from magnetic resonance imaging using derivative-free optimization of convolutional neural network.

Journal: Scientific reports

In common: DOI 10.17632/ch87yswbz4.1, Alzheimer's / dementia, structural MRI / diffusion, 2 references

[3] doi:10.1038/s41598-025-85703-x [code]

Stacked CNN-based multichannel attention networks for Alzheimer disease detection.

Journal: Scientific reports

In common: Alzheimer's / dementia, structural MRI / diffusion, 5 references

[4] doi:10.1038/s41598-025-15007-7

A novel interpreted deep network for Alzheimer's disease prediction based on inverted self attention and vision transformer.

Journal: Scientific reports

In common: data.mendeley.com/datasets/ch87yswbz4, Alzheimer's / dementia, structural MRI / diffusion, 1 reference

[5] doi:10.1162/imag.a.1129

Deep learning interpretability in neuroimaging: A comprehensive survey and methodological recommendations.

Journal: Imaging neuroscience (Cambridge, Mass.)

In common: 5 references

[6] doi:10.1002/hbm.70276 [code]

Mind the Gap: Does Brain Age Improve Alzheimer's Disease Prediction?

Journal: Human brain mapping

In common: Alzheimer's / dementia, structural MRI / diffusion, 4 references

[7] doi:10.1038/s41598-026-50791-w [code]

Hybrid Vi+ECNN framework for advanced ADHD diagnostic accuracy in medical imaging.

Journal: Scientific reports

In common: structural MRI / diffusion, 4 references

[8] doi:10.3390/healthcare11182551

Improving Alzheimer's Disease Classification in Brain MRI Images Using a Neural Network Model Enhanced with PCA and SWLDA.

Journal: Healthcare (Basel, Switzerland)

In common: Alzheimer's / dementia, structural MRI / diffusion, 3 references

[9] doi:10.3390/diagnostics13071216

Accurate Detection of Alzheimer's Disease Using Lightweight Deep Learning Model on MRI Data.

Journal: Diagnostics (Basel, Switzerland)

In common: Alzheimer's / dementia, structural MRI / diffusion, 3 references

[10] doi:10.3389/fpsyt.2024.1395563

Enhancing Alzheimer's disease diagnosis and staging: a multistage CNN framework using MRI.

Journal: Frontiers in psychiatry

In common: Alzheimer's / dementia, structural MRI / diffusion, 3 references

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion: code errors and mismatches between the code and the paper about this paper and its code, from readers and its authors, beside the paper and its tracing map.

Reproductions: reports from readers who ran the authors' code and did not get the paper's result, what they ran, with which environment, commit and data.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.