Convolutional Neural Network Achieves 97.67 Percent Accuracy for Alzheimer MRI Classification

Topic: Amyloid, tau and blood-test diagnosis

Using approximately 5,000 ADNI MRI images, the model achieved 97.67% accuracy, 97.73% precision, 97.67% recall, and 97.65% F1-score, with AUC values near 1.00. Learning curves indicated stable convergence without overfitting or underfitting, and confusion matrix analysis confirmed consistent multi-class discrimination. The deployed Hugging Face–Gradio application generated predictions in under five seconds per scan without performance degradation. Novelty: This research combines rigorous multi-metric validation with interactive web deployment as an artificial intelligence decision support system for early AD screening. The findings demonstrate the technical feasibility of CNN-based MRI classification for preliminary cognitive disorder screening, while emphasizing the need for multimodal integration and prospective clinical validation. Highlights• Achieved robust multi-class discrimination among AD, MCI, and CN categories using axial brain scans.• Demonstrated stable training dynamics validated through loss convergence and receiver operating characteristics.• Implemented an interactive artificial intelligence platform with sub-five-second prediction time. KeywordsAlzheimers Disease; Convolutional Neural Networks; MRI Classification; Deep Learning; Clinical Decision Support System

Key findings

• Using approximately 5,000 ADNI MRI images, the model achieved 97.67% accuracy, 97.73% precision, 97.67% recall, and 97.65% F1-score, with AUC values near 1.00.
• Learning curves indicated stable convergence without overfitting or underfitting, and confusion matrix analysis confirmed consistent multi-class discrimination.
• The deployed Hugging Face–Gradio application generated predictions in under five seconds per scan without performance degradation.
• Novelty: This research combines rigorous multi-metric validation with interactive web deployment as an artificial intelligence decision support system for early AD screening.
• The findings demonstrate the technical feasibility of CNN-based MRI classification for preliminary cognitive disorder screening, while emphasizing the need for multimodal integration and prospective clinical validation.

Why it matters

A CNN classified AD, MCI, and cognitively normal MRI scans with 97.67% accuracy and was deployed as a web tool giving predictions in under five seconds. The authors note the need for multimodal integration and prospective clinical validation, so this is a screening feasibility tool, not a treatment or cure.

New to this subject? Start with our plain-English guide: Brain scans & tests →

Study details

• Effect size97.67%; 97.73%; 97.65%
• Evidence strengthLow

Read the original

• DOI: 10.21070/acopen.11.2026.13477
• Original source →
• Free full text: Academia Open →

Full text: free to read — OpenAlex lists this copy as free to read: the link above (checked 6 Feb 1020).

@article{pangestu2026-70f8fee0,
  author  = {Pangestu, Ichwan Puja and Tundjungsari, Vitri},
  title   = {{Convolutional Neural Network Achieves 97.67 Percent Accuracy for Alzheimer MRI Classification}},
  journal = {Academia Open},
  year    = {2026},
  doi     = {10.21070/acopen.11.2026.13477},
  url     = {https://doi.org/10.21070/acopen.11.2026.13477}
}

Related studies in Brain scans and imaging

• Advanced convolutional neural network with attention mechanism for Alzheimer's disease classification using MRI Computers in Biology and Medicine · 2025-03-30 · usefulness score 46/100
• Classification and Visualization of Alzheimer’s Disease using Volumetric Convolutional Neural Network and Transfer Learning Scientific Reports · 2019-12-03 · usefulness score 45/100
• Multimodal Retinal Imaging Classification for Parkinson's Disease Using a Convolutional Neural Network Translational vision science & technology · 2024-08-01 · usefulness score 43/100
• Effective deep convolutional neural network with attention mechanism for Alzheimer disease classification Frontiers in Radiology · 2026-01-14 · usefulness score 37/100
• Application of Convolutional Neural Network Based on ResNet18 for Alzheimer Disease Classification International Journal of Artificial Intelligence Research · 2025-12-30 · usefulness score 28/100
• Convolutional neural network to identify symptomatic Alzheimer's disease using multimodal retinal imaging The British journal of ophthalmology · 2020-11-26 · usefulness score 55/100

Also tagged “classification”

835 studies in the library carry the topic tag “classification”; these are this study's neighbours in a fixed, alphabetical-by-hash tour of them, not the closest in content. All 835 tagged studies.

• Sex and age differences in atrophic rates: an ADNI study with n=1368 MRI scans Neurobiology of aging · 2010-08-01 · usefulness score 65/100 · Mild cognitive impairment
• Performance of FDG PET for detection of Alzheimer's disease in two independent multicentre samples (NEST-DD and ADNI) Dementia and geriatric cognitive disorders · 2009-09-25 · usefulness score 43/100 · Long-term cohort studies
• Disparities in Research Participation within a Multi‐Racial SARS‐CoV‐2 Cohort for Evaluation of Ultrahigh Field (7T) MRI and Clinical Precursors of Alzheimer’s Disease and Related Dementias Alzheimer s & Dementia · 2023-12-01 · usefulness score 44/100 · Risk factors

Similar studies

• A Deep Siamese Convolution Neural Network for Multi-Class Classification of Alzheimer Disease 2020 · Brain scans and imaging
• Alzheimer’s related dementia severity classification from magnetic resonance imaging using derivative-free optimization of convolutional neural network 2026 · Getting a diagnosis
• Classifying and diagnosing Alzheimer’s disease with deep learning using 6735 brain MRI images 2025 · Brain scans and imaging
• Cross-cohort generalizability of deep and conventional machine learning for MRI-based diagnosis and prediction of Alzheimer's disease 2021 · Digital health tools
• Optimized Neural Network Architectures for Early Detection of Alzheimer\'s disease Using MRI Images 2025 · Brain scans and imaging
• Alzheimer Detection Using Deep Learning Methods 2025 · Brain scans and imaging

More on Brain scans and imaging

• A review that covers this ground Random Forest Algorithm for the Classification of Neuroimaging Data in Alzheimer's Disease: A Systematic Review Frontiers in aging neuroscience · 2017-10-06 · usefulness score 68/100
• Newest in this subject Large-scale head-to-head comparison of on- and off-target profiles of [18F]Tauvid and [18F]MK6240 tau-PET in aging and Alzheimer’s disease Research Square · 2026-11-01 · Preprint — not yet peer-reviewed · usefulness score 16/100
• Newest in this subject Repetitive negative thinking is associated with amyloid accumulation over 3 years in cognitively healthy adults medRxiv · 2026-10-31 · Preprint — not yet peer-reviewed · usefulness score 16/100

See all studies in Brain scans and imaging →