Multi-scale 3D CNN with imbalance-aware training for structural MRI-based six-class Alzheimer disease staging

Topic: Amyloid, tau and blood-test diagnosis

Alzheimer's disease staging from structural magnetic resonance imaging (MRI) is challenging when clinically adjacent stages and severe class imbalance are considered simultaneously. This study evaluates six-class classification of cognitively normal, subjective memory complaint, early mild cognitive impairment, mild cognitive impairment, late mild cognitive impairment, and Alzheimer's disease using T1-weighted MRI from the Alzheimer's Disease Neuroimaging Initiative (ADNI). The final cohort included 3592 MRI volumes from 904 participants, with subjective memory complaint representing 3.79% of the data. We developed a parameter-compact three-dimensional convolutional neural network (3D CNN) with multi-scale volumetric feature extraction and imbalance-aware training using class weighting, focal loss with label smoothing, weighted sampling, and minority-class intensity perturbation. In the primary evaluation, partitioning was performed at the MRI ImageID (scan) level: a fixed test set of 719 MRI volumes was excluded from model development, while the remaining 2873 vol were used in five stratified training and validation folds. ImageIDs were mutually exclusive across partitions; however, participants were not grouped, and longitudinal scans from the same participant could therefore occur in different partitions. The proposed model achieved 0.9018 ± 0.0452 accuracy, 0.8804 ± 0.0393 macro F1, 0.8762 ± 0.0544 Matthews correlation coefficient (MCC), and 0.9463 ± 0.0056 macro area under the receiver operating characteristic curve (AUC) under this scan-level protocol. A same-data EfficientNet-B0 baseline achieved stronger aggregate performance, while the proposed model used 43.7% fewer parameters. Paired ablation analysis showed that weighted sampling did not improve aggregate metrics but increased subjective memory complaint precision, recall, and F1, with all corresponding 95% confidence intervals excluding zero. These findings support class-specific evaluation under severe class imbalance while distinguishing scan-level discrimination from participant-independent generalization.

Key findings

• Paired ablation analysis showed that weighted sampling did not improve aggregate metrics but increased subjective memory complaint precision, recall, and F1, with all corresponding 95% confidence intervals excluding zero.
• These findings support class-specific evaluation under severe class imbalance while distinguishing scan-level discrimination from participant-independent generalization.

Why it matters

This study tested a computer model that sorts MRI brain scans into six stages, from cognitively normal to Alzheimer's disease, and it reached about 90% accuracy. However, scans from the same person could appear in both the training and test data, so the results show how well the model tells scans apart, not how well it would work on new patients.

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

Study details

• Study designlongitudinal study
• Participants3,592
• Effect size3.79%; 43.7%
• Evidence strengthModerate

Read the original

• DOI: 10.1016/j.compbiomed.2026.111949
• PubMed: 42784895
• Original source →
• Free full text: Computers in Biology and Medicine →

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

@article{khan2026-42784895,
  author  = {Khan, Faizaan Fazal and Kim, Jun‐Hyung and Kwon, Goo‐Rak},
  title   = {{Multi-scale 3D CNN with imbalance-aware training for structural MRI-based six-class Alzheimer disease staging}},
  journal = {Computers in Biology and Medicine},
  year    = {2026},
  doi     = {10.1016/j.compbiomed.2026.111949},
  pmid    = {42784895},
  url     = {https://doi.org/10.1016/j.compbiomed.2026.111949}
}

Studies this one cites

Referenced by this study and also in the alzhub library, so you can read them here.

• Alzheimer's Disease Neuroimaging Initiative (ADNI): clinical characterization Neurology · 2009-12-30 · usefulness score 68/100 · Mild cognitive impairment

Related studies in Brain scans and imaging

• Progression-Aware and Explainable CNN–Transformer Framework for Multiclass Alzheimer’s Disease Staging Using MRI Diagnostics · 2026-02-16 · usefulness score 35/100
• Interpretable Frequency-Aware Deep Learning for Multi-Class EEG Classification of Neurological Disorders Preprints.org · 2026-10-12 · usefulness score 16/100
• High dimensional classification of structural MRI Alzheimer's disease data based on large scale regularization Frontiers in neuroinformatics · 2011-10-14 · usefulness score 47/100
• Hybrid of DSR-GAN and CNN for Alzheimer disease detection based on MRI images Scientific Reports · 2025-04-13 · usefulness score 44/100
• MVMGNN: Multi-View Masked Graph Neural Network for Alzheimer’s Disease Diagnosis using Structural MRI Research Square · 2026-10-23 · usefulness score 16/100
• A Deep Siamese Convolution Neural Network for Multi-Class Classification of Alzheimer Disease Brain sciences · 2020-02-05 · usefulness score 49/100

Similar studies

• Generalizable deep learning model for early Alzheimer's disease detection from structural MRIs 2022 · Long-term cohort studies
• Alzheimer's Disease Detection Through Whole-Brain 3D-CNN MRI 2020 · Digital health tools
• Stacked CNN-based multichannel attention networks for Alzheimer disease detection 2025 · Brain scans and imaging
• Structural MRI–based Computer-aided Diagnosis Models for Alzheimer Disease: Insights into Misclassifications and Diagnostic Limitations 2025 · Brain scans and imaging
• A Deep Learning Approach for Automated Diagnosis and Multi-Class Classification of Alzheimer's Disease Stages Using Resting-State fMRI and Residual Neural Networks 2019 · Long-term cohort studies
• Using machine learning to quantify structural MRI neurodegeneration patterns of Alzheimer's disease into dementia score: Independent validation on 8,834 images from ADNI, AIBL, OASIS, and MIRIAD databases 2020 · Digital health tools

More on Brain scans and imaging

• A review that covers this ground The Use of Tau PET to Stage Alzheimer Disease According to the Braak Staging Framework Journal of nuclear medicine : official publication, Society of Nuclear Medicine · 2023-06-15 · usefulness score 49/100
• 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 →