A multi-model deep convolutional neural network for automatic hippocampus segmentation and classification in Alzheimer's disease

Topic: Amyloid, tau and blood-test diagnosis

Alzheimer's disease (AD) is a progressive and irreversible brain degenerative disorder. Mild cognitive impairment (MCI) is a clinical precursor of AD. Although some treatments can delay its progression, no effective cures are available for AD. Accurate early-stage diagnosis of AD is vital for the prevention and intervention of the disease progression. Hippocampus is one of the first affected brain regions in AD. To help AD diagnosis, the shape and volume of the hippocampus are often measured using structural magnetic resonance imaging (MRI). However, these features encode limited information and may suffer from segmentation errors. Additionally, the extraction of these features is independent of the classification model, which could result in sub-optimal performance. In this study, we propose a multi-model deep learning framework based on convolutional neural network (CNN) for joint automatic hippocampal segmentation and AD classification using structural MRI data. Firstly, a multi-task deep CNN model is constructed for jointly learning hippocampal segmentation and disease classification. Then, we construct a 3D Densely Connected Convolutional Networks (3D DenseNet) to learn features of the 3D patches extracted based on the hippocampal segmentation results for the classification task. Finally, the learned features from the multi-task CNN and DenseNet models are combined to classify disease status. Our method is evaluated on the baseline T1-weighted structural MRI data collected from 97 AD, 233 MCI, 119 Normal Control (NC) subjects in the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. The proposed method achieves a dice similarity coefficient of 87.0% for hippocampal segmentation. In addition, the proposed method achieves an accuracy of 88.9% and an AUC (area under the ROC curve) of 92.5% for classifying AD vs. NC subjects, and an accuracy of 76.2% and an AUC of 77.5% for classifying MCI vs. NC subjects. Our empirical study also demonstrates that the proposed multi-model method outperforms the single-model methods and several other competing methods.

Key findings

• Additionally, the extraction of these features is independent of the classification model, which could result in sub-optimal performance.
• Then, we construct a 3D Densely Connected Convolutional Networks (3D DenseNet) to learn features of the 3D patches extracted based on the hippocampal segmentation results for the classification task.

Why it matters

A deep learning method was developed to automatically segment the hippocampus and classify Alzheimer's disease from MRI scans. This is a technical tool for diagnosis and does not provide a treatment or cure.

Study details

• Effect size87.0%; 88.9%; 92.5%
• Evidence strengthLow

Read the original

• DOI: 10.1016/j.neuroimage.2019.116459
• PubMed: 31837471
• Original source →
• Free full text: NeuroImage →

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

@article{liu2020-31837471,
  author  = {Liu, M. and Li, F. and Yan, H. and Wang, K. and Ma, Y. and {Alzheimer’s Disease Neuroimaging Initiative} and Shen, L. and Xu, M.},
  title   = {{A multi-model deep convolutional neural network for automatic hippocampus segmentation and classification in Alzheimer's disease}},
  journal = {NeuroImage},
  year    = {2020},
  doi     = {10.1016/j.neuroimage.2019.116459},
  pmid    = {31837471},
  url     = {https://doi.org/10.1016/j.neuroimage.2019.116459}
}

Studies this one cites

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

• The Alzheimer's disease neuroimaging initiative (ADNI): MRI methods Journal of Magnetic Resonance Imaging · 2008-02-26 · usefulness score 72/100 · Brain scans and imaging
• Introduction to the recommendations from the National Institute on Aging-Alzheimer's Association workgroups on diagnostic guidelines for Alzheimer's disease Alzheimer's & dementia : the journal of the Alzheimer's Association · 2011-04-21 · usefulness score 58/100 · Getting a diagnosis

Later studies that cite this one

3 studies in the alzhub library list this one in their references.

• Deep Learning-Based Classification and Voxel-Based Visualization of Frontotemporal Dementia and Alzheimer's Disease Frontiers in neuroscience · 2021-01-21 · usefulness score 55/100 · Long-term cohort studies
• Comparison of Deep Learning and Traditional Machine Learning Models for Predicting Mild Cognitive Impairment Using Plasma Proteomic Biomarkers International Journal of Molecular Sciences · 2025-03-08 · usefulness score 48/100 · Mild cognitive impairment
• Applications of artificial intelligence to aid early detection of dementia: A scoping review on current capabilities and future directions Journal of biomedical informatics · 2022-02-17 · usefulness score 47/100 · Digital health tools

Related studies in Mild cognitive impairment

• Detecting Mild Cognitive Impairment to Alzheimer’s Disease Progression by fMRI Using Convolutional Neural Network and Long-short Term Memory Basic and Clinical Neuroscience Journal · 2025-11-01 · usefulness score 34/100
• Predicting Mild Cognitive Impairment to Alzheimer's Disease Progression by Explainable Multi‐Modal Framework Using Deep and Machine Learning Hybrid Model International Journal of Imaging Systems and Technology · 2026-06-09 · usefulness score 35/100
• Development of a neural network-based risk prediction model for mild cognitive impairment in older adults with functional disability BMC Public Health · 2025-06-02 · usefulness score 46/100
• Predicting Alzheimer's disease progression using multi-modal deep learning approach Scientific reports · 2019-02-13 · usefulness score 66/100
• Neural network disruptions between default mode network and salience network in mild cognitive impairment with neuropsychiatric symptoms International Psychogeriatrics · 2025-05-01 · usefulness score 49/100
• A Novel Approach to the Prediction of Alzheimer’s Disease Progression by Leveraging Neural Processes and a Transformer Encoder Model IEEE Access · 2025-01-01 · usefulness score 46/100

Similar studies

• A Deep Siamese Convolution Neural Network for Multi-Class Classification of Alzheimer Disease 2020 · Brain scans and imaging
• Fully automatic hippocampus segmentation and classification in Alzheimer's disease and mild cognitive impairment applied on data from ADNI 2009 · Hippocampus size on brain scans
• Effective deep convolutional neural network with attention mechanism for Alzheimer disease classification 2026 · 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
• A deep learning model for early prediction of Alzheimer's disease dementia based on hippocampal magnetic resonance imaging data 2019 · Prevention and risk
• Advanced convolutional neural network with attention mechanism for Alzheimer's disease classification using MRI 2025 · Brain scans and imaging

More on Mild cognitive impairment

• A review that covers this ground A review on neuroimaging-based classification studies and associated feature extraction methods for Alzheimer's disease and its prodromal stages NeuroImage · 2017-04-13 · usefulness score 56/100
• Newest in this subject Paths of Aging Minds: Health Journeys of Older Adults with Mild Cognitive Impairment Research Square · 2026-11-01 · Preprint — not yet peer-reviewed · usefulness score 16/100
• Newest in this subject Neuroinflammation is an early pathological process in a mouse model of prodromal Parkinsons disease bioRxiv · 2026-10-30 · Preprint — not yet peer-reviewed · usefulness score 16/100

See all studies in Mild cognitive impairment →