Multiple instance learning for classification of dementia in brain MRI

Topic: Risk, prevention and care in population studies

Machine learning techniques have been widely used to detect morphological abnormalities from structural brain magnetic resonance imaging data and to support the diagnosis of neurological diseases such as dementia. In this paper, we propose to use a multiple instance learning (MIL) method in an application for the detection of Alzheimer's disease (AD) and its prodromal stage mild cognitive impairment (MCI). In our work, local intensity patches are extracted as features. However, not all the patches extracted from patients with dementia are equally affected by the disease and some of them may not be characteristic of morphology associated with the disease. Therefore, there is some ambiguity in assigning disease labels to these patches. The problem of the ambiguous training labels can be addressed by weakly supervised learning techniques such as MIL. A graph is built for each image to exploit the relationships among the patches and then to solve the MIL problem. The constructed graphs contain information about the appearances of patches and the relationships among them, which can reflect the inherent structures of images and aids the classification. Using the baseline MR images of 834 subjects from the ADNI study, the proposed method can achieve a classification accuracy of 89% between AD patients and healthy controls, and 70% between patients defined as stable MCI and progressive MCI in a leave-one-out cross validation. Compared with two state-of-the-art methods using the same dataset, the proposed method can achieve similar or improved results, providing an alternative framework for the detection and prediction of neurodegenerative diseases.

Key findings

• However, not all the patches extracted from patients with dementia are equally affected by the disease and some of them may not be characteristic of morphology associated with the disease.
• Compared with two state-of-the-art methods using the same dataset, the proposed method can achieve similar or improved results, providing an alternative framework for the detection and prediction of neurodegenerative diseases.

Why it matters

Using baseline MRI scans of 834 people from the ADNI research study, this machine-learning method told Alzheimer's patients apart from healthy controls with 89% accuracy. It was less accurate (70%) at telling which people with mild cognitive impairment would stay stable and which would progress. Both figures come from leave-one-out cross-validation within that one dataset rather than a new group of patients, and the method was reported as similar to or better than two earlier methods. It is a diagnostic-research study and does not test any treatment, cure or prevention.

New to this subject? Start with our plain-English guide: Digital health →

Study details

• Participants834
• Evidence strengthLow

Read the original

• DOI: 10.1016/j.media.2014.04.006
• PubMed: 24858570
• Original source →

May need a subscription OpenAlex found no free copy of the full text (checked 6 Feb 1020), so the publisher may charge for it. The PubMed abstract is free.

@article{tong2014-24858570,
  author  = {Tong, T. and Wolz, R. and Gao, Q. and Guerrero, R. and Hajnal, J. V. and Rueckert, D. and {Alzheimer’s Disease Neuroimaging Initiative}},
  title   = {{Multiple instance learning for classification of dementia in brain MRI}},
  journal = {Medical image analysis},
  year    = {2014},
  doi     = {10.1016/j.media.2014.04.006},
  pmid    = {24858570},
  url     = {https://doi.org/10.1016/j.media.2014.04.006}
}

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
• Tracking pathophysiological processes in Alzheimer's disease: an updated hypothetical model of dynamic biomarkers The Lancet Neurology · 2013-01-16 · usefulness score 64/100 · Biomarkers
• Measurement of hippocampal atrophy using 4D graph-cut segmentation: application to ADNI NeuroImage · 2010-04-09 · usefulness score 60/100 · Long-term cohort studies
• Discrimination between Alzheimer dementia and controls by automated analysis of multicenter FDG PET NeuroImage · 2002-09-01 · usefulness score 59/100 · Getting a diagnosis
• Forecasting the global burden of Alzheimer's disease Alzheimer s & Dementia · 2007-06-04 · usefulness score 59/100 · How common it is
• Mild cognitive impairment can be distinguished from Alzheimer disease and normal aging for clinical trials Archives of neurology · 2004-01-01 · usefulness score 56/100 · Getting a diagnosis
• Predictive markers for AD in a multi-modality framework: an analysis of MCI progression in the ADNI population NeuroImage · 2010-12-10 · usefulness score 51/100 · Mild cognitive impairment
• Prediction of Alzheimer's disease in subjects with mild cognitive impairment from the ADNI cohort using patterns of cortical thinning NeuroImage · 2012-10-02 · usefulness score 51/100 · Mild cognitive impairment
• Biomarkers for early detection of Alzheimer pathology Neuro-Signals · 2007-12-05 · usefulness score 41/100 · Brain scans and imaging

Later studies that cite this one

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

• Machine learning methods for predicting progression from mild cognitive impairment to Alzheimer's disease dementia: a systematic review Alzheimer's research & therapy · 2021-09-28 · usefulness score 65/100 · Digital health tools
• Recent publications from the Alzheimer's Disease Neuroimaging Initiative: Reviewing progress toward improved AD clinical trials Alzheimer's & dementia : the journal of the Alzheimer's Association · 2017-03-22 · usefulness score 65/100 · Mild cognitive impairment
• Generalizable deep learning model for early Alzheimer's disease detection from structural MRIs Scientific reports · 2022-10-17 · usefulness score 54/100 · Long-term cohort studies
• An MRI-based strategy for differentiation of frontotemporal dementia and Alzheimer's disease Alzheimer's research & therapy · 2021-01-12 · usefulness score 49/100 · Long-term cohort studies
• Multi-modal latent space inducing ensemble SVM classifier for early dementia diagnosis with neuroimaging data Medical image analysis · 2019-12-28 · usefulness score 47/100 · Long-term cohort studies
• Neuroimaging and Machine Learning for Dementia Diagnosis: Recent Advancements and Future Prospects IEEE reviews in biomedical engineering · 2018-12-11 · usefulness score 44/100 · Digital health tools
• Attention-Guided Hybrid Network for Dementia Diagnosis With Structural MR Images IEEE transactions on cybernetics · 2022-04-05 · usefulness score 38/100 · Long-term cohort studies

Related studies in Digital health tools

• Biomarker Investigation Using Multiple Brain Measures from MRI Through Explainable Artificial Intelligence in Alzheimer’s Disease Classification Bioengineering · 2025-01-17 · usefulness score 43/100
• Multiple Brain Tumor Classification with Dense CNN Architecture Using Brain MRI Images Life (Basel, Switzerland) · 2023-01-28 · usefulness score 43/100
• Brain MRI Analysis for Alzheimer's Disease Diagnosis Using CNN-Based Feature Extraction and Machine Learning Sensors (Basel, Switzerland) · 2022-04-11 · usefulness score 51/100
• Rey's Auditory Verbal Learning Test scores can be predicted from whole brain MRI in Alzheimer's disease NeuroImage. Clinical · 2016-12-18 · usefulness score 45/100
• Comparison of Feature Selection Techniques in Machine Learning for Anatomical Brain MRI in Dementia Neuroinformatics · 2016-07-01 · usefulness score 38/100
• Classification of CT brain images based on deep learning networks Computer methods and programs in biomedicine · 2016-10-20 · usefulness score 50/100

Similar studies

• Novel MRI techniques in the assessment of dementia 2008 · Digital health tools
• Investigating dementia patterns by machine learning and graph-based marker analysis for multiclass dementia diagnosis 2026 · Getting a diagnosis
• Application of machine learning in EEG-based dementia diagnosis: Classification and differential diagnosis 2025 · Digital health tools
• A novel multi-modal machine learning based approach for automatic classification of EEG recordings in dementia 2020 · Digital health tools
• Multi-model deep learning for dementia detection: addressing data and model limitations 2025 · Getting a diagnosis
• Using Machine Learning to Predict Dementia from Neuropsychiatric Symptom and Neuroimaging Data 2020 · Digital health tools

More on Digital health tools

• A review that covers this ground A Review on a Deep Learning Perspective in Brain Cancer Classification Cancers · 2019-01-18 · usefulness score 41/100
• Newest in this subject Speaker-Wise Dementia Screening fromNaturalistic Speech with Lexical Entropy, Semantic Drift, and Multimodal Fusion Research Square · 2026-10-21 · Preprint — not yet peer-reviewed · usefulness score 16/100
• Newest in this subject Integrating Multisource Target Evidence with Machine-Learning Potency Prediction for Alzheimer’s Disease Drug Discovery bioRxiv · 2026-10-20 · Preprint — not yet peer-reviewed · usefulness score 16/100

See all studies in Digital health tools →