Deep learning detection of informative features in tau PET for Alzheimer’s disease classification

Topic: Plasma and spinal-fluid biomarkers

Background Alzheimer’s disease (AD) is the most common type of dementia, typically characterized by memory loss followed by progressive cognitive decline and functional impairment. Many clinical trials of potential therapies for AD have failed, and there is currently no approved disease-modifying treatment. Biomarkers for early detection and mechanistic understanding of disease course are critical for drug development and clinical trials. Amyloid has been the focus of most biomarker research. Here, we developed a deep learning-based framework to identify informative features for AD classification using tau positron emission tomography (PET) scans. Methods We analysed [ 18 F]flortaucipir PET image data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) cohort. We first developed an image classifier to distinguish AD from cognitively normal (CN) older adults by training a 3D convolutional neural network (CNN)-based deep learning model on tau PET images (N=132; 66 CN and 66 AD), then applied the classifier to images from individuals with mild cognitive impairment (MCI; N=168). In addition, we applied a layer-wise relevance propagation (LRP)-based model to identify informative features and to visualize classification results. We compared these results with those from whole brain voxel-wise between-group analysis using conventional Statistical Parametric Mapping (SPM12). Results The 3D CNN-based classification model of AD from CN yielded an average accuracy of 90.8% based on five-fold cross-validation. The LRP model identified the brain regions in tau PET images that contributed most to the AD classification from CN. The top identified regions included the hippocampus, parahippocampus, thalamus, and fusiform. The LRP results were consistent with those from the voxel-wise analysis in SPM12, showing significant focal AD associated regional tau deposition in the bilateral temporal lobes including the entorhinal cortex. The AD probability scores calculated by the classifier were correlated with brain tau deposition in the medial temporal lobe in MCI participants (r=0.43 for early MCI and r=0.49 for late MCI). Conclusion A deep learning framework combining 3D CNN and LRP algorithms can be used with tau PET images to identify informative features for AD classification and may have application for early detection during prodromal stages of AD.

@article{jo2020-33371874,
  author  = {Jo, Taeho and Nho, Kwangsik T. and Risacher, Shannon L. and Saykin, Andrew J. and {Alzheimer’s Disease Neuroimaging Initiative}},
  title   = {{Deep learning detection of informative features in tau PET for Alzheimer’s disease classification}},
  journal = {BMC Bioinformatics},
  year    = {2020},
  doi     = {10.1186/s12859-020-03848-0},
  pmid    = {33371874},
  url     = {https://doi.org/10.1186/s12859-020-03848-0}
}

Key findings

• In addition, we applied a layer-wise relevance propagation (LRP)-based model to identify informative features and to visualize classification results.
• We compared these results with those from whole brain voxel-wise between-group analysis using conventional Statistical Parametric Mapping (SPM12).
• Results The 3D CNN-based classification model of AD from CN yielded an average accuracy of 90.8% based on five-fold cross-validation.
• The LRP results were consistent with those from the voxel-wise analysis in SPM12, showing significant focal AD associated regional tau deposition in the bilateral temporal lobes including the entorhinal cortex.

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

Study details

• Participants132
• Effect size90.8%
• Evidence strengthModerate

Read the original

• DOI: 10.1186/s12859-020-03848-0
• PubMed: 33371874
• Original source →

Free copy unknown: no free-copy check has an answer for this record yet. That does not mean it is paywalled.

Related studies in Brain scans and imaging

• Longitudinal Structural MRI-Based Deep Learning And Radiomics Features For Predicting Alzheimer\\\\\\\'s Disease Progression Zenodo (CERN European Organization for Nuclear Research) · 2026-01-01 · usefulness score 55/100
• Small-Data Deep Learning for Alzheimer-Spectrum Classification from Structural MRI: A Feasibility Study Using OASIS Journal of Imaging · 2026-08-03 · usefulness score 42/100
• Enhanced Deep Learning Framework for Precise MRI ‐Based Alzheimer's Disease Stage Classification Computational Intelligence · 2025-08-01 · usefulness score 31/100
• ENHANCED ALZHEIMER DISEASE DIAGNOSIS THROUGH DEEP LEARNING-BASED MRI SEGMENTATION AND CLASSIFICATION RCHUB JOURNAL OF COMPUTATIONAL INTELLIGENCE SCIENCE AND ENGINEERING (JCISE) · 2026-07-01 · usefulness score 26/100
• Interpretable Frequency-Aware Deep Learning for Multi-Class EEG Classification of Neurological Disorders Preprints.org · 2026-10-12 · usefulness score 16/100
• Deep Learning Framework for Characterizing Tau‐PET Spatial Heterogeneity along AD Spectrum: A Self‐supervised Approach Alzheimer s & Dementia · 2025-12-01 · usefulness score 37/100

Also tagged “convolutional”

205 studies in the library carry the topic tag “convolutional”; these are this study's neighbours in a fixed, alphabetical-by-hash tour of them, not the closest in content. All 205 tagged studies.

• Automated quantification of cerebral microbleeds for ARIA-H monitoring in Aging and Alzheimer’s Disease: A multicenter deep learning validation medRxiv · 2026-05-26 · usefulness score 16/100 · Treatments
• Assessment of the predictive potential of cognitive scores from retinal images and retinal fundus metadata via deep learning using the CLSA database Scientific reports · 2022-04-06 · usefulness score 61/100 · Brain scans and imaging
• Current gaps in downstream applications of fMRI foundation models: lessons learned from BrainLM & BrainHarmonix on Prevent-AD medRxiv · 2026-10-26 · usefulness score 16/100 · Brain scans and imaging

Similar studies

• A Deep Learning Model to Predict a Diagnosis of Alzheimer Disease by Using 18 F-FDG PET of the Brain 2019 · Digital health tools
• Predicting cognitive decline with deep learning of brain metabolism and amyloid imaging 2018 · Digital health tools
• Automated classification of Alzheimer's disease and mild cognitive impairment using a single MRI and deep neural networks 2019 · Digital health tools
• Classification of Alzheimer's Disease by Combination of Convolutional and Recurrent Neural Networks Using FDG-PET Images 2018 · Digital health tools
• Multimodal deep learning models for early detection of Alzheimer's disease stage 2021 · Digital health tools
• DEMNET: A Deep Learning Model for Early Diagnosis of Alzheimer Diseases and Dementia From MR Images 2021 · Long-term cohort studies

More on Brain scans and imaging

• A review that covers this ground Deep Reinforcement Learning-Based Retinal Imaging in Alzheimer's Disease: Potential and Perspectives Journal of Alzheimer's disease : JAD · 2023 · usefulness score 41/100
• 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 →