Interpretable classification of Alzheimer's disease pathologies with a convolutional neural network pipeline

Topic: Plasma and spinal-fluid biomarkers

Neuropathologists assess vast brain areas to identify diverse and subtly-differentiated morphologies. Standard semi-quantitative scoring approaches, however, are coarse-grained and lack precise neuroanatomic localization. We report a proof-of-concept deep learning pipeline that identifies specific neuropathologies-amyloid plaques and cerebral amyloid angiopathy-in immunohistochemically-stained archival slides. Using automated segmentation of stained objects and a cloud-based interface, we annotate > 70,000 plaque candidates from 43 whole slide images (WSIs) to train and evaluate convolutional neural networks. Networks achieve strong plaque classification on a 10-WSI hold-out set (0.993 and 0.743 areas under the receiver operating characteristic and precision recall curve, respectively). Prediction confidence maps visualize morphology distributions at high resolution. Resulting network-derived amyloid beta (Aβ)-burden scores correlate well with established semi-quantitative scores on a 30-WSI blinded hold-out. Finally, saliency mapping demonstrates that networks learn patterns agreeing with accepted pathologic features. This scalable means to augment a neuropathologist's ability suggests a route to neuropathologic deep phenotyping.

Key findings

• Networks achieve strong plaque classification on a 10-WSI hold-out set (0.993 and 0.743 areas under the receiver operating characteristic and precision recall curve, respectively).
• Prediction confidence maps visualize morphology distributions at high resolution.
• Resulting network-derived amyloid beta (Aβ)-burden scores correlate well with established semi-quantitative scores on a 30-WSI blinded hold-out.
• Finally, saliency mapping demonstrates that networks learn patterns agreeing with accepted pathologic features.
• This scalable means to augment a neuropathologist's ability suggests a route to neuropathologic deep phenotyping.

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

Study details

• Evidence strengthLow

Read the original

• DOI: 10.1038/s41467-019-10212-1
• PubMed: 31092819
• Original source →

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

@article{tang2019-31092819,
  author  = {Tang, Z. and Chuang, K. V. and DeCarli, C. and Jin, L. W. and Beckett, L. and Keiser, M. J. and Dugger, B. N.},
  title   = {{Interpretable classification of Alzheimer's disease pathologies with a convolutional neural network pipeline}},
  journal = {Nature communications},
  year    = {2019},
  doi     = {10.1038/s41467-019-10212-1},
  pmid    = {31092819},
  url     = {https://doi.org/10.1038/s41467-019-10212-1}
}

Related studies in Digital health tools

• Classification of Alzheimer's Disease Based on Eight-Layer Convolutional Neural Network with Leaky Rectified Linear Unit and Max Pooling Journal of medical systems · 2018-03-26 · usefulness score 41/100
• Diagnosis of Alzheimer's Disease via Multi-Modality 3D Convolutional Neural Network Frontiers in neuroscience · 2019-05-31 · usefulness score 53/100
• Convolutional neural networks for classification of Alzheimer's disease: Overview and reproducible evaluation Medical image analysis · 2020-05-01 · usefulness score 59/100
• Classification of Alzheimer's Disease by Combination of Convolutional and Recurrent Neural Networks Using FDG-PET Images Frontiers in neuroinformatics · 2018-06-19 · usefulness score 53/100
• Layer-Wise Relevance Propagation for Explaining Deep Neural Network Decisions in MRI-Based Alzheimer's Disease Classification Frontiers in aging neuroscience · 2019-07-31 · usefulness score 41/100
• Multi-Modality Cascaded Convolutional Neural Networks for Alzheimer's Disease Diagnosis Neuroinformatics · 2018-10-01 · usefulness score 50/100

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.

• Analysis of entropies based on empirical mode decomposition in amnesic mild cognitive impairment of diabetes mellitus Journal of Innovative Optical Health Sciences · 2015-08-21 · usefulness score 39/100 · Risk factors
• Artificial intelligence framework identifies candidate targets for drug repurposing in Alzheimer's disease Alzheimer's research & therapy · 2022-01-10 · usefulness score 63/100 · Genetics
• Predictive Models for Cognitive Decline Assessment F1000Res · 2026-07-22 · usefulness score 48/100 · Long-term cohort studies

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
• Deep learning detection of informative features in tau PET for Alzheimer’s disease classification 2020 · Brain scans and imaging
• Multimodal deep learning for Alzheimer's disease dementia assessment 2022 · Digital health tools
• Deep learning to detect Alzheimer's disease from neuroimaging: A systematic literature review 2020 · Digital health tools
• Early detection of dementia through retinal imaging and trustworthy AI 2024 · Brain scans and imaging
• Neuron-level explainable AI for Alzheimer's Disease assessment from fundus images 2024 · Brain scans and imaging

More on Digital health tools

• A review that covers this ground GABAergic dysfunction, neural network hyperactivity and memory impairments in human aging and Alzheimer's disease Seminars in cell & developmental biology · 2021-02-09 · usefulness score 43/100
• 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 →