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

BioRxiv : the Preprint Server for Biology
Ziqi TangBrittany N. Dugger

Abstract

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 identifying 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 annotated >70,000 plaque candidates from 43 whole slide images (WSIs) to train and evaluate convolutional neural networks. Networks achieved 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 visualized morphology distributions for WSIs at high resolution. Resulting plaque-burden scores correlated well with established semi-quantitative scores on a 30-WSI blinded hold-out. Finally, saliency mapping demonstrated that networks learned patterns agreeing with accepted pathologic features. This scalable means to augment a neuropathologist’s ability may suggest a route to neuropathologic deep phenotyping. * Aβ ...Continue Reading

Related Concepts

Alzheimer's Disease
Classification
Immunohistochemistry
Learning
1-(4-methoxyphenyl)pyridinium
Cyclophosphamide/Doxorubicin/Methotrexate Protocol
Cerebral Amyloid Angiopathy
Blinded
Neural Networks (Anatomic)
Neuropathologist

Related Feeds

Alzheimer's Disease: Microglia (Preprints)

Microglial proliferation and activation, as well as its concentration around amyloid plaques, is a prominent feature of Alzheimer’s disease. Here is the latest research on microglia and Alzheimer’s disease.

Researcher Network:CZI Neurodegeneration Challenge

The Neurodegeneration Challenge Network aims to provide funding for and to bring together researchers studying neurodegenerative diseases. Find the latest research from the NDCN grantees here.

BioRxiv & MedRxiv Preprints

BioRxiv and MedRxiv are the preprint servers for biology and health sciences respectively, operated by Cold Spring Harbor Laboratory. Here are the latest preprint articles (which are not peer-reviewed) from BioRxiv and MedRxiv.

Related Papers

Investigative Ophthalmology & Visual Science
Carson LamDaniel Rubin
Laboratory Investigation; a Journal of Technical Methods and Pathology
Maxim SignaevskyJohn F Crary
Nihon rinsho. Japanese journal of clinical medicine
H Yamanouchi
© 2021 Meta ULC. All rights reserved