Artificial intelligence in neuropathology: deep learning-based assessment of tauopathy

Maxim Signaevsky, Marcel Prastawa, Kurt Farrell, Nabil Tabish, Elena Baldwin, Natalia Han, Megan A. Iida, John Koll, Clare Bryce, Dushyant Purohit, Vahram Haroutunian, Ann C. McKee, Thor D. Stein, Charles L White, Jamie Walker, Timothy E. Richardson, Russell Hanson, Michael J. Donovan, Carlos Cordon-Cardo, Jack ZeinehGerardo Fernandez, John F. Crary

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Accumulation of abnormal tau in neurofibrillary tangles (NFT) occurs in Alzheimer disease (AD) and a spectrum of tauopathies. These tauopathies have diverse and overlapping morphological phenotypes that obscure classification and quantitative assessments. Recently, powerful machine learning-based approaches have emerged, allowing the recognition and quantification of pathological changes from digital images. Here, we applied deep learning to the neuropathological assessment of NFT in postmortem human brain tissue to develop a classifier capable of recognizing and quantifying tau burden. The histopathological material was derived from 22 autopsy brains from patients with tauopathies. We used a custom web-based informatics platform integrated with an in-house information management system to manage whole slide images (WSI) and human expert annotations as ground truth. We utilized fully annotated regions to train a deep learning fully convolutional neural network (FCN) implemented in PyTorch against the human expert annotations. We found that the deep learning framework is capable of identifying and quantifying NFT with a range of staining intensities and diverse morphologies. With our FCN model, we achieved high precision and recall in naive WSI semantic segmentation, correctly identifying tangle objects using a SegNet model trained for 200 epochs. Our FCN is efficient and well suited for the practical application of WSIs with average processing times of 45 min per WSI per GPU, enabling reliable and reproducible large-scale detection of tangles. We measured performance on test data of 50 pre-annotated regions on eight naive WSI across various tauopathies, resulting in the recall, precision, and an F1 score of 0.92, 0.72, and 0.81, respectively. Machine learning is a useful tool for complex pathological assessment of AD and other tauopathies. Using deep learning classifiers, we have the potential to integrate cell- and region-specific annotations with clinical, genetic, and molecular data, providing unbiased data for clinicopathological correlations that will enhance our knowledge of the neurodegeneration.

Original languageEnglish (US)
JournalLaboratory Investigation
DOIs
StatePublished - Jan 1 2019

Fingerprint

Tauopathies
Artificial Intelligence
Neurofibrillary Tangles
Learning
Alzheimer Disease
Management Information Systems
Informatics
Neural Networks (Computer)
Brain
Semantics
Molecular Biology
Autopsy
Neuropathology
Staining and Labeling
Phenotype

ASJC Scopus subject areas

  • Pathology and Forensic Medicine
  • Molecular Biology
  • Cell Biology

Cite this

Signaevsky, M., Prastawa, M., Farrell, K., Tabish, N., Baldwin, E., Han, N., ... Crary, J. F. (2019). Artificial intelligence in neuropathology: deep learning-based assessment of tauopathy. Laboratory Investigation. https://doi.org/10.1038/s41374-019-0202-4

Artificial intelligence in neuropathology : deep learning-based assessment of tauopathy. / Signaevsky, Maxim; Prastawa, Marcel; Farrell, Kurt; Tabish, Nabil; Baldwin, Elena; Han, Natalia; Iida, Megan A.; Koll, John; Bryce, Clare; Purohit, Dushyant; Haroutunian, Vahram; McKee, Ann C.; Stein, Thor D.; White, Charles L; Walker, Jamie; Richardson, Timothy E.; Hanson, Russell; Donovan, Michael J.; Cordon-Cardo, Carlos; Zeineh, Jack; Fernandez, Gerardo; Crary, John F.

In: Laboratory Investigation, 01.01.2019.

Research output: Contribution to journalArticle

Signaevsky, M, Prastawa, M, Farrell, K, Tabish, N, Baldwin, E, Han, N, Iida, MA, Koll, J, Bryce, C, Purohit, D, Haroutunian, V, McKee, AC, Stein, TD, White, CL, Walker, J, Richardson, TE, Hanson, R, Donovan, MJ, Cordon-Cardo, C, Zeineh, J, Fernandez, G & Crary, JF 2019, 'Artificial intelligence in neuropathology: deep learning-based assessment of tauopathy', Laboratory Investigation. https://doi.org/10.1038/s41374-019-0202-4
Signaevsky, Maxim ; Prastawa, Marcel ; Farrell, Kurt ; Tabish, Nabil ; Baldwin, Elena ; Han, Natalia ; Iida, Megan A. ; Koll, John ; Bryce, Clare ; Purohit, Dushyant ; Haroutunian, Vahram ; McKee, Ann C. ; Stein, Thor D. ; White, Charles L ; Walker, Jamie ; Richardson, Timothy E. ; Hanson, Russell ; Donovan, Michael J. ; Cordon-Cardo, Carlos ; Zeineh, Jack ; Fernandez, Gerardo ; Crary, John F. / Artificial intelligence in neuropathology : deep learning-based assessment of tauopathy. In: Laboratory Investigation. 2019.
@article{bffaac4083ec4ce0b4c7677ac4c4089d,
title = "Artificial intelligence in neuropathology: deep learning-based assessment of tauopathy",
abstract = "Accumulation of abnormal tau in neurofibrillary tangles (NFT) occurs in Alzheimer disease (AD) and a spectrum of tauopathies. These tauopathies have diverse and overlapping morphological phenotypes that obscure classification and quantitative assessments. Recently, powerful machine learning-based approaches have emerged, allowing the recognition and quantification of pathological changes from digital images. Here, we applied deep learning to the neuropathological assessment of NFT in postmortem human brain tissue to develop a classifier capable of recognizing and quantifying tau burden. The histopathological material was derived from 22 autopsy brains from patients with tauopathies. We used a custom web-based informatics platform integrated with an in-house information management system to manage whole slide images (WSI) and human expert annotations as ground truth. We utilized fully annotated regions to train a deep learning fully convolutional neural network (FCN) implemented in PyTorch against the human expert annotations. We found that the deep learning framework is capable of identifying and quantifying NFT with a range of staining intensities and diverse morphologies. With our FCN model, we achieved high precision and recall in naive WSI semantic segmentation, correctly identifying tangle objects using a SegNet model trained for 200 epochs. Our FCN is efficient and well suited for the practical application of WSIs with average processing times of 45 min per WSI per GPU, enabling reliable and reproducible large-scale detection of tangles. We measured performance on test data of 50 pre-annotated regions on eight naive WSI across various tauopathies, resulting in the recall, precision, and an F1 score of 0.92, 0.72, and 0.81, respectively. Machine learning is a useful tool for complex pathological assessment of AD and other tauopathies. Using deep learning classifiers, we have the potential to integrate cell- and region-specific annotations with clinical, genetic, and molecular data, providing unbiased data for clinicopathological correlations that will enhance our knowledge of the neurodegeneration.",
author = "Maxim Signaevsky and Marcel Prastawa and Kurt Farrell and Nabil Tabish and Elena Baldwin and Natalia Han and Iida, {Megan A.} and John Koll and Clare Bryce and Dushyant Purohit and Vahram Haroutunian and McKee, {Ann C.} and Stein, {Thor D.} and White, {Charles L} and Jamie Walker and Richardson, {Timothy E.} and Russell Hanson and Donovan, {Michael J.} and Carlos Cordon-Cardo and Jack Zeineh and Gerardo Fernandez and Crary, {John F.}",
year = "2019",
month = "1",
day = "1",
doi = "10.1038/s41374-019-0202-4",
language = "English (US)",
journal = "Laboratory Investigation",
issn = "0023-6837",
publisher = "Nature Publishing Group",

}

TY - JOUR

T1 - Artificial intelligence in neuropathology

T2 - deep learning-based assessment of tauopathy

AU - Signaevsky, Maxim

AU - Prastawa, Marcel

AU - Farrell, Kurt

AU - Tabish, Nabil

AU - Baldwin, Elena

AU - Han, Natalia

AU - Iida, Megan A.

AU - Koll, John

AU - Bryce, Clare

AU - Purohit, Dushyant

AU - Haroutunian, Vahram

AU - McKee, Ann C.

AU - Stein, Thor D.

AU - White, Charles L

AU - Walker, Jamie

AU - Richardson, Timothy E.

AU - Hanson, Russell

AU - Donovan, Michael J.

AU - Cordon-Cardo, Carlos

AU - Zeineh, Jack

AU - Fernandez, Gerardo

AU - Crary, John F.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Accumulation of abnormal tau in neurofibrillary tangles (NFT) occurs in Alzheimer disease (AD) and a spectrum of tauopathies. These tauopathies have diverse and overlapping morphological phenotypes that obscure classification and quantitative assessments. Recently, powerful machine learning-based approaches have emerged, allowing the recognition and quantification of pathological changes from digital images. Here, we applied deep learning to the neuropathological assessment of NFT in postmortem human brain tissue to develop a classifier capable of recognizing and quantifying tau burden. The histopathological material was derived from 22 autopsy brains from patients with tauopathies. We used a custom web-based informatics platform integrated with an in-house information management system to manage whole slide images (WSI) and human expert annotations as ground truth. We utilized fully annotated regions to train a deep learning fully convolutional neural network (FCN) implemented in PyTorch against the human expert annotations. We found that the deep learning framework is capable of identifying and quantifying NFT with a range of staining intensities and diverse morphologies. With our FCN model, we achieved high precision and recall in naive WSI semantic segmentation, correctly identifying tangle objects using a SegNet model trained for 200 epochs. Our FCN is efficient and well suited for the practical application of WSIs with average processing times of 45 min per WSI per GPU, enabling reliable and reproducible large-scale detection of tangles. We measured performance on test data of 50 pre-annotated regions on eight naive WSI across various tauopathies, resulting in the recall, precision, and an F1 score of 0.92, 0.72, and 0.81, respectively. Machine learning is a useful tool for complex pathological assessment of AD and other tauopathies. Using deep learning classifiers, we have the potential to integrate cell- and region-specific annotations with clinical, genetic, and molecular data, providing unbiased data for clinicopathological correlations that will enhance our knowledge of the neurodegeneration.

AB - Accumulation of abnormal tau in neurofibrillary tangles (NFT) occurs in Alzheimer disease (AD) and a spectrum of tauopathies. These tauopathies have diverse and overlapping morphological phenotypes that obscure classification and quantitative assessments. Recently, powerful machine learning-based approaches have emerged, allowing the recognition and quantification of pathological changes from digital images. Here, we applied deep learning to the neuropathological assessment of NFT in postmortem human brain tissue to develop a classifier capable of recognizing and quantifying tau burden. The histopathological material was derived from 22 autopsy brains from patients with tauopathies. We used a custom web-based informatics platform integrated with an in-house information management system to manage whole slide images (WSI) and human expert annotations as ground truth. We utilized fully annotated regions to train a deep learning fully convolutional neural network (FCN) implemented in PyTorch against the human expert annotations. We found that the deep learning framework is capable of identifying and quantifying NFT with a range of staining intensities and diverse morphologies. With our FCN model, we achieved high precision and recall in naive WSI semantic segmentation, correctly identifying tangle objects using a SegNet model trained for 200 epochs. Our FCN is efficient and well suited for the practical application of WSIs with average processing times of 45 min per WSI per GPU, enabling reliable and reproducible large-scale detection of tangles. We measured performance on test data of 50 pre-annotated regions on eight naive WSI across various tauopathies, resulting in the recall, precision, and an F1 score of 0.92, 0.72, and 0.81, respectively. Machine learning is a useful tool for complex pathological assessment of AD and other tauopathies. Using deep learning classifiers, we have the potential to integrate cell- and region-specific annotations with clinical, genetic, and molecular data, providing unbiased data for clinicopathological correlations that will enhance our knowledge of the neurodegeneration.

UR - http://www.scopus.com/inward/record.url?scp=85061718942&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061718942&partnerID=8YFLogxK

U2 - 10.1038/s41374-019-0202-4

DO - 10.1038/s41374-019-0202-4

M3 - Article

C2 - 30770886

AN - SCOPUS:85061718942

JO - Laboratory Investigation

JF - Laboratory Investigation

SN - 0023-6837

ER -