A deep learning model to predict a diagnosis of Alzheimer disease by using 18 F-FDG PET of the brain

Yiming Ding, Jae Ho Sohn, Michael G. Kawczynski, Hari Trivedi, Roy Harnish, Nathaniel W. Jenkins, Dmytro Lituiev, Timothy P. Copeland, Mariam S. Aboian, Carina Mari Aparici, Spencer C. Behr, Robert R. Flavell, Shih Ying Huang, Kelly A. Zalocusky, Lorenzo Nardo, Youngho Seo, Randall A. Hawkins, Miguel Hernandez Pampaloni, Dexter Hadley, Benjamin L. Franc

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Purpose: To develop and validate a deep learning algorithm that predicts the final diagnosis of Alzheimer disease (AD), mild cognitive impairment, or neither at fluorine 18 ( 18 F) fluorodeoxyglucose (FDG) PET of the brain and compare its performance to that of radiologic readers. Materials and Methods: Prospective 18 F-FDG PET brain images from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) (2109 imaging studies from 2005 to 2017, 1002 patients) and retrospective independent test set (40 imaging studies from 2006 to 2016, 40 patients) were collected. Final clinical diagnosis at follow-up was recorded. Convolutional neural network of InceptionV3 architecture was trained on 90% of ADNI data set and tested on the remaining 10%, as well as the independent test set, with performance compared to radiologic readers. Model was analyzed with sensitivity, specificity, receiver operating characteristic (ROC), saliency map, and t-distributed stochastic neighbor embedding. Results: The algorithm achieved area under the ROC curve of 0.98 (95% confidence interval: 0.94, 1.00) when evaluated on predicting the final clinical diagnosis of AD in the independent test set (82% specificity at 100% sensitivity), an average of 75.8 months prior to the final diagnosis, which in ROC space outperformed reader performance (57% [four of seven] sensitivity, 91% [30 of 33] specificity; P , .05). Saliency map demonstrated attention to known areas of interest but with focus on the entire brain. Conclusion: By using fluorine 18 fluorodeoxyglucose PET of the brain, a deep learning algorithm developed for early prediction of Alzheimer disease achieved 82% specificity at 100% sensitivity, an average of 75.8 months prior to the final diagnosis.

Original languageEnglish (US)
Pages (from-to)456-464
Number of pages9
JournalRADIOLOGY
Volume290
Issue number3
DOIs
StatePublished - Mar 1 2019

Fingerprint

Fluorodeoxyglucose F18
Alzheimer Disease
Learning
ROC Curve
Brain
Neuroimaging
Fluorine
Confidence Intervals
Sensitivity and Specificity

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Cite this

Ding, Y., Sohn, J. H., Kawczynski, M. G., Trivedi, H., Harnish, R., Jenkins, N. W., ... Franc, B. L. (2019). A deep learning model to predict a diagnosis of Alzheimer disease by using 18 F-FDG PET of the brain RADIOLOGY, 290(3), 456-464. https://doi.org/10.1148/radiol.2018180958

A deep learning model to predict a diagnosis of Alzheimer disease by using 18 F-FDG PET of the brain . / Ding, Yiming; Sohn, Jae Ho; Kawczynski, Michael G.; Trivedi, Hari; Harnish, Roy; Jenkins, Nathaniel W.; Lituiev, Dmytro; Copeland, Timothy P.; Aboian, Mariam S.; Aparici, Carina Mari; Behr, Spencer C.; Flavell, Robert R.; Huang, Shih Ying; Zalocusky, Kelly A.; Nardo, Lorenzo; Seo, Youngho; Hawkins, Randall A.; Pampaloni, Miguel Hernandez; Hadley, Dexter; Franc, Benjamin L.

In: RADIOLOGY, Vol. 290, No. 3, 01.03.2019, p. 456-464.

Research output: Contribution to journalArticle

Ding, Y, Sohn, JH, Kawczynski, MG, Trivedi, H, Harnish, R, Jenkins, NW, Lituiev, D, Copeland, TP, Aboian, MS, Aparici, CM, Behr, SC, Flavell, RR, Huang, SY, Zalocusky, KA, Nardo, L, Seo, Y, Hawkins, RA, Pampaloni, MH, Hadley, D & Franc, BL 2019, ' A deep learning model to predict a diagnosis of Alzheimer disease by using 18 F-FDG PET of the brain ', RADIOLOGY, vol. 290, no. 3, pp. 456-464. https://doi.org/10.1148/radiol.2018180958
Ding, Yiming ; Sohn, Jae Ho ; Kawczynski, Michael G. ; Trivedi, Hari ; Harnish, Roy ; Jenkins, Nathaniel W. ; Lituiev, Dmytro ; Copeland, Timothy P. ; Aboian, Mariam S. ; Aparici, Carina Mari ; Behr, Spencer C. ; Flavell, Robert R. ; Huang, Shih Ying ; Zalocusky, Kelly A. ; Nardo, Lorenzo ; Seo, Youngho ; Hawkins, Randall A. ; Pampaloni, Miguel Hernandez ; Hadley, Dexter ; Franc, Benjamin L. / A deep learning model to predict a diagnosis of Alzheimer disease by using 18 F-FDG PET of the brain In: RADIOLOGY. 2019 ; Vol. 290, No. 3. pp. 456-464.
@article{7a9ed55211274af2bf9033b5d8825afa,
title = "A deep learning model to predict a diagnosis of Alzheimer disease by using 18 F-FDG PET of the brain",
abstract = "Purpose: To develop and validate a deep learning algorithm that predicts the final diagnosis of Alzheimer disease (AD), mild cognitive impairment, or neither at fluorine 18 ( 18 F) fluorodeoxyglucose (FDG) PET of the brain and compare its performance to that of radiologic readers. Materials and Methods: Prospective 18 F-FDG PET brain images from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) (2109 imaging studies from 2005 to 2017, 1002 patients) and retrospective independent test set (40 imaging studies from 2006 to 2016, 40 patients) were collected. Final clinical diagnosis at follow-up was recorded. Convolutional neural network of InceptionV3 architecture was trained on 90{\%} of ADNI data set and tested on the remaining 10{\%}, as well as the independent test set, with performance compared to radiologic readers. Model was analyzed with sensitivity, specificity, receiver operating characteristic (ROC), saliency map, and t-distributed stochastic neighbor embedding. Results: The algorithm achieved area under the ROC curve of 0.98 (95{\%} confidence interval: 0.94, 1.00) when evaluated on predicting the final clinical diagnosis of AD in the independent test set (82{\%} specificity at 100{\%} sensitivity), an average of 75.8 months prior to the final diagnosis, which in ROC space outperformed reader performance (57{\%} [four of seven] sensitivity, 91{\%} [30 of 33] specificity; P , .05). Saliency map demonstrated attention to known areas of interest but with focus on the entire brain. Conclusion: By using fluorine 18 fluorodeoxyglucose PET of the brain, a deep learning algorithm developed for early prediction of Alzheimer disease achieved 82{\%} specificity at 100{\%} sensitivity, an average of 75.8 months prior to the final diagnosis.",
author = "Yiming Ding and Sohn, {Jae Ho} and Kawczynski, {Michael G.} and Hari Trivedi and Roy Harnish and Jenkins, {Nathaniel W.} and Dmytro Lituiev and Copeland, {Timothy P.} and Aboian, {Mariam S.} and Aparici, {Carina Mari} and Behr, {Spencer C.} and Flavell, {Robert R.} and Huang, {Shih Ying} and Zalocusky, {Kelly A.} and Lorenzo Nardo and Youngho Seo and Hawkins, {Randall A.} and Pampaloni, {Miguel Hernandez} and Dexter Hadley and Franc, {Benjamin L.}",
year = "2019",
month = "3",
day = "1",
doi = "10.1148/radiol.2018180958",
language = "English (US)",
volume = "290",
pages = "456--464",
journal = "Radiology",
issn = "0033-8419",
publisher = "Radiological Society of North America Inc.",
number = "3",

}

TY - JOUR

T1 - A deep learning model to predict a diagnosis of Alzheimer disease by using 18 F-FDG PET of the brain

AU - Ding, Yiming

AU - Sohn, Jae Ho

AU - Kawczynski, Michael G.

AU - Trivedi, Hari

AU - Harnish, Roy

AU - Jenkins, Nathaniel W.

AU - Lituiev, Dmytro

AU - Copeland, Timothy P.

AU - Aboian, Mariam S.

AU - Aparici, Carina Mari

AU - Behr, Spencer C.

AU - Flavell, Robert R.

AU - Huang, Shih Ying

AU - Zalocusky, Kelly A.

AU - Nardo, Lorenzo

AU - Seo, Youngho

AU - Hawkins, Randall A.

AU - Pampaloni, Miguel Hernandez

AU - Hadley, Dexter

AU - Franc, Benjamin L.

PY - 2019/3/1

Y1 - 2019/3/1

N2 - Purpose: To develop and validate a deep learning algorithm that predicts the final diagnosis of Alzheimer disease (AD), mild cognitive impairment, or neither at fluorine 18 ( 18 F) fluorodeoxyglucose (FDG) PET of the brain and compare its performance to that of radiologic readers. Materials and Methods: Prospective 18 F-FDG PET brain images from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) (2109 imaging studies from 2005 to 2017, 1002 patients) and retrospective independent test set (40 imaging studies from 2006 to 2016, 40 patients) were collected. Final clinical diagnosis at follow-up was recorded. Convolutional neural network of InceptionV3 architecture was trained on 90% of ADNI data set and tested on the remaining 10%, as well as the independent test set, with performance compared to radiologic readers. Model was analyzed with sensitivity, specificity, receiver operating characteristic (ROC), saliency map, and t-distributed stochastic neighbor embedding. Results: The algorithm achieved area under the ROC curve of 0.98 (95% confidence interval: 0.94, 1.00) when evaluated on predicting the final clinical diagnosis of AD in the independent test set (82% specificity at 100% sensitivity), an average of 75.8 months prior to the final diagnosis, which in ROC space outperformed reader performance (57% [four of seven] sensitivity, 91% [30 of 33] specificity; P , .05). Saliency map demonstrated attention to known areas of interest but with focus on the entire brain. Conclusion: By using fluorine 18 fluorodeoxyglucose PET of the brain, a deep learning algorithm developed for early prediction of Alzheimer disease achieved 82% specificity at 100% sensitivity, an average of 75.8 months prior to the final diagnosis.

AB - Purpose: To develop and validate a deep learning algorithm that predicts the final diagnosis of Alzheimer disease (AD), mild cognitive impairment, or neither at fluorine 18 ( 18 F) fluorodeoxyglucose (FDG) PET of the brain and compare its performance to that of radiologic readers. Materials and Methods: Prospective 18 F-FDG PET brain images from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) (2109 imaging studies from 2005 to 2017, 1002 patients) and retrospective independent test set (40 imaging studies from 2006 to 2016, 40 patients) were collected. Final clinical diagnosis at follow-up was recorded. Convolutional neural network of InceptionV3 architecture was trained on 90% of ADNI data set and tested on the remaining 10%, as well as the independent test set, with performance compared to radiologic readers. Model was analyzed with sensitivity, specificity, receiver operating characteristic (ROC), saliency map, and t-distributed stochastic neighbor embedding. Results: The algorithm achieved area under the ROC curve of 0.98 (95% confidence interval: 0.94, 1.00) when evaluated on predicting the final clinical diagnosis of AD in the independent test set (82% specificity at 100% sensitivity), an average of 75.8 months prior to the final diagnosis, which in ROC space outperformed reader performance (57% [four of seven] sensitivity, 91% [30 of 33] specificity; P , .05). Saliency map demonstrated attention to known areas of interest but with focus on the entire brain. Conclusion: By using fluorine 18 fluorodeoxyglucose PET of the brain, a deep learning algorithm developed for early prediction of Alzheimer disease achieved 82% specificity at 100% sensitivity, an average of 75.8 months prior to the final diagnosis.

UR - http://www.scopus.com/inward/record.url?scp=85060372984&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060372984&partnerID=8YFLogxK

U2 - 10.1148/radiol.2018180958

DO - 10.1148/radiol.2018180958

M3 - Article

VL - 290

SP - 456

EP - 464

JO - Radiology

JF - Radiology

SN - 0033-8419

IS - 3

ER -