Deep convolutional neural networks to predict cardiovascular risk from computed tomography

Roman Zeleznik; Borek Foldyna; Parastou Eslami; Jakob Weiss; Ivanov Alexander; Jana Taron; Chintan Parmar; Raza M. Alvi; Dahlia Banerji; Mio Uno; Yasuka Kikuchi; Julia Karady; Lili Zhang; Jan-Erik Scholtz; Thomas Mayrhofer; Asya Lyass; Taylor F. Mahoney; Joseph M. Massaro; Ramachandran S. Vasan; Pamela S. Douglas; Udo Hoffmann; Michael T. Lu; Hugo J. W. L. Aerts

doi:10.1038/s41467-021-20966-2

Deep convolutional neural networks to predict cardiovascular risk from computed tomography

Roman Zeleznik, Borek Foldyna, Parastou Eslami, Jakob Weiss, Ivanov Alexander, Jana Taron, Chintan Parmar, Raza M. Alvi, Dahlia Banerji, Mio Uno, Yasuka Kikuchi, Julia Karady, Lili Zhang, Jan-Erik Scholtz, Thomas Mayrhofer, Asya Lyass, Taylor F. Mahoney, Joseph M. Massaro, Ramachandran S. Vasan, Pamela S. DouglasUdo Hoffmann, Michael T. Lu, Hugo J. W. L. Aerts^*

^*Corresponding author for this work

Research output: Contribution to journal › Article › Academic › peer-review

Abstract

Coronary artery calcium is an accurate predictor of cardiovascular events. While it is visible on all computed tomography (CT) scans of the chest, this information is not routinely quantified as it requires expertise, time, and specialized equipment. Here, we show a robust and time-efficient deep learning system to automatically quantify coronary calcium on routine cardiac-gated and non-gated CT. As we evaluate in 20,084 individuals from distinct asymptomatic (Framingham Heart Study, NLST) and stable and acute chest pain (PROMISE, ROMICAT-II) cohorts, the automated score is a strong predictor of cardiovascular events, independent of risk factors (multivariable-adjusted hazard ratios up to 4.3), shows high correlation with manual quantification, and robust test-retest reliability. Our results demonstrate the clinical value of a deep learning system for the automated prediction of cardiovascular events. Implementation into clinical practice would address the unmet need of automating proven imaging biomarkers to guide management and improve population health. Coronary artery calcium is an accurate predictor of cardiovascular events but this information is not routinely quantified. Here the authors show a robust and time-efficient deep learning system to automatically quantify coronary calcium on CT scans and predict cardiovascular events in a large, multicentre study.

Original language	English
Article number	715
Number of pages	9
Journal	Nature Communications
Volume	12
Issue number	1
DOIs	https://doi.org/10.1038/s41467-021-20966-2
Publication status	Published - 29 Jan 2021

Keywords

CORONARY-ARTERY CALCIUM
CT ANGIOGRAPHY
CHEST-PAIN
CARDIAC CT
HEART
LUNG
CALCIFICATION
DISEASE
DESIGN
QUANTIFICATION

Access to Document

10.1038/s41467-021-20966-2Licence: CC BY

Cite this

Zeleznik, R., Foldyna, B., Eslami, P., Weiss, J., Alexander, I., Taron, J., Parmar, C., Alvi, R. M., Banerji, D., Uno, M., Kikuchi, Y., Karady, J., Zhang, L., Scholtz, J.-E., Mayrhofer, T., Lyass, A., Mahoney, T. F., Massaro, J. M., Vasan, R. S., ... Aerts, H. J. W. L. (2021). Deep convolutional neural networks to predict cardiovascular risk from computed tomography. Nature Communications, 12(1), Article 715. https://doi.org/10.1038/s41467-021-20966-2

@article{e365d237ab0f453fa9b132bd87bff7f1,

title = "Deep convolutional neural networks to predict cardiovascular risk from computed tomography",

abstract = "Coronary artery calcium is an accurate predictor of cardiovascular events. While it is visible on all computed tomography (CT) scans of the chest, this information is not routinely quantified as it requires expertise, time, and specialized equipment. Here, we show a robust and time-efficient deep learning system to automatically quantify coronary calcium on routine cardiac-gated and non-gated CT. As we evaluate in 20,084 individuals from distinct asymptomatic (Framingham Heart Study, NLST) and stable and acute chest pain (PROMISE, ROMICAT-II) cohorts, the automated score is a strong predictor of cardiovascular events, independent of risk factors (multivariable-adjusted hazard ratios up to 4.3), shows high correlation with manual quantification, and robust test-retest reliability. Our results demonstrate the clinical value of a deep learning system for the automated prediction of cardiovascular events. Implementation into clinical practice would address the unmet need of automating proven imaging biomarkers to guide management and improve population health. Coronary artery calcium is an accurate predictor of cardiovascular events but this information is not routinely quantified. Here the authors show a robust and time-efficient deep learning system to automatically quantify coronary calcium on CT scans and predict cardiovascular events in a large, multicentre study.",

keywords = "CORONARY-ARTERY CALCIUM, CT ANGIOGRAPHY, CHEST-PAIN, CARDIAC CT, HEART, LUNG, CALCIFICATION, DISEASE, DESIGN, QUANTIFICATION",

author = "Roman Zeleznik and Borek Foldyna and Parastou Eslami and Jakob Weiss and Ivanov Alexander and Jana Taron and Chintan Parmar and Alvi, {Raza M.} and Dahlia Banerji and Mio Uno and Yasuka Kikuchi and Julia Karady and Lili Zhang and Jan-Erik Scholtz and Thomas Mayrhofer and Asya Lyass and Mahoney, {Taylor F.} and Massaro, {Joseph M.} and Vasan, {Ramachandran S.} and Douglas, {Pamela S.} and Udo Hoffmann and Lu, {Michael T.} and Aerts, {Hugo J. W. L.}",

note = "Funding Information: The authors thank the Framingham Heart Study, NCI, ACRIN, NLST, Prospective Multicenter Imaging Study for Evaluation of Chest Pain, and Rule Out Myocardial Infarction Using Computer Assisted Tomography II trial for access to trial data. The authors acknowledge financial support from NIH (HA: NIH-USA U24CA194354, NIH-USA U01CA190234, NIH-USA U01CA209414, and NIH-USA R35CA22052; UH: NIH, 5R01-HL109711, NIH/NHLBI 5K24HL113128, NIH/NHLBI 5T32HL076136, NIH/ NHLBI 5U01HL123339), the European Union—European Research Council (HA: 866504), as well as the German Research Foundation (DFG; TA: 1438/1-1 and WE: 6405/ 2-1), American Heart Association Institute for Precision Cardiovascular Medicine (MTL: 18UNPG34030172), Fulbright Visiting Researcher Grant (E0583118), Rosztoczy Foundation Grant. The Framingham Heart Study (FHS) acknowledges the support of contracts NO1-HC-25195, HHSN268201500001I, and 75N92019D00031 from the National Heart, Lung and Blood Institute. Publisher Copyright: {\textcopyright} 2021, The Author(s).",

year = "2021",

month = jan,

day = "29",

doi = "10.1038/s41467-021-20966-2",

language = "English",

volume = "12",

journal = "Nature Communications",

issn = "2041-1723",

publisher = "Nature Publishing Group",

number = "1",

}

Zeleznik, R, Foldyna, B, Eslami, P, Weiss, J, Alexander, I, Taron, J, Parmar, C, Alvi, RM, Banerji, D, Uno, M, Kikuchi, Y, Karady, J, Zhang, L, Scholtz, J-E, Mayrhofer, T, Lyass, A, Mahoney, TF, Massaro, JM, Vasan, RS, Douglas, PS, Hoffmann, U, Lu, MT & Aerts, HJWL 2021, 'Deep convolutional neural networks to predict cardiovascular risk from computed tomography', Nature Communications, vol. 12, no. 1, 715. https://doi.org/10.1038/s41467-021-20966-2

TY - JOUR

T1 - Deep convolutional neural networks to predict cardiovascular risk from computed tomography

AU - Zeleznik, Roman

AU - Foldyna, Borek

AU - Eslami, Parastou

AU - Weiss, Jakob

AU - Alexander, Ivanov

AU - Taron, Jana

AU - Parmar, Chintan

AU - Alvi, Raza M.

AU - Banerji, Dahlia

AU - Uno, Mio

AU - Kikuchi, Yasuka

AU - Karady, Julia

AU - Zhang, Lili

AU - Scholtz, Jan-Erik

AU - Mayrhofer, Thomas

AU - Lyass, Asya

AU - Mahoney, Taylor F.

AU - Massaro, Joseph M.

AU - Vasan, Ramachandran S.

AU - Douglas, Pamela S.

AU - Hoffmann, Udo

AU - Lu, Michael T.

AU - Aerts, Hugo J. W. L.

N1 - Funding Information: The authors thank the Framingham Heart Study, NCI, ACRIN, NLST, Prospective Multicenter Imaging Study for Evaluation of Chest Pain, and Rule Out Myocardial Infarction Using Computer Assisted Tomography II trial for access to trial data. The authors acknowledge financial support from NIH (HA: NIH-USA U24CA194354, NIH-USA U01CA190234, NIH-USA U01CA209414, and NIH-USA R35CA22052; UH: NIH, 5R01-HL109711, NIH/NHLBI 5K24HL113128, NIH/NHLBI 5T32HL076136, NIH/ NHLBI 5U01HL123339), the European Union—European Research Council (HA: 866504), as well as the German Research Foundation (DFG; TA: 1438/1-1 and WE: 6405/ 2-1), American Heart Association Institute for Precision Cardiovascular Medicine (MTL: 18UNPG34030172), Fulbright Visiting Researcher Grant (E0583118), Rosztoczy Foundation Grant. The Framingham Heart Study (FHS) acknowledges the support of contracts NO1-HC-25195, HHSN268201500001I, and 75N92019D00031 from the National Heart, Lung and Blood Institute. Publisher Copyright: © 2021, The Author(s).

PY - 2021/1/29

Y1 - 2021/1/29

N2 - Coronary artery calcium is an accurate predictor of cardiovascular events. While it is visible on all computed tomography (CT) scans of the chest, this information is not routinely quantified as it requires expertise, time, and specialized equipment. Here, we show a robust and time-efficient deep learning system to automatically quantify coronary calcium on routine cardiac-gated and non-gated CT. As we evaluate in 20,084 individuals from distinct asymptomatic (Framingham Heart Study, NLST) and stable and acute chest pain (PROMISE, ROMICAT-II) cohorts, the automated score is a strong predictor of cardiovascular events, independent of risk factors (multivariable-adjusted hazard ratios up to 4.3), shows high correlation with manual quantification, and robust test-retest reliability. Our results demonstrate the clinical value of a deep learning system for the automated prediction of cardiovascular events. Implementation into clinical practice would address the unmet need of automating proven imaging biomarkers to guide management and improve population health. Coronary artery calcium is an accurate predictor of cardiovascular events but this information is not routinely quantified. Here the authors show a robust and time-efficient deep learning system to automatically quantify coronary calcium on CT scans and predict cardiovascular events in a large, multicentre study.

AB - Coronary artery calcium is an accurate predictor of cardiovascular events. While it is visible on all computed tomography (CT) scans of the chest, this information is not routinely quantified as it requires expertise, time, and specialized equipment. Here, we show a robust and time-efficient deep learning system to automatically quantify coronary calcium on routine cardiac-gated and non-gated CT. As we evaluate in 20,084 individuals from distinct asymptomatic (Framingham Heart Study, NLST) and stable and acute chest pain (PROMISE, ROMICAT-II) cohorts, the automated score is a strong predictor of cardiovascular events, independent of risk factors (multivariable-adjusted hazard ratios up to 4.3), shows high correlation with manual quantification, and robust test-retest reliability. Our results demonstrate the clinical value of a deep learning system for the automated prediction of cardiovascular events. Implementation into clinical practice would address the unmet need of automating proven imaging biomarkers to guide management and improve population health. Coronary artery calcium is an accurate predictor of cardiovascular events but this information is not routinely quantified. Here the authors show a robust and time-efficient deep learning system to automatically quantify coronary calcium on CT scans and predict cardiovascular events in a large, multicentre study.

KW - CORONARY-ARTERY CALCIUM

KW - CT ANGIOGRAPHY

KW - CHEST-PAIN

KW - CARDIAC CT

KW - HEART

KW - LUNG

KW - CALCIFICATION

KW - DISEASE

KW - DESIGN

KW - QUANTIFICATION

U2 - 10.1038/s41467-021-20966-2

DO - 10.1038/s41467-021-20966-2

M3 - Article

C2 - 33514711

SN - 2041-1723

VL - 12

JO - Nature Communications

JF - Nature Communications

IS - 1

M1 - 715

ER -

Deep convolutional neural networks to predict cardiovascular risk from computed tomography

Abstract

Keywords

Access to Document

Fingerprint

Cite this