AI-driven quantification, staging and outcome prediction of COVID-19 pneumonia

Guillaume Chassagnon; Maria Vakalopoulou; Enzo Battistella; Stergios Christodoulidis; Trieu Nghi Hoang-Thi; Severine Dangeard; Eric Deutsch; Fabrice Andre; Enora Guillo; Nara Halm; Stefany El Hajj; Florian Bompard; Sophie Neveu; Chahinez Hani; Ines Saab; Aliénor Campredon; Hasmik Koulakian; Souhail Bennani; Gael Freche; Maxime Barat; Aurelien Lombard; Laure Fournier; Hippolyte Monnier; Téodor Grand; Jules Gregory; Yann Nguyen; Antoine Khalil; Elyas Mahdjoub; Pierre Yves Brillet; Stéphane Tran Ba; Valérie Bousson; Ahmed Mekki; Robert Yves Carlier; Marie Pierre Revel; Nikos Paragios

doi:10.1016/j.media.2020.101860

AI-driven quantification, staging and outcome prediction of COVID-19 pneumonia

Guillaume Chassagnon, Maria Vakalopoulou, Enzo Battistella, Stergios Christodoulidis, Trieu Nghi Hoang-Thi, Severine Dangeard, Eric Deutsch, Fabrice Andre, Enora Guillo, Nara Halm, Stefany El Hajj, Florian Bompard, Sophie Neveu, Chahinez Hani, Ines Saab, Aliénor Campredon, Hasmik Koulakian, Souhail Bennani, Gael Freche, Maxime BaratAurelien Lombard, Laure Fournier, Hippolyte Monnier, Téodor Grand, Jules Gregory, Yann Nguyen, Antoine Khalil, Elyas Mahdjoub, Pierre Yves Brillet, Stéphane Tran Ba, Valérie Bousson, Ahmed Mekki, Robert Yves Carlier, Marie Pierre Revel, Nikos Paragios

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

103 Citations (Scopus)

Abstract

Coronavirus disease 2019 (COVID-19) emerged in 2019 and disseminated around the world rapidly. Computed tomography (CT) imaging has been proven to be an important tool for screening, disease quantification and staging. The latter is of extreme importance for organizational anticipation (availability of intensive care unit beds, patient management planning) as well as to accelerate drug development through rapid, reproducible and quantified assessment of treatment response. Even if currently there are no specific guidelines for the staging of the patients, CT together with some clinical and biological biomarkers are used. In this study, we collected a multi-center cohort and we investigated the use of medical imaging and artificial intelligence for disease quantification, staging and outcome prediction. Our approach relies on automatic deep learning-based disease quantification using an ensemble of architectures, and a data-driven consensus for the staging and outcome prediction of the patients fusing imaging biomarkers with clinical and biological attributes. Highly promising results on multiple external/independent evaluation cohorts as well as comparisons with expert human readers demonstrate the potentials of our approach.

Original language	English
Article number	101860
Journal	Medical Image Analysis
Volume	67
DOIs	https://doi.org/10.1016/j.media.2020.101860
Publication status	Published - 1 Jan 2021

Keywords

Artifial intelligence
Biomarker discovery
COVID 19 pneumonia
Deep learning
Ensemble methods
Prognosis
Staging

Access to Document

10.1016/j.media.2020.101860

Cite this

Chassagnon, G., Vakalopoulou, M., Battistella, E., Christodoulidis, S., Hoang-Thi, T. N., Dangeard, S., Deutsch, E., Andre, F., Guillo, E., Halm, N., El Hajj, S., Bompard, F., Neveu, S., Hani, C., Saab, I., Campredon, A., Koulakian, H., Bennani, S., Freche, G., ... Paragios, N. (2021). AI-driven quantification, staging and outcome prediction of COVID-19 pneumonia. Medical Image Analysis, 67, Article 101860. https://doi.org/10.1016/j.media.2020.101860

@article{455bda0836f64612892e4fc620e28d06,

title = "AI-driven quantification, staging and outcome prediction of COVID-19 pneumonia",

abstract = "Coronavirus disease 2019 (COVID-19) emerged in 2019 and disseminated around the world rapidly. Computed tomography (CT) imaging has been proven to be an important tool for screening, disease quantification and staging. The latter is of extreme importance for organizational anticipation (availability of intensive care unit beds, patient management planning) as well as to accelerate drug development through rapid, reproducible and quantified assessment of treatment response. Even if currently there are no specific guidelines for the staging of the patients, CT together with some clinical and biological biomarkers are used. In this study, we collected a multi-center cohort and we investigated the use of medical imaging and artificial intelligence for disease quantification, staging and outcome prediction. Our approach relies on automatic deep learning-based disease quantification using an ensemble of architectures, and a data-driven consensus for the staging and outcome prediction of the patients fusing imaging biomarkers with clinical and biological attributes. Highly promising results on multiple external/independent evaluation cohorts as well as comparisons with expert human readers demonstrate the potentials of our approach.",

keywords = "Artifial intelligence, Biomarker discovery, COVID 19 pneumonia, Deep learning, Ensemble methods, Prognosis, Staging",

author = "Guillaume Chassagnon and Maria Vakalopoulou and Enzo Battistella and Stergios Christodoulidis and Hoang-Thi, {Trieu Nghi} and Severine Dangeard and Eric Deutsch and Fabrice Andre and Enora Guillo and Nara Halm and {El Hajj}, Stefany and Florian Bompard and Sophie Neveu and Chahinez Hani and Ines Saab and Ali{\'e}nor Campredon and Hasmik Koulakian and Souhail Bennani and Gael Freche and Maxime Barat and Aurelien Lombard and Laure Fournier and Hippolyte Monnier and T{\'e}odor Grand and Jules Gregory and Yann Nguyen and Antoine Khalil and Elyas Mahdjoub and Brillet, {Pierre Yves} and {Tran Ba}, St{\'e}phane and Val{\'e}rie Bousson and Ahmed Mekki and Carlier, {Robert Yves} and Revel, {Marie Pierre} and Nikos Paragios",

note = "Publisher Copyright: {\textcopyright} 2020 The Author(s)",

year = "2021",

month = jan,

day = "1",

doi = "10.1016/j.media.2020.101860",

language = "English",

volume = "67",

journal = "Medical Image Analysis",

issn = "1361-8415",

}

Chassagnon, G, Vakalopoulou, M, Battistella, E, Christodoulidis, S, Hoang-Thi, TN, Dangeard, S, Deutsch, E, Andre, F, Guillo, E, Halm, N, El Hajj, S, Bompard, F, Neveu, S, Hani, C, Saab, I, Campredon, A, Koulakian, H, Bennani, S, Freche, G, Barat, M, Lombard, A, Fournier, L, Monnier, H, Grand, T, Gregory, J, Nguyen, Y, Khalil, A, Mahdjoub, E, Brillet, PY, Tran Ba, S, Bousson, V, Mekki, A, Carlier, RY, Revel, MP & Paragios, N 2021, 'AI-driven quantification, staging and outcome prediction of COVID-19 pneumonia', Medical Image Analysis, vol. 67, 101860. https://doi.org/10.1016/j.media.2020.101860

TY - JOUR

T1 - AI-driven quantification, staging and outcome prediction of COVID-19 pneumonia

AU - Chassagnon, Guillaume

AU - Vakalopoulou, Maria

AU - Battistella, Enzo

AU - Christodoulidis, Stergios

AU - Hoang-Thi, Trieu Nghi

AU - Dangeard, Severine

AU - Deutsch, Eric

AU - Andre, Fabrice

AU - Guillo, Enora

AU - Halm, Nara

AU - El Hajj, Stefany

AU - Bompard, Florian

AU - Neveu, Sophie

AU - Hani, Chahinez

AU - Saab, Ines

AU - Campredon, Aliénor

AU - Koulakian, Hasmik

AU - Bennani, Souhail

AU - Freche, Gael

AU - Barat, Maxime

AU - Lombard, Aurelien

AU - Fournier, Laure

AU - Monnier, Hippolyte

AU - Grand, Téodor

AU - Gregory, Jules

AU - Nguyen, Yann

AU - Khalil, Antoine

AU - Mahdjoub, Elyas

AU - Brillet, Pierre Yves

AU - Tran Ba, Stéphane

AU - Bousson, Valérie

AU - Mekki, Ahmed

AU - Carlier, Robert Yves

AU - Revel, Marie Pierre

AU - Paragios, Nikos

PY - 2021/1/1

Y1 - 2021/1/1

N2 - Coronavirus disease 2019 (COVID-19) emerged in 2019 and disseminated around the world rapidly. Computed tomography (CT) imaging has been proven to be an important tool for screening, disease quantification and staging. The latter is of extreme importance for organizational anticipation (availability of intensive care unit beds, patient management planning) as well as to accelerate drug development through rapid, reproducible and quantified assessment of treatment response. Even if currently there are no specific guidelines for the staging of the patients, CT together with some clinical and biological biomarkers are used. In this study, we collected a multi-center cohort and we investigated the use of medical imaging and artificial intelligence for disease quantification, staging and outcome prediction. Our approach relies on automatic deep learning-based disease quantification using an ensemble of architectures, and a data-driven consensus for the staging and outcome prediction of the patients fusing imaging biomarkers with clinical and biological attributes. Highly promising results on multiple external/independent evaluation cohorts as well as comparisons with expert human readers demonstrate the potentials of our approach.

AB - Coronavirus disease 2019 (COVID-19) emerged in 2019 and disseminated around the world rapidly. Computed tomography (CT) imaging has been proven to be an important tool for screening, disease quantification and staging. The latter is of extreme importance for organizational anticipation (availability of intensive care unit beds, patient management planning) as well as to accelerate drug development through rapid, reproducible and quantified assessment of treatment response. Even if currently there are no specific guidelines for the staging of the patients, CT together with some clinical and biological biomarkers are used. In this study, we collected a multi-center cohort and we investigated the use of medical imaging and artificial intelligence for disease quantification, staging and outcome prediction. Our approach relies on automatic deep learning-based disease quantification using an ensemble of architectures, and a data-driven consensus for the staging and outcome prediction of the patients fusing imaging biomarkers with clinical and biological attributes. Highly promising results on multiple external/independent evaluation cohorts as well as comparisons with expert human readers demonstrate the potentials of our approach.

KW - Artifial intelligence

KW - Biomarker discovery

KW - COVID 19 pneumonia

KW - Deep learning

KW - Ensemble methods

KW - Prognosis

KW - Staging

UR - http://www.scopus.com/inward/record.url?scp=85095434755&partnerID=8YFLogxK

U2 - 10.1016/j.media.2020.101860

DO - 10.1016/j.media.2020.101860

M3 - Article

C2 - 33171345

AN - SCOPUS:85095434755

SN - 1361-8415

VL - 67

JO - Medical Image Analysis

JF - Medical Image Analysis

M1 - 101860

ER -

AI-driven quantification, staging and outcome prediction of COVID-19 pneumonia

Abstract

Keywords

Access to Document

Other files and links

Cite this