Rapid artificial intelligence solutions in a pandemic—The COVID-19-20 Lung CT Lesion Segmentation Challenge

Holger R. Roth; Ziyue Xu; Carlos Tor-Díez; Ramon Sanchez Jacob; Jonathan Zember; Jose Molto; Wenqi Li; Sheng Xu; Baris Turkbey; Evrim Turkbey; Dong Yang; Ahmed Harouni; Nicola Rieke; Shishuai Hu; Fabian Isensee; Claire Tang; Qinji Yu; Jan Sölter; Tong Zheng; Vitali Liauchuk; Ziqi Zhou; Jan Hendrik Moltz; Bruno Oliveira; Yong Xia; Klaus H. Maier-Hein; Qikai Li; Andreas Husch; Luyang Zhang; Vassili Kovalev; Li Kang; Alessa Hering; João L. Vilaça; Mona Flores; Daguang Xu; Bradford Wood; Marius George Linguraru

doi:10.1016/j.media.2022.102605

Rapid artificial intelligence solutions in a pandemic—The COVID-19-20 Lung CT Lesion Segmentation Challenge

Holger R. Roth^*, Ziyue Xu, Carlos Tor-Díez, Ramon Sanchez Jacob, Jonathan Zember, Jose Molto, Wenqi Li, Sheng Xu, Baris Turkbey, Evrim Turkbey, Dong Yang, Ahmed Harouni, Nicola Rieke, Shishuai Hu, Fabian Isensee, Claire Tang, Qinji Yu, Jan Sölter, Tong Zheng, Vitali LiauchukZiqi Zhou, Jan Hendrik Moltz, Bruno Oliveira, Yong Xia, Klaus H. Maier-Hein, Qikai Li, Andreas Husch, Luyang Zhang, Vassili Kovalev, Li Kang, Alessa Hering, João L. Vilaça, Mona Flores, Daguang Xu, Bradford Wood, Marius George Linguraru

^*Corresponding author for this work

Institute of Mathematics and Image Computing

Abstract

Artificial intelligence (AI) methods for the automatic detection and quantification of COVID-19 lesions in chest computed tomography (CT) might play an important role in the monitoring and management of the disease. We organized an international challenge and competition for the development and comparison of AI algorithms for this task, which we supported with public data and state-of-the-art benchmark methods. Board Certified Radiologists annotated 295 public images from two sources (A and B) for algorithms training (n=199, source A), validation (n=50, source A) and testing (n=23, source A; n=23, source B). There were 1,096 registered teams of which 225 and 98 completed the validation and testing phases, respectively. The challenge showed that AI models could be rapidly designed by diverse teams with the potential to measure disease or facilitate timely and patient-specific interventions. This paper provides an overview and the major outcomes of the COVID-19 Lung CT Lesion Segmentation Challenge — 2020.

Original language	English
Article number	102605
Journal	Medical Image Analysis
Volume	82
ISSN	1361-8415
DOIs	https://doi.org/10.1016/j.media.2022.102605
Publication status	Published - 11.2022

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1016/j.media.2022.102605

Cite this

Roth, H. R., Xu, Z., Tor-Díez, C., Sanchez Jacob, R., Zember, J., Molto, J., Li, W., Xu, S., Turkbey, B., Turkbey, E., Yang, D., Harouni, A., Rieke, N., Hu, S., Isensee, F., Tang, C., Yu, Q., Sölter, J., Zheng, T., ... Linguraru, M. G. (2022). Rapid artificial intelligence solutions in a pandemic—The COVID-19-20 Lung CT Lesion Segmentation Challenge. Medical Image Analysis, 82, Article 102605. https://doi.org/10.1016/j.media.2022.102605

@article{65d2d135f41d4013b56103d92859407c,

title = "Rapid artificial intelligence solutions in a pandemic—The COVID-19-20 Lung CT Lesion Segmentation Challenge",

abstract = "Artificial intelligence (AI) methods for the automatic detection and quantification of COVID-19 lesions in chest computed tomography (CT) might play an important role in the monitoring and management of the disease. We organized an international challenge and competition for the development and comparison of AI algorithms for this task, which we supported with public data and state-of-the-art benchmark methods. Board Certified Radiologists annotated 295 public images from two sources (A and B) for algorithms training (n=199, source A), validation (n=50, source A) and testing (n=23, source A; n=23, source B). There were 1,096 registered teams of which 225 and 98 completed the validation and testing phases, respectively. The challenge showed that AI models could be rapidly designed by diverse teams with the potential to measure disease or facilitate timely and patient-specific interventions. This paper provides an overview and the major outcomes of the COVID-19 Lung CT Lesion Segmentation Challenge — 2020.",

author = "Roth, {Holger R.} and Ziyue Xu and Carlos Tor-D{\'i}ez and {Sanchez Jacob}, Ramon and Jonathan Zember and Jose Molto and Wenqi Li and Sheng Xu and Baris Turkbey and Evrim Turkbey and Dong Yang and Ahmed Harouni and Nicola Rieke and Shishuai Hu and Fabian Isensee and Claire Tang and Qinji Yu and Jan S{\"o}lter and Tong Zheng and Vitali Liauchuk and Ziqi Zhou and Moltz, {Jan Hendrik} and Bruno Oliveira and Yong Xia and Maier-Hein, {Klaus H.} and Qikai Li and Andreas Husch and Luyang Zhang and Vassili Kovalev and Li Kang and Alessa Hering and Vila{\c c}a, {Jo{\~a}o L.} and Mona Flores and Daguang Xu and Bradford Wood and Linguraru, {Marius George}",

note = "Publisher Copyright: {\textcopyright} 2022 Elsevier B.V.",

year = "2022",

month = nov,

doi = "10.1016/j.media.2022.102605",

language = "English",

volume = "82",

journal = "Medical Image Analysis",

issn = "1361-8415",

}

Roth, HR, Xu, Z, Tor-Díez, C, Sanchez Jacob, R, Zember, J, Molto, J, Li, W, Xu, S, Turkbey, B, Turkbey, E, Yang, D, Harouni, A, Rieke, N, Hu, S, Isensee, F, Tang, C, Yu, Q, Sölter, J, Zheng, T, Liauchuk, V, Zhou, Z, Moltz, JH, Oliveira, B, Xia, Y, Maier-Hein, KH, Li, Q, Husch, A, Zhang, L, Kovalev, V, Kang, L, Hering, A, Vilaça, JL, Flores, M, Xu, D, Wood, B & Linguraru, MG 2022, 'Rapid artificial intelligence solutions in a pandemic—The COVID-19-20 Lung CT Lesion Segmentation Challenge', Medical Image Analysis, vol. 82, 102605. https://doi.org/10.1016/j.media.2022.102605

TY - JOUR

T1 - Rapid artificial intelligence solutions in a pandemic—The COVID-19-20 Lung CT Lesion Segmentation Challenge

AU - Roth, Holger R.

AU - Xu, Ziyue

AU - Tor-Díez, Carlos

AU - Sanchez Jacob, Ramon

AU - Zember, Jonathan

AU - Molto, Jose

AU - Li, Wenqi

AU - Xu, Sheng

AU - Turkbey, Baris

AU - Turkbey, Evrim

AU - Yang, Dong

AU - Harouni, Ahmed

AU - Rieke, Nicola

AU - Hu, Shishuai

AU - Isensee, Fabian

AU - Tang, Claire

AU - Yu, Qinji

AU - Sölter, Jan

AU - Zheng, Tong

AU - Liauchuk, Vitali

AU - Zhou, Ziqi

AU - Moltz, Jan Hendrik

AU - Oliveira, Bruno

AU - Xia, Yong

AU - Maier-Hein, Klaus H.

AU - Li, Qikai

AU - Husch, Andreas

AU - Zhang, Luyang

AU - Kovalev, Vassili

AU - Kang, Li

AU - Hering, Alessa

AU - Vilaça, João L.

AU - Flores, Mona

AU - Xu, Daguang

AU - Wood, Bradford

AU - Linguraru, Marius George

PY - 2022/11

Y1 - 2022/11

N2 - Artificial intelligence (AI) methods for the automatic detection and quantification of COVID-19 lesions in chest computed tomography (CT) might play an important role in the monitoring and management of the disease. We organized an international challenge and competition for the development and comparison of AI algorithms for this task, which we supported with public data and state-of-the-art benchmark methods. Board Certified Radiologists annotated 295 public images from two sources (A and B) for algorithms training (n=199, source A), validation (n=50, source A) and testing (n=23, source A; n=23, source B). There were 1,096 registered teams of which 225 and 98 completed the validation and testing phases, respectively. The challenge showed that AI models could be rapidly designed by diverse teams with the potential to measure disease or facilitate timely and patient-specific interventions. This paper provides an overview and the major outcomes of the COVID-19 Lung CT Lesion Segmentation Challenge — 2020.

AB - Artificial intelligence (AI) methods for the automatic detection and quantification of COVID-19 lesions in chest computed tomography (CT) might play an important role in the monitoring and management of the disease. We organized an international challenge and competition for the development and comparison of AI algorithms for this task, which we supported with public data and state-of-the-art benchmark methods. Board Certified Radiologists annotated 295 public images from two sources (A and B) for algorithms training (n=199, source A), validation (n=50, source A) and testing (n=23, source A; n=23, source B). There were 1,096 registered teams of which 225 and 98 completed the validation and testing phases, respectively. The challenge showed that AI models could be rapidly designed by diverse teams with the potential to measure disease or facilitate timely and patient-specific interventions. This paper provides an overview and the major outcomes of the COVID-19 Lung CT Lesion Segmentation Challenge — 2020.

UR - http://www.scopus.com/inward/record.url?scp=85138451932&partnerID=8YFLogxK

U2 - 10.1016/j.media.2022.102605

DO - 10.1016/j.media.2022.102605

M3 - Short survey

C2 - 36156419

AN - SCOPUS:85138451932

SN - 1361-8415

VL - 82

JO - Medical Image Analysis

JF - Medical Image Analysis

M1 - 102605

ER -

Rapid artificial intelligence solutions in a pandemic—The COVID-19-20 Lung CT Lesion Segmentation Challenge

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this