Automated Assessment of COVID-19 Reporting and Data System and Chest CT Severity Scores in Patients Suspected of Having COVID-19 Using Artificial Intelligence

被引：96

作者：

Lessmann, Nikolas ^{[1
]}

Sanchez, Clara, I ^{[1
]}

Beenen, Ludo ^{[2
]}

Boulogne, Luuk H. ^{[1
]}

Brink, Monique ^{[1
]}

Calli, Erdi ^{[1
]}

Charbonnier, Jean-Paul ^{[3
]}

Dofferhoff, Ton ^{[4
]}

van Everdingen, Wouter M. ^{[1
]}

Gerke, Paul K. ^{[1
]}

Geurts, Bram ^{[1
]}

Gietema, Hester A. ^{[6
]}

Groeneveld, Miriam ^{[1
]}

van Harten, Louis ^{[7
,8
]}

Hendrix, Nils ^{[1
]}

Hendrix, Ward ^{[1
]}

Huisman, Henkjan J. ^{[1
]}

Isgum, Ivana ^{[7
,8
]}

Jacobs, Colin ^{[1
]}

Kluge, Ruben ^{[1
]}

Kok, Michel ^{[1
]}

Krdzalic, Jasenko ^{[9
]}

Lassen-Schmidt, Bianca ^{[10
]}

van Leeuwen, Kicky ^{[1
]}

Meakin, James ^{[1
]}

Overkamp, Mike ^{[1
]}

Vellinga, Tjalco van Rees ^{[11
]}

van Rikxoort, Eva M. ^{[3
]}

Samperna, Riccardo ^{[1
]}

Schaefer-Prokop, Cornelia ^{[1
,12
]}

Schalekamp, Steven ^{[1
,12
]}

Scholten, Ernst Th ^{[1
]}

Sital, Cheryl ^{[1
]}

Stoeger, J. Lauran ^{[1
,13
]}

Teuwen, Jonas ^{[1
]}

Venkadesh, Kiran Vaidhya ^{[1
]}

de Vente, Coen ^{[1
]}

Vermaat, Marieke ^{[5
]}

Xie, Weiyi ^{[1
]}

de Wilde, Bram ^{[1
]}

Prokop, Mathias ^{[1
]}

van Ginneken, Bram ^{[1
]}

机构：

[1] Radboud Univ Nijmegen, Dept Radiol Nucl Med & Anat, Med Ctr, POB 9101, NL-6500 HB Nijmegen, Netherlands

[2] Acad Med Ctr, Dept Radiol, Amsterdam, Netherlands

[3] Thirona, Nijmegen, Netherlands

[4] Canisius Wilhelmina Ziekenhuis, Dept Internal Med, Nijmegen, Netherlands

[5] Canisius Wilhelmina Ziekenhuis, Dept Radiol, Nijmegen, Netherlands

[6] Maastricht Univ, Dept Radiol & Nucl Med, Med Ctr, Maastricht, Netherlands

[7] Univ Amsterdam, Med Ctr, Dept Biomed Phys & Engn, Amsterdam, Netherlands

[8] Univ Amsterdam, Med Ctr, Dept Radiol & Nucl Med, Amsterdam, Netherlands

[9] Zuyderland Med Ctr, Dept Radiol, Heerlen, Netherlands

[10] Fraunhofer Inst Digital Med MEVIS, Bremen, Germany

[11] Haaglanden Med Ctr, Dept Radiol & Nucl Med, The Hague, Netherlands

[12] Meander Med Ctr, Dept Radiol, Amersfoort, Netherlands

[13] Leiden Univ, Dept Radiol, Med Ctr, Leiden, Netherlands

来源：

RADIOLOGY | 2021年 / 298卷 / 01期

关键词：

DIAGNOSIS;

D O I：

10.1148/radiol.2020202439

中图分类号：

R8 [特种医学]; R445 [影像诊断学];

学科分类号：

100231 [临床病理学]; 100902 [航空航天医学];

摘要：

Background: The coronavirus disease 2019 (COVID-19) pandemic has spread across the globe with alarming speed, morbidity, and mortality. Immediate triage of patients with chest infections suspected to be caused by COVID-19 using chest CT may be of assistance when results from definitive viral testing are delayed. Purpose: To develop and validate an artificial intelligence (AI) system to score the likelihood and extent of pulmonary COVID-19 on chest CT scans using the COVID-19 Reporting and Data System (CO-RADS) and CT severity scoring systems. Materials and Methods: The CO-RADS AI system consists of three deep-learning algorithms that automatically segment the five pulmonary lobes, assign a CO-RADS score for the suspicion of COVID-19, and assign a CT severity score for the degree of parenchymal involvement per lobe. This study retrospectively included patients who underwent a nonenhanced chest CT examination because of clinical suspicion of COVID-19 at two medical centers. The system was trained, validated, and tested with data from one of the centers. Data from the second center served as an external test set. Diagnostic performance and agreement with scores assigned by eight independent observers were measured using receiver operating characteristic analysis, linearly weighted kappa values, and classification accuracy. Results: A total of 105 patients (mean age, 62 years +/- 16 [standard deviation]; 61 men) and 262 patients (mean age, 64 years +/- 16; 154 men) were evaluated in the internal and external test sets, respectively. The system discriminated between patients with COVID-19 and those without COVID-19, with areas under the receiver operating characteristic curve of 0.95 (95% CI: 0.91, 0.98) and 0.88 (95% CI: 0.84, 0.93), for the internal and external test sets, respectively. Agreement with the eight human observers was moderate to substantial, with mean linearly weighted k values of 0.60 +/- 0.01 for CO-RADS scores and 0.54 +/- 0.01 for CT severity scores. Conclusion: With high diagnostic performance, the CO-RADS AI system correctly identified patients with COVID-19 using chest CT scans and assigned standardized CO-RADS and CT severity scores that demonstrated good agreement with findings from eight independent observers and generalized well to external data. (C) RSNA, 2020

引用

页码：E18 / E28

页数：11

共 33 条

[1]

[Anonymous], 2020, CLIN CHEM LAB MED, DOI DOI 10.1515/cclm-2020-0593

[2]

End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography [J].

Ardila, Diego ;

Kiraly, Atilla P. ;

Bharadwaj, Sujeeth ;

Choi, Bokyung ;

Reicher, Joshua J. ;

Peng, Lily ;

Tse, Daniel ;

Etemadi, Mozziyar ;

Ye, Wenxing ;

Corrado, Greg ;

Naidich, David P. ;

Shetty, Shravya .

NATURE MEDICINE, 2019, 25 (06) :954-+

[3]

Artificial Intelligence Augmentation of Radiologist Performance in Distinguishing COVID-19 from Pneumonia of Other Origin at Chest CT [J].

Bai, Harrison X. ;

Wang, Robin ;

Xiong, Zeng ;

Hsieh, Ben ;

Chang, Ken ;

Halsey, Kasey ;

Thi My Linh Tran ;

Choi, Ji Whae ;

Wang, Dong-Cui ;

Shi, Lin-Bo ;

Mei, Ji ;

Jiang, Xiao-Long ;

Pan, Ian ;

Zeng, Qiu-Hua ;

Hu, Ping-Feng ;

Li, Yi-Hui ;

Fu, Fei-Xian ;

Huang, Raymond Y. ;

Sebro, Ronnie ;

Yu, Qi-Zhi ;

Atalay, Michael K. ;

Liao, Wei-Hua .

RADIOLOGY, 2020, 296 (03) :E156-E165

[4]

RETRACTED: Deep learning system to screen coronavirus disease 2019 pneumonia (Retracted Article) [J].

Butt, Charmaine ;

Gill, Jagpal ;

Chun, David ;

Babu, Benson A. .

APPLIED INTELLIGENCE, 2023, 53 (04) :4874-4874

[5]

Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset [J].

Carreira, Joao ;

Zisserman, Andrew .

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :4724-4733

[6]

Pulmonary sequelae in convalescent patients after severe acute respiratory syndrome: Evaluation with thin-section CT [J].

Chang, YC ;

Yu, CJ ;

Chang, SC ;

Galvin, JR ;

Liu, HM ;

Hsiao, CH ;

Kuo, PH ;

Chen, KY ;

Franks, TJ ;

Huang, KM ;

Yang, PC .

RADIOLOGY, 2005, 236 (03) :1067-1075

[7]

Dofferhoff A S M, 2020, Ned Tijdschr Geneeskd, V164

[8]

Quantifying the Extent of Emphysema: Factors Associated with Radiologists' Estimations and Quantitative Indices of Emphysema Severity Using the ECLIPSE Cohort [J].

Gietema, Hester A. ;

Mueller, Nestor L. ;

Fauerbach, Paola V. Nasute ;

Sharma, Sanjay ;

Edwards, Lisa D. ;

Camp, Pat G. ;

Coxson, Harvey O. .

ACADEMIC RADIOLOGY, 2011, 18 (06) :661-671

[9]

Gozes O., ARXIV200305037

[10]

Isensee F, 2019, ARXIV190408128

← 1 2 3 4 →