nach oben

Erschienen in:

18.03.2021 | COVID-19 | Chest Zur Zeit gratis

AI detection of mild COVID-19 pneumonia from chest CT scans

verfasst von: Jin-Cao Yao, Tao Wang, Guang-Hua Hou, Di Ou, Wei Li, Qiao-Dan Zhu, Wen-Cong Chen, Chen Yang, Li-Jing Wang, Li-Ping Wang, Lin-Yin Fan, Kai-Yuan Shi, Jie Zhang, Dong Xu, Ya-Qing Li

Erschienen in: European Radiology | Ausgabe 9/2021

Einloggen, um Zugang zu erhalten

Abstract

Objectives

An artificial intelligence model was adopted to identify mild COVID-19 pneumonia from computed tomography (CT) volumes, and its diagnostic performance was then evaluated.

Methods

In this retrospective multicenter study, an atrous convolution-based deep learning model was established for the computer-assisted diagnosis of mild COVID-19 pneumonia. The dataset included 2087 chest CT exams collected from four hospitals between 1 January 2019 and 31 May 2020. The true positive rate, true negative rate, receiver operating characteristic curve, area under the curve (AUC) and convolutional feature map were used to evaluate the model.

Results

The proposed deep learning model was trained on 1538 patients and tested on an independent testing cohort of 549 patients. The overall sensitivity was 91.5% (195/213; p < 0.001, 95% CI: 89.2–93.9%), the overall specificity was 90.5% (304/336; p < 0.001, 95% CI: 88.0–92.9%) and the general AUC value was 0.955 (p < 0.001).

Conclusions

A deep learning model can accurately detect COVID-19 and serve as an important supplement to the COVID-19 reverse transcription–polymerase chain reaction (RT-PCR) test.

Key Points

• The implementation of a deep learning model to identify mild COVID-19 pneumonia was confirmed to be effective and feasible.

• The strategy of using a binary code instead of the region of interest label to identify mild COVID-19 pneumonia was verified.

• This AI model can assist in the early screening of COVID-19 without interfering with normal clinical examinations.

Nur mit Berechtigung zugänglich

Our previous CSAC-Net was submitted to PASCAL VOC server on 9 February 2020 and ranked first in the object classification task (Supplementary Materials 1).

Huang CL, Wang Y, Li XW et al (2020) Clinical features of patients infected with 2019 novel coronavirus in Wuhan, China. Lancet 395:497–506. https://doi.org/10.1016/S0140-6736(20)30183-5CrossRefPubMedPubMedCentral

Shang J, Ye G, Shi K et al (2020) Structural basis of receptor recognition by SARS-CoV-2. Nature 581:221–224. https://doi.org/10.1038/s41586-020-2179-yCrossRefPubMedPubMedCentral

Wu ZY, Jennifer MM (2020) Characteristics of and important lessons from the coronavirus disease 2019 (COVID-19) outbreak in China: summary of a report of 72,314 cases from the Chinese center for disease control and prevention. JAMA 13:1239–1242. https://doi.org/10.1001/jama.2020.2648CrossRef

Maier BF, Brockmann D (2020) Effective containment explains subexponential growth in recent confirmed COVID-19 cases in China. Science 368:742–746. https://doi.org/10.1126/science.abb4557CrossRefPubMedPubMedCentral

Word Health Organization (2020) Clinical management of COVID-19 interim guidance. https://www.who.int/publications/i/item/clinical-management-of-covid-19. Accessed 27 May 2020

Ai T, Yang ZL, Hou HY et al (2020) Correlation of chest CT and RT-PCR testing in coronavirus disease 2019 (COVID-19) in China: a report of 1014 cases. Radiology. https://doi.org/10.1148/radiol.2020200642

Fang YC, Zhang HQ, Xie JC et al (2020) Sensitivity of chest CT for COVID-19: comparison to RT-PCR. Radiology. https://doi.org/10.1148/radiol.2020200432

Choe JY, Kim JW, Kwon HH et al (2020) Diagnostic performance of immunochromatography assay for rapid detection of IgM and IgG in coronavirus disease 2019. J Med Virol 92:2567–2572. https://doi.org/10.1002/jmv.26060CrossRefPubMed

Pan Y, Guan H, Zhou S et al (2020) Initial CT findings and temporal changes in patients with the novel coronavirus pneumonia (2019-nCoV): a study of 63 patients in Wuhan, China. Eur Radiol 30:3306–3309. https://doi.org/10.1007/s00330-020-06731-xCrossRefPubMed

10.

Xiao AT, Tong YX, Gao C (2020) Dynamic profile of RT-PCR findings from 301 COVID-19 patients in Wuhan, China: a descriptive study. J Clin Virol. https://doi.org/10.1016/j.jcv.2020.104346

11.

Bernheim A, Mei X, Huang M et al (2020) Chest CT findings in coronavirus disease-19 (COVID-19): relationship to duration of infection. Radiology 295:685–691. https://doi.org/10.1148/radiol.2020200463CrossRef

12.

Kim H (2020) Outbreak of novel coronavirus (COVID-19): what is the role of radiologists? Eur Radiol 30:3266–3267. https://doi.org/10.1007/s00330-020-06748-2CrossRefPubMed

13.

Wang H, Wei R, Rao G et al (2020) Characteristic CT findings distinguishing 2019 novel coronavirus disease (COVID-19) from influenza pneumonia. Eur Radiol. https://doi.org/10.1007/s00330-020-06880-z

14.

Zhu N, Zhang D, Wang W et al (2020) A novel coronavirus from patients with pneumonia in China, 2019. N Engl J Med 382:727–733. https://doi.org/10.1056/NEJMoa2001017CrossRefPubMedPubMedCentral

15.

Fu F, Lou J, Xi D et al (2020) Chest computed tomography findings of coronavirus disease 2019 (COVID-19) pneumonia. Eur Radiol. https://doi.org/10.1007/s00330-020-06920-8

16.

Duan Y, Zhu Y, Tang L et al (2020) CT features of novel coronavirus pneumonia (COVID-19) in children. Eur Radiol. https://doi.org/10.1007/s00330-020-06860-3

17.

Li L, Qin L, Xu Z et al (2020) Using artificial intelligence to detect COVID-19 and community-acquired pneumonia based on pulmonary CT: evaluation of the diagnostic accuracy. Radiology 296:65–71. https://doi.org/10.1148/radiol.2020200905CrossRef

18.

Fan DP, Zhou T, Ji GP et al (2020) Inf-Net: automatic COVID-19 lung infection segmentation from CT images. IEEE Trans Med Imaging 39:2626–2637. https://doi.org/10.1109/TMI.2020.2996645CrossRefPubMed

19.

Li MD, Arun NT, Gidwani M et al (2020) Automated assessment of COVID-19 pulmonary disease severity on chest radiographs using convolutional Siamese neural networks. Radiol Artif Intell. https://doi.org/10.1148/ryai.2020200079

20.

She Y, Jin Z, Wu J et al (2020) Development and validation of a deep learning model for non-small cell lung cancer survival. JAMA Netw Open. https://doi.org/10.1001/jamanetworkopen.2020.5842

21.

Sim Y, Chung MJ, Kotter E et al (2020) Deep convolutional neural network-based software improves radiologist detection of malignant lung nodules on chest radiographs. Radiology 294:199–209. https://doi.org/10.1148/radiol.2019182465CrossRefPubMed

22.

Wang S, Zhou M, Liu Z et al (2017) Central focused convolutional neural networks: developing data-driven model for lung nodule segmentation. Med Image Anal 40:172–183. https://doi.org/10.1016/j.media.2017.06.014CrossRefPubMedPubMedCentral

23.

Xie Y, Zhang J, Xia Y (2019) Semi-supervised adversarial model for benign-malignant lung nodule classification on chest CT. Med Image Anal 57:237–248. https://doi.org/10.1016/j.media.2019.07.004CrossRefPubMed

24.

Liu L, Dou Q, Chen H et al (2020) Multi-task deep model with margin ranking loss for lung nodule analysis. IEEE Trans Med Imaging 39:718–728. https://doi.org/10.1109/TMI.2019.2934577CrossRefPubMed

25.

Mei X, Lee H, Diao K et al (2020) Artificial intelligence–enabled rapid diagnosis of patients with COVID-19. Nat Med. https://doi.org/10.1038/s41591-020-0931-3

26.

Bai HX, Wang R, Xiong Z et al (2020) AI augmentation of radiologist performance in distinguishing COVID-19 from pneumonia of other. Radiology. https://doi.org/10.1148/radiol.2020201491

27.

Junaid M, Renato P, Salvatore L et al (2020) Initial chest radiographs and artificial intelligence (AI) predict clinical outcomes in COVID-19 patients: analysis of 697 Italian patients. Eur Radiol. https://doi.org/10.1007/s00330-020-07269-8

28.

Ali AA, Acharya UR, Sina H et al (2020) COVIDiag: a clinical CAD system to diagnose COVID-19 pneumonia based on CT findings. Eur Radiol. https://doi.org/10.1007/s00330-020-07087-y

29.

Li L, Qin LX, Xu ZG et al (2020) Artificial intelligence distinguishes COVID-19 from community acquired pneumonia on chest CT. Radiology. https://doi.org/10.1148/radiol.2020200905

30.

Chen LC, Zhu Y, Papandreou G, Schroff F, Adam H (2018) Encoder-decoder with atrous separable convolution for semantic image segmentation. ECCV:833–851. https://doi.org/10.1007/978-3-030-01234-2_49

31.

He KM, Zhang XY, Ren SQ, Sun J (2016) Deep residual learning for image recognition. CVPR:770–778. https://doi.org/10.1109/CVPR.2016.90

32.

Hesamian MH, Jia WJ, He XJ, Kennedy PJ (2019) Atrous convolution for binary semantic segmentation of lung nodule. ICASSP. https://doi.org/10.1109/ICASSP.2019.8682220

33.

Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2018) DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE T Pattern Anal 4:834–848. https://doi.org/10.1109/TPAMI.2017.2699184CrossRef

34.

Kensho H, Hirokatsu K, Yutaka S (2017) Learning spatio-temporal features with 3D residual networks for action recognition. ICCV:3154–3160. https://doi.org/10.1109/ICCVW.2017.373

35.

Muller KR, Smola AJ, Rtsch G, Schlkopf B, Kohlmorgen J, Vapnik V (1997) Predicting time series with support vector machines. ICANN:999–1004. https://doi.org/10.1007/BFb0020283

36.

Vladimir S, Andy L, Christopher TJ, Christopher C, Robert PS, Bradley PF (2003) Random forest: a classification and regression tool for compound classification and QSAR modeling. J Chem Inf Comput Sci:1947–1958. https://doi.org/10.1021/ci034160g

37.

Sun BQ, Feng Y, Mo XN (2020) Kinetics of SARS-CoV-2 specific IgM and IgG responses in COVID-19 patients. Emerg Microbes Infect. https://doi.org/10.1080/22221751.2020.1762515

38.

Zhang ZL, Hou YL, Li DT, Li FZ (2020) Diagnostic efficacy of anti-SARS-CoV-2 IgG/IgM test for COVID-19: a meta-analysis. J Med Virol. https://doi.org/10.1002/jmv.26211

39.

Liang T, Liu Zhe WCC et al (2020) Evolution of CT findings in patients with mild COVID-19 pneumonia. Eur Radiol. https://doi.org/10.1007/s00330-020-06823-8

40.

Qianqian N, Zhi YS, Li Q et al (2020) A deep learning approach to characterize 2019 coronavirus disease (COVID-19) pneumonia in chest CT images. Eur Radiol 30:6517–6527. https://doi.org/10.1007/s00330-020-07044-9CrossRef

41.

Isaac S, Azadeh A, Amirhossein S et al (2020) Ultra-low-dose chest CT imaging of COVID-19 patients using a deep residual neural network. Eur Radiol. https://doi.org/10.1007/s00330-020-07225-6

42.

Jiantao P, Joseph KL, Andriy B et al (2020) Automated quantification of COVID-19 severity and progression using chest CT images. Eur Radiol. https://doi.org/10.1007/s00330-020-07269-8

43.

Tizhoosh HR, Jennifer F (2020) COVID-19, AI enthusiasts, and toy datasets: radiology without radiologists. Eur Radiol. https://doi.org/10.1007/s00330-020-07453-w

44.

Liang WW, Zhang W, Jin B (2018) Learning to detect pathogenic microorganism of community-acquired pneumonia. ACM SIGIR 969-972. https://doi.org/10.1145/3209978.3210112

45.

Zhang L, Zheng Z, Yang L et al (2020) From community-acquired pneumonia to COVID-19: a deep learning–based method for quantitative analysis of COVID-19 on thick-section CT scans. Eur Radiol 30:6828–6837. https://doi.org/10.1007/s00330-020-07042-xCrossRefPubMed

Titel: AI detection of mild COVID-19 pneumonia from chest CT scans
verfasst von: Jin-Cao Yao
Tao Wang
Guang-Hua Hou
Di Ou
Wei Li
Qiao-Dan Zhu
Wen-Cong Chen
Chen Yang
Li-Jing Wang
Li-Ping Wang
Lin-Yin Fan
Kai-Yuan Shi
Jie Zhang
Dong Xu
Ya-Qing Li
Publikationsdatum: 18.03.2021
Verlag: Springer Berlin Heidelberg
Schlagwort: COVID-19
Erschienen in: European Radiology / Ausgabe 9/2021
Print ISSN: 0938-7994
Elektronische ISSN: 1432-1084
DOI: https://doi.org/10.1007/s00330-021-07797-x

Update Radiologie

Bestellen Sie unseren Fach-Newsletter und bleiben Sie gut informiert.

Newsletter bestellen

Springer Medizin

AI detection of mild COVID-19 pneumonia from chest CT scans