Rapid identification of COVID-19 severity in CT scans through classification of deep features

Zekuan Yu, Xiaohu Li, Haitao Sun, Jian Wang, Tongtong Zhao, Hongyi Chen, Yichuan Ma, Shujin Zhu, Zongyu Xie, Zekuan Yu, Xiaohu Li, Haitao Sun, Jian Wang, Tongtong Zhao, Hongyi Chen, Yichuan Ma, Shujin Zhu, Zongyu Xie

Abstract

Background: Chest CT is used for the assessment of the severity of patients infected with novel coronavirus 2019 (COVID-19). We collected chest CT scans of 202 patients diagnosed with the COVID-19, and try to develop a rapid, accurate and automatic tool for severity screening follow-up therapeutic treatment.

Methods: A total of 729 2D axial plan slices with 246 severe cases and 483 non-severe cases were employed in this study. By taking the advantages of the pre-trained deep neural network, four pre-trained off-the-shelf deep models (Inception-V3, ResNet-50, ResNet-101, DenseNet-201) were exploited to extract the features from these CT scans. These features are then fed to multiple classifiers (linear discriminant, linear SVM, cubic SVM, KNN and Adaboost decision tree) to identify the severe and non-severe COVID-19 cases. Three validation strategies (holdout validation, tenfold cross-validation and leave-one-out) are employed to validate the feasibility of proposed pipelines.

Results and conclusion: The experimental results demonstrate that classification of the features from pre-trained deep models shows the promising application in COVID-19 severity screening, whereas the DenseNet-201 with cubic SVM model achieved the best performance. Specifically, it achieved the highest severity classification accuracy of 95.20% and 95.34% for tenfold cross-validation and leave-one-out, respectively. The established pipeline was able to achieve a rapid and accurate identification of the severity of COVID-19. This may assist the physicians to make more efficient and reliable decisions.

Keywords: COVID-19; Coronavirus; Deep learning; Pneumonia; Tomography.

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Fig. 1
Fig. 1
The performance of classified deep features based on holdout validation: a The accuracy and AUC performance; b The AUC performance; c The sensitivity performance; (d) The specificity performance
Fig. 2
Fig. 2
Two sample attention maps from the last ‘pooling’ layer in DenseNet-201. Whereas the attention seems to be generally rather non-exclusive, it may sometimes not contribute to human interpretation. Restricting deep feature learning or extraction to the lung regions is expected to improve the interpretability of the attention maps
Fig. 3
Fig. 3
CT and DR images of a 76-year-old male with fever, cough and expectoration: a Chest CT scan. b–d Follow-up DR images
Fig. 4
Fig. 4
Sample CT scans of COVID-19-infected patients: a non-severe cases; b severe cases
Fig. 5
Fig. 5
Typical examples for severe and non-severe CT chest slides in axial, sagittal and coronal views: a non-severe cases; b severe cases
Fig. 6
Fig. 6
The pipeline of the proposed method

References

    1. Chan JF-W, Yuan S, Kok K-H, To KK-W, Chu H, Yang J, Xing F, Liu J, Yip CC-Y, Yip CC-Y, Poon RW-S. A familial cluster of pneumonia associated with the 2019 novel coronavirus indicating person-to-person transmission: a study of a family cluster. Lancet. 2020;395(10223):514–523. doi: 10.1016/S0140-6736(20)30154-9.
    1. Li Q, Guan X, Wu P, Wang X, Zhou L, Tong Y, Ren R, Leung KS, Lau EH, Wong JY. Early transmission dynamics in Wuhan, China, of novel coronavirus–infected pneumonia. N Engl J Med. 2020;328(13):1109–1207.
    1. Rothe C, Schunk M, Sothmann P, Bretzel G, Froeschl G, Wallrauch C, Zimmer T, Thiel V, Janke C, Guggemos W. Transmission of 2019-nCoV infection from an asymptomatic contact in Germany. N Engl J Med. 2020;328(10):970–971. doi: 10.1056/NEJMc2001468.
    1. Giovanetti M, Benvenuto D, Angeletti S, Ciccozzi M. The first two cases of 2019-nCoV in Italy: where they come from? J Med Virol. 2020;92(5):518–521. doi: 10.1002/jmv.25699.
    1. .
    1. Wang S, Kang B, Ma J, Zeng X, Xiao M, Guo J, Cai M, Yang J, Li Y, Meng X. A deep learning algorithm using CT images to screen for Corona Virus Disease (COVID-19). medRxiv. 2020.
    1. Ai T, Yang Z, Hou H, Zhan C, Chen C, Lv W, Tao Q, Sun Z, Xia L. Correlation of Chest CT and RT-PCR Testing in Coronavirus Disease 2019 (COVID-19) in China: a Report of 1014 Cases. Radiology. 2020;200642:3.
    1. Bernheim A, Mei X, Huang M, Yang Y, Fayad ZA, Zhang N, Diao K, Lin B, Zhu X, Li K. Chest CT Findings in Coronavirus Disease-19 (COVID-19): relationship to duration of infection. Radiology. 2020;3:200463. doi: 10.1148/radiol.2020200463.
    1. Pan F, Ye T, Sun P, Gui S, Liang B, Li L, Zheng D, Wang J, Hesketh RL, Yang L. Time course of lung changes on chest CT during recovery from 2019 novel coronavirus (COVID-19) pneumonia. Radiology. 2020;2020:200370.
    1. Liu T, Huang P, Liu H, Huang L, Lei M, Xu W, Hu X, Chen J, Liu B. Spectrum of chest CT findings in a familial cluster of COVID-19 infection. Radiology. 2020;2(1):e200025.
    1. Ng M-Y, Lee EY, Yang J, Yang F, Li X, Wang H, Lui MM-S, Leung B, Khong P-L. Imaging profile of the COVID-19 infection: radiologic findings and literature review. Radiology. 2020;2(1):e200034.
    1. Li L, Qin L, Xu Z, Yin Y, Wang X, Kong B, Bai J, Lu Y, Fang Z, Song QJR. Artificial intelligence distinguishes COVID-19 from community acquired pneumonia on chest CT. Radiology. 2020;3:200905.
    1. Song Y, Zheng S, Li L, Zhang X, Zhang X, Huang Z, Chen J, Zhao H, Jie Y, Wang R. Deep learning Enables Accurate Diagnosis of Novel Coronavirus (COVID-19) with CT images. medRxiv. 2020.
    1. Li K, Wu J, Wu F, Guo D, Chen L, Fang Z, Li C. The clinical and chest CT features associated with severe and critical COVID-19 pneumonia. Invest Radiol. 2020;55(6):327–331. doi: 10.1097/RLI.0000000000000672.
    1. Xu X, Jiang X, Ma C, Du P, Li X, Lv S, Yu L, Chen Y, Su J, Lang G. Deep learning system to screen coronavirus disease 2019 pneumonia. arXiv preprint . 2020.
    1. Gozes O, Frid-Adar M, Greenspan H, Browning PD, Zhang H, Ji W, Bernheim A, Siegel E. Rapid AI Development Cycle for the Coronavirus (COVID-19) Pandemic: Initial Results for Automated Detection & Patient Monitoring using Deep Learning CT Image Analysis. arXiv preprint . 2020.
    1. Shan F, Gao Y, Wang J, Shi W, Shi N, Han M, Xue Z, Shen D, Shi Y. Lung Infection Quantification of COVID-19 in CT Images with Deep Learning. arXiv preprint . 2020.
    1. Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2016. p. 2818–26.
    1. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2016. p. 770–8.
    1. Huang G, Liu Z, Van Der Maaten L, Weinberger KQ. Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2017. p. 4700–8.
    1. .
    1. Zheng C, Deng X, Fu Q, Zhou Q, Feng J, Ma H, Liu W, Wang XJM. Deep learning-based detection for COVID-19 from chest CT using weak label. medRxiv. 2020 doi: 10.1101/2020.03.12.20027185.
    1. Tang Z, Zhao W, Xie X, Zhong Z, Shi F, Liu J, Shen D. Severity Assessment of Coronavirus Disease 2019 (COVID-19) Using Quantitative Features from Chest CT Images. arXiv preprint . 2020.

Source: PubMed

Sponsorer og samarbeidspartnere

Medisinsk tilstand

Legemiddelintervensjoner

3
Abonnere