Tags

Type your tag names separated by a space and hit enter

A deep learning approach to characterize 2019 coronavirus disease (COVID-19) pneumonia in chest CT images.
Eur Radiol. 2020 Dec; 30(12):6517-6527.ER

Abstract

OBJECTIVES

To utilize a deep learning model for automatic detection of abnormalities in chest CT images from COVID-19 patients and compare its quantitative determination performance with radiological residents.

METHODS

A deep learning algorithm consisted of lesion detection, segmentation, and location was trained and validated in 14,435 participants with chest CT images and definite pathogen diagnosis. The algorithm was tested in a non-overlapping dataset of 96 confirmed COVID-19 patients in three hospitals across China during the outbreak. Quantitative detection performance of the model was compared with three radiological residents with two experienced radiologists' reading reports as reference standard by assessing the accuracy, sensitivity, specificity, and F1 score.

RESULTS

Of 96 patients, 88 had pneumonia lesions on CT images and 8 had no abnormities on CT images. For per-patient basis, the algorithm showed superior sensitivity of 1.00 (95% confidence interval (CI) 0.95, 1.00) and F1 score of 0.97 in detecting lesions from CT images of COVID-19 pneumonia patients. While for per-lung lobe basis, the algorithm achieved a sensitivity of 0.96 (95% CI 0.94, 0.98) and a slightly inferior F1 score of 0.86. The median volume of lesions calculated by algorithm was 40.10 cm3. An average running speed of 20.3 s ± 5.8 per case demonstrated the algorithm was much faster than the residents in assessing CT images (all p < 0.017). The deep learning algorithm can also assist radiologists make quicker diagnosis (all p < 0.0001) with superior diagnostic performance.

CONCLUSIONS

The algorithm showed excellent performance in detecting COVID-19 pneumonia on chest CT images compared with resident radiologists.

KEY POINTS

• The higher sensitivity of deep learning model in detecting COVID-19 pneumonia were found compared with radiological residents on a per-lobe and per-patient basis. • The deep learning model improves diagnosis efficiency by shortening processing time. • The deep learning model can automatically calculate the volume of the lesions and whole lung.

Authors+Show Affiliations

Department of Medical Imaging, Jinling Hospital, Medical School of Nanjing University, Nanjing, 210002, Jiangsu, China.Department of Medical Imaging, Jinling Hospital, Medical School of Nanjing University, Nanjing, 210002, Jiangsu, China.Department of Medical Imaging, Jinling Hospital, Medical School of Nanjing University, Nanjing, 210002, Jiangsu, China.Department of Medical Imaging, Taihe Hospital, Shiyan, 442008, Hubei, China.Department of Medical Imaging, Wuhan First Hospital, Wuhan, 430022, Hubei, China.Department of Medical Imaging, Jinling Hospital, Medical School of Nanjing University, Nanjing, 210002, Jiangsu, China.Department of Medical Imaging, Jinling Hospital, Medical School of Nanjing University, Nanjing, 210002, Jiangsu, China.Department of Medical Imaging, Jinling Hospital, Medical School of Nanjing University, Nanjing, 210002, Jiangsu, China.Department of Medical Imaging, Jinling Hospital, Medical School of Nanjing University, Nanjing, 210002, Jiangsu, China.Deepwise AI Lab, Beijing, 100080, China.School of Electronics Engineering and Computer Science, Peking University, Beijing, 10080, China.Department of Computer Science, The University of Hong Kong, Pok Fu Lam, Hong Kong.Department of Medical Imaging, Jinling Hospital, Medical School of Nanjing University, Nanjing, 210002, Jiangsu, China.Department of Medical Imaging, Jinling Hospital, Medical School of Nanjing University, Nanjing, 210002, Jiangsu, China. kevinzhlj@163.com. Department of Medical Imaging, Medical Imaging Center, Nanjing Clinical School, Southern Medical University, 305 Zhongshan East Road, Xuanwu District, Nanjing, 210002, Jiangsu, China. kevinzhlj@163.com.

Pub Type(s)

Comparative Study
Journal Article
Multicenter Study

Language

eng

PubMed ID

32617690

Citation

Ni, Qianqian, et al. "A Deep Learning Approach to Characterize 2019 Coronavirus Disease (COVID-19) Pneumonia in Chest CT Images." European Radiology, vol. 30, no. 12, 2020, pp. 6517-6527.
Ni Q, Sun ZY, Qi L, et al. A deep learning approach to characterize 2019 coronavirus disease (COVID-19) pneumonia in chest CT images. Eur Radiol. 2020;30(12):6517-6527.
Ni, Q., Sun, Z. Y., Qi, L., Chen, W., Yang, Y., Wang, L., Zhang, X., Yang, L., Fang, Y., Xing, Z., Zhou, Z., Yu, Y., Lu, G. M., & Zhang, L. J. (2020). A deep learning approach to characterize 2019 coronavirus disease (COVID-19) pneumonia in chest CT images. European Radiology, 30(12), 6517-6527. https://doi.org/10.1007/s00330-020-07044-9
Ni Q, et al. A Deep Learning Approach to Characterize 2019 Coronavirus Disease (COVID-19) Pneumonia in Chest CT Images. Eur Radiol. 2020;30(12):6517-6527. PubMed PMID: 32617690.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - A deep learning approach to characterize 2019 coronavirus disease (COVID-19) pneumonia in chest CT images. AU - Ni,Qianqian, AU - Sun,Zhi Yuan, AU - Qi,Li, AU - Chen,Wen, AU - Yang,Yi, AU - Wang,Li, AU - Zhang,Xinyuan, AU - Yang,Liu, AU - Fang,Yi, AU - Xing,Zijian, AU - Zhou,Zhen, AU - Yu,Yizhou, AU - Lu,Guang Ming, AU - Zhang,Long Jiang, Y1 - 2020/07/02/ PY - 2020/03/04/received PY - 2020/06/22/accepted PY - 2020/06/06/revised PY - 2020/7/4/pubmed PY - 2020/11/11/medline PY - 2020/7/4/entrez KW - COVID-19 KW - Deep learning KW - Diagnosis KW - Multidetector computed tomography KW - Pneumonia SP - 6517 EP - 6527 JF - European radiology JO - Eur Radiol VL - 30 IS - 12 N2 - OBJECTIVES: To utilize a deep learning model for automatic detection of abnormalities in chest CT images from COVID-19 patients and compare its quantitative determination performance with radiological residents. METHODS: A deep learning algorithm consisted of lesion detection, segmentation, and location was trained and validated in 14,435 participants with chest CT images and definite pathogen diagnosis. The algorithm was tested in a non-overlapping dataset of 96 confirmed COVID-19 patients in three hospitals across China during the outbreak. Quantitative detection performance of the model was compared with three radiological residents with two experienced radiologists' reading reports as reference standard by assessing the accuracy, sensitivity, specificity, and F1 score. RESULTS: Of 96 patients, 88 had pneumonia lesions on CT images and 8 had no abnormities on CT images. For per-patient basis, the algorithm showed superior sensitivity of 1.00 (95% confidence interval (CI) 0.95, 1.00) and F1 score of 0.97 in detecting lesions from CT images of COVID-19 pneumonia patients. While for per-lung lobe basis, the algorithm achieved a sensitivity of 0.96 (95% CI 0.94, 0.98) and a slightly inferior F1 score of 0.86. The median volume of lesions calculated by algorithm was 40.10 cm3. An average running speed of 20.3 s ± 5.8 per case demonstrated the algorithm was much faster than the residents in assessing CT images (all p < 0.017). The deep learning algorithm can also assist radiologists make quicker diagnosis (all p < 0.0001) with superior diagnostic performance. CONCLUSIONS: The algorithm showed excellent performance in detecting COVID-19 pneumonia on chest CT images compared with resident radiologists. KEY POINTS: • The higher sensitivity of deep learning model in detecting COVID-19 pneumonia were found compared with radiological residents on a per-lobe and per-patient basis. • The deep learning model improves diagnosis efficiency by shortening processing time. • The deep learning model can automatically calculate the volume of the lesions and whole lung. SN - 1432-1084 UR - https://www.unboundmedicine.com/medline/citation/32617690/A_deep_learning_approach_to_characterize_2019_coronavirus_disease__COVID_19__pneumonia_in_chest_CT_images_ L2 - https://dx.doi.org/10.1007/s00330-020-07044-9 DB - PRIME DP - Unbound Medicine ER -