CT quantification of pneumonia lesions in early days predicts progression to severe illness in a cohort of COVID-19 patients

Fengjun Liu, Qi Zhang, Chao Huang, Chunzi Shi, Lin Wang, Nannan Shi, Cong Fang, Fei Shan, Xue Mei, Jing Shi, Fengxiang Song, Zhongcheng Yang, Zezhen Ding, Xiaoming Su, Hongzhou Lu, Tongyu Zhu, Zhiyong Zhang, Lei Shi, Yuxin Shi, Fengjun Liu, Qi Zhang, Chao Huang, Chunzi Shi, Lin Wang, Nannan Shi, Cong Fang, Fei Shan, Xue Mei, Jing Shi, Fengxiang Song, Zhongcheng Yang, Zezhen Ding, Xiaoming Su, Hongzhou Lu, Tongyu Zhu, Zhiyong Zhang, Lei Shi, Yuxin Shi

Abstract

Rationale: Some patients with coronavirus disease 2019 (COVID-19) rapidly develop respiratory failure or even die, underscoring the need for early identification of patients at elevated risk of severe illness. This study aims to quantify pneumonia lesions by computed tomography (CT) in the early days to predict progression to severe illness in a cohort of COVID-19 patients. Methods: This retrospective cohort study included confirmed COVID-19 patients. Three quantitative CT features of pneumonia lesions were automatically calculated using artificial intelligence algorithms, representing the percentages of ground-glass opacity volume (PGV), semi-consolidation volume (PSV), and consolidation volume (PCV) in both lungs. CT features, acute physiology and chronic health evaluation II (APACHE-II) score, neutrophil-to-lymphocyte ratio (NLR), and d-dimer, on day 0 (hospital admission) and day 4, were collected to predict the occurrence of severe illness within a 28-day follow-up using both logistic regression and Cox proportional hazard models. Results: We included 134 patients, of whom 19 (14.2%) developed any severe illness. CT features on day 0 and day 4, as well as their changes from day 0 to day 4, showed predictive capability. Changes in CT features from day 0 to day 4 performed the best in the prediction (area under the receiver operating characteristic curve = 0.93, 95% confidence interval [CI] 0.87~0.99; C-index=0.88, 95% CI 0.81~0.95). The hazard ratios of PGV and PCV were 1.39 (95% CI 1.05~1.84, P=0.023) and 1.67 (95% CI 1.17~2.38, P=0.005), respectively. CT features, adjusted for age and gender, on day 4 and in terms of changes from day 0 to day 4 outperformed APACHE-II, NLR, and d-dimer. Conclusions: CT quantification of pneumonia lesions can early and non-invasively predict the progression to severe illness, providing a promising prognostic indicator for clinical management of COVID-19.

Keywords: Artificial intelligence; COVID-19; Chest CT; Retrospective cohort; Severe illness.

Conflict of interest statement

Competing Interests: The authors have declared that no competing interest exists.

© The author(s).

Figures

Figure 1
Figure 1
Flow diagram of the study population.
Figure 2
Figure 2
CT image quantization and analysis with artificial intelligence (AI) system. CT images acquired on the day of admission (day 0, in the lower right panel of the figure denoted as “Previous”) and acquired four (±1) days after admission (day 4, upper right denoted as “Current”) can be compared using histograms (upper left) and AI-derived quantitative features. Here, on day 0, the percentage of ground-glass opacity (GGO) volume, percentage of semi-consolidation volume, and percentage of consolidation volume were 0.7, 0.6 and 0.1, while on day 4, they increased to 10.8, 26.1 and 11.5.
Figure 3
Figure 3
COVID-19 pneumonia lesions detected by the AI system and visualized as pseudo colors. First to third columns: initial CT images; displayed with red pseudo colors; displayed with blue, pink, and red pseudo colors representing ground-glass opacity (GGO), semi-consolidation and consolidation, respectively. Pictures of two patients are illustrated: one was a 38year-old male (A and B), who reached the endpoint of progression to severe illness after 7 days from admission, and the other was a 31-year-old male (C), who did not meet the endpoint during the follow-up and was discharged from the hospital after 13 days from admission. The upper halves of A, B, and C show images on day 0, and the lower halves show images on day 4.

References

    1. Novel CPERE. The epidemiological characteristics of an outbreak of 2019 novel coronavirus diseases (COVID-19) in China. Zhonghua liu xing bing xue za zhi= Zhonghua liuxingbingxue zazhi. 2020;41:145.
    1. WHO. Coronavirus disease 2019 (COVID-19): situation report-79. 2020.
    1. Yang X, Yu Y, Xu J, Shu H, Xia Ja, Liu H, Clinical course and outcomes of critically ill patients with SARS-CoV-2 pneumonia in Wuhan, China: a single-centered, retrospective, observational study. Lancet Respir Med. 2020.
    1. Lipsitch M, Swerdlow DL, Finelli L. Defining the Epidemiology of Covid-19 - Studies Needed. N Engl J Med. 2020.
    1. Wu WH, Niu YY, Zhang CR, Xiao LB, Ye HS, Pan DM. et al. Combined APACH II score and arterial blood lactate clearance rate to predict the prognosis of ARDS patients. Asian Pac J Trop Med. 2012;5:656–60.
    1. Wang Y, Ju M, Chen C, Yang D, Hou D, Tang X. et al. Neutrophil-to-lymphocyte ratio as a prognostic marker in acute respiratory distress syndrome patients: a retrospective study. J Thorac Dis. 2018;10:273–82.
    1. Kumarasamy C, Sabarimurugan S, Madurantakam RM, Lakhotiya K, Samiappan S, Baxi S. et al. Prognostic significance of blood inflammatory biomarkers NLR, PLR, and LMR in cancer-A protocol for systematic review and meta-analysis. Medicine (Baltimore) 2019;98:e14834.
    1. Jiang J, Liu R, Yu X, Yang R, Xu H, Mao Z. et al. The neutrophil-lymphocyte count ratio as a diagnostic marker for bacteraemia: A systematic review and meta-analysis. Am J Emerg Med. 2019;37:1482–9.
    1. Huang NC, Hung YM, Lin SL, Wann SR, Hsu CW, Ger LP. et al. Further evidence of the usefulness of Acute Physiology and Chronic Health Evaluation II scoring system in acute paraquat poisoning. Clin Toxicol (Phila) 2006;44:99–102.
    1. Nishiyama A, Kawata N, Yokota H, Sugiura T, Matsumura Y, Higashide T. et al. A predictive factor for patients with acute respiratory distress syndrome: CT lung volumetry of the well-aerated region as an automated method. Eur J Radiol. 2020;122:108748.
    1. Tai D, Lew T, Loo S, Earnest A, Chen M. Critically ill patients with severe acute respiratory syndrome (SARS) in a designated national SARS ICU: clinical features and predictors for mortality. Critical Care. 2004;8:P38.
    1. Zhou F, Yu T, Du R, Fan G, Liu Y, Liu Z, Clinical course and risk factors for mortality of adult inpatients with COVID-19 in Wuhan, China: a retrospective cohort study. The Lancet. 2020.
    1. Wu C, Chen X, Cai Y, Xia J, Zhou X, Xu S, Risk Factors Associated With Acute Respiratory Distress Syndrome and Death in Patients With Coronavirus Disease 2019 Pneumonia in Wuhan, China. JAMA Intern Med. 2020.
    1. Pan F, Ye T, Sun P, Gui S, Liang B, Li L, Time Course of Lung Changes On Chest CT During Recovery From 2019 Novel Coronavirus (COVID-19) Pneumonia. Radiology. 2020: 200370.
    1. Song F, Shi N, Shan F, Zhang Z, Shen J, Lu H, Emerging Coronavirus 2019-nCoV Pneumonia. Radiology. 2020: 200274.
    1. Zhao W, Zhong Z, Xie X, Yu Q, Liu J. CT Scans of Patients with 2019 Novel Coronavirus (COVID-19) Pneumonia. Theranostics. 2020;10:4606–13.
    1. China NHC. Diagnosis and treatment protocols of pneumonia caused by novel coronavirus (trial version 6) 2020.
    1. Ardila D, Kiraly AP, Bharadwaj S, Choi B, Reicher JJ, Peng L. et al. End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography. Nat Med. 2019;25:954–61.
    1. Huang P, Lin CT, Li Y, Tammemagi MC, Brock MV, Atkar-Khattra S. et al. Prediction of lung cancer risk at follow-up screening with low-dose CT: a training and validation study of a deep learning method. Lancet Digit Health. 2019;1:e353–e62.
    1. Pickhardt PJ, Graffy PM, Zea R, Lee SJ, Liu J, Sandfort V, Automated CT biomarkers for opportunistic prediction of future cardiovascular events and mortality in an asymptomatic screening population: a retrospective cohort study. Lancet Digit Health. 2020.
    1. Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. International Conference on Medical image computing and computer-assisted intervention: Springer. 2015. p. 234-41.
    1. Wang S, Zhou M, Liu Z, Liu Z, Gu D, Zang Y. et al. Central focused convolutional neural networks: Developing a data-driven model for lung nodule segmentation. Med Image Anal. 2017;40:172–83.
    1. Suzuki K, Kusumoto M, Watanabe S, Tsuchiya R, Asamura H. Radiologic classification of small adenocarcinoma of the lung: radiologic-pathologic correlation and its prognostic impact. Ann Thorac Surg. 2006;81:413–9.
    1. Metlay JP, Waterer GW, Long AC, Anzueto A, Brozek J, Crothers K. et al. Diagnosis and Treatment of Adults with Community-acquired Pneumonia. An Official Clinical Practice Guideline of the American Thoracic Society and Infectious Diseases Society of America. Am J Respir Crit Care Med. 2019;200:e45–e67.
    1. Huang Z, Fu Z, Huang W, Huang K. Prognostic value of neutrophil-to-lymphocyte ratio in sepsis: A meta-analysis. Am J Emerg Med. 2019.
    1. Wang S, Shi J, Ye Z, Dong D, Yu D, Zhou M. et al. Predicting EGFR mutation status in lung adenocarcinoma on computed tomography image using deep learning. Eur Respir J. 2019;53:1800986.
    1. Park H, Lim Y, Ko ES, Cho HH, Lee JE, Han BK. et al. Radiomics Signature on Magnetic Resonance Imaging: Association with Disease-Free Survival in Patients with Invasive Breast Cancer. Clin Cancer Res. 2018;24:4705–14.

Source: PubMed

3
구독하다