A novel CT-based radiomics in the distinction of severity of coronavirus disease 2019 (COVID-19) pneumonia
Abstract Background Convenient and precise assessment of the severity in coronavirus disease 2019 (COVID-19) contributes to the timely patient treatment and prognosis improvement. We aimed to evaluate the ability of CT-based radiomics nomogram in discriminating the severity of patients with COVID-19...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2021-06-01
|
| Series: | BMC Infectious Diseases |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12879-021-06331-0 |
| _version_ | 1818825213606887424 |
|---|---|
| author | Zongyu Xie Haitao Sun Jian Wang He Xu Shuhua Li Cancan Zhao Yuqing Gao Xiaolei Wang Tongtong Zhao Shaofeng Duan Chunhong Hu Weiqun Ao |
| author_facet | Zongyu Xie Haitao Sun Jian Wang He Xu Shuhua Li Cancan Zhao Yuqing Gao Xiaolei Wang Tongtong Zhao Shaofeng Duan Chunhong Hu Weiqun Ao |
| author_sort | Zongyu Xie |
| collection | DOAJ |
| description | Abstract Background Convenient and precise assessment of the severity in coronavirus disease 2019 (COVID-19) contributes to the timely patient treatment and prognosis improvement. We aimed to evaluate the ability of CT-based radiomics nomogram in discriminating the severity of patients with COVID-19 Pneumonia. Methods A total of 150 patients (training cohort n = 105; test cohort n = 45) with COVID-19 confirmed by reverse transcription polymerase chain reaction (RT-PCR) test were enrolled. Two feature selection methods, Max-Relevance and Min-Redundancy (mRMR) and least absolute shrinkage and selection operator (LASSO), were used to extract features from CT images and construct model. A total of 30 radiomic features were finally retained. Rad-score was calculated by summing the selected features weighted by their coefficients. The radiomics nomogram incorporating clinical-radiological features was eventually constructed by multivariate regression analysis. Nomogram, calibration, and decision-curve analysis were all assessed. Results In both cohorts, 40 patients with COVID-19 pneumonia were severe and 110 patients were non-severe. By combining the 30 radiomic features extracted from CT images, the radiomics signature showed high discrimination between severe and non-severe patients in the training set [Area Under the Curve (AUC), 0.857; 95% confidence interval (CI), 0.775–0.918] and the test set (AUC, 0.867; 95% CI, 0.732–949). The final combined model that integrated age, comorbidity, CT scores, number of lesions, ground glass opacity (GGO) with consolidation, and radiomics signature, improved the AUC to 0.952 in the training cohort and 0.98 in the test cohort. The nomogram based on the combined model similarly exhibited excellent discrimination performance in both training and test cohorts. Conclusions The developed model based on a radiomics signature derived from CT images can be a reliable marker for discriminating the severity of COVID-19 pneumonia. |
| first_indexed | 2024-12-19T00:08:12Z |
| format | Article |
| id | doaj.art-08007fd1a1b341b1a75f68754f46d919 |
| institution | Directory Open Access Journal |
| issn | 1471-2334 |
| language | English |
| last_indexed | 2024-12-19T00:08:12Z |
| publishDate | 2021-06-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Infectious Diseases |
| spelling | doaj.art-08007fd1a1b341b1a75f68754f46d9192022-12-21T20:46:05ZengBMCBMC Infectious Diseases1471-23342021-06-0121111110.1186/s12879-021-06331-0A novel CT-based radiomics in the distinction of severity of coronavirus disease 2019 (COVID-19) pneumoniaZongyu Xie0Haitao Sun1Jian Wang2He Xu3Shuhua Li4Cancan Zhao5Yuqing Gao6Xiaolei Wang7Tongtong Zhao8Shaofeng Duan9Chunhong Hu10Weiqun Ao11Department of Radiology, The First Affiliated Hospital of Bengbu Medical CollegeShanghai Institute of Medical Imaging, and Department of Interventional Radiology, Zhongshan Hospital, Fudan UniversityDepartment of Radiology, Tongde Hospital of Zhejiang ProvinceDepartment of Radiology, The First Affiliated Hospital of Bengbu Medical CollegeDepartment of Radiology, The First Affiliated Hospital of Bengbu Medical CollegeDepartment of Radiology, The First Affiliated Hospital of Bengbu Medical CollegeDepartment of Radiology, The First Affiliated Hospital of Bengbu Medical CollegeDepartment of Radiology, The First Affiliated Hospital of Bengbu Medical CollegeDepartment of Radiology, Fuyang Second People’s HospitalGE Healthcare China, Pudong new townDepartment of Radiology, The First Affiliated Hospital of Soochow UniversityDepartment of Radiology, Tongde Hospital of Zhejiang ProvinceAbstract Background Convenient and precise assessment of the severity in coronavirus disease 2019 (COVID-19) contributes to the timely patient treatment and prognosis improvement. We aimed to evaluate the ability of CT-based radiomics nomogram in discriminating the severity of patients with COVID-19 Pneumonia. Methods A total of 150 patients (training cohort n = 105; test cohort n = 45) with COVID-19 confirmed by reverse transcription polymerase chain reaction (RT-PCR) test were enrolled. Two feature selection methods, Max-Relevance and Min-Redundancy (mRMR) and least absolute shrinkage and selection operator (LASSO), were used to extract features from CT images and construct model. A total of 30 radiomic features were finally retained. Rad-score was calculated by summing the selected features weighted by their coefficients. The radiomics nomogram incorporating clinical-radiological features was eventually constructed by multivariate regression analysis. Nomogram, calibration, and decision-curve analysis were all assessed. Results In both cohorts, 40 patients with COVID-19 pneumonia were severe and 110 patients were non-severe. By combining the 30 radiomic features extracted from CT images, the radiomics signature showed high discrimination between severe and non-severe patients in the training set [Area Under the Curve (AUC), 0.857; 95% confidence interval (CI), 0.775–0.918] and the test set (AUC, 0.867; 95% CI, 0.732–949). The final combined model that integrated age, comorbidity, CT scores, number of lesions, ground glass opacity (GGO) with consolidation, and radiomics signature, improved the AUC to 0.952 in the training cohort and 0.98 in the test cohort. The nomogram based on the combined model similarly exhibited excellent discrimination performance in both training and test cohorts. Conclusions The developed model based on a radiomics signature derived from CT images can be a reliable marker for discriminating the severity of COVID-19 pneumonia.https://doi.org/10.1186/s12879-021-06331-0COVID-19RadiomicsTomographyX-ray computedNomogram |
| spellingShingle | Zongyu Xie Haitao Sun Jian Wang He Xu Shuhua Li Cancan Zhao Yuqing Gao Xiaolei Wang Tongtong Zhao Shaofeng Duan Chunhong Hu Weiqun Ao A novel CT-based radiomics in the distinction of severity of coronavirus disease 2019 (COVID-19) pneumonia BMC Infectious Diseases COVID-19 Radiomics Tomography X-ray computed Nomogram |
| title | A novel CT-based radiomics in the distinction of severity of coronavirus disease 2019 (COVID-19) pneumonia |
| title_full | A novel CT-based radiomics in the distinction of severity of coronavirus disease 2019 (COVID-19) pneumonia |
| title_fullStr | A novel CT-based radiomics in the distinction of severity of coronavirus disease 2019 (COVID-19) pneumonia |
| title_full_unstemmed | A novel CT-based radiomics in the distinction of severity of coronavirus disease 2019 (COVID-19) pneumonia |
| title_short | A novel CT-based radiomics in the distinction of severity of coronavirus disease 2019 (COVID-19) pneumonia |
| title_sort | novel ct based radiomics in the distinction of severity of coronavirus disease 2019 covid 19 pneumonia |
| topic | COVID-19 Radiomics Tomography X-ray computed Nomogram |
| url | https://doi.org/10.1186/s12879-021-06331-0 |
| work_keys_str_mv | AT zongyuxie anovelctbasedradiomicsinthedistinctionofseverityofcoronavirusdisease2019covid19pneumonia AT haitaosun anovelctbasedradiomicsinthedistinctionofseverityofcoronavirusdisease2019covid19pneumonia AT jianwang anovelctbasedradiomicsinthedistinctionofseverityofcoronavirusdisease2019covid19pneumonia AT hexu anovelctbasedradiomicsinthedistinctionofseverityofcoronavirusdisease2019covid19pneumonia AT shuhuali anovelctbasedradiomicsinthedistinctionofseverityofcoronavirusdisease2019covid19pneumonia AT cancanzhao anovelctbasedradiomicsinthedistinctionofseverityofcoronavirusdisease2019covid19pneumonia AT yuqinggao anovelctbasedradiomicsinthedistinctionofseverityofcoronavirusdisease2019covid19pneumonia AT xiaoleiwang anovelctbasedradiomicsinthedistinctionofseverityofcoronavirusdisease2019covid19pneumonia AT tongtongzhao anovelctbasedradiomicsinthedistinctionofseverityofcoronavirusdisease2019covid19pneumonia AT shaofengduan anovelctbasedradiomicsinthedistinctionofseverityofcoronavirusdisease2019covid19pneumonia AT chunhonghu anovelctbasedradiomicsinthedistinctionofseverityofcoronavirusdisease2019covid19pneumonia AT weiqunao anovelctbasedradiomicsinthedistinctionofseverityofcoronavirusdisease2019covid19pneumonia AT zongyuxie novelctbasedradiomicsinthedistinctionofseverityofcoronavirusdisease2019covid19pneumonia AT haitaosun novelctbasedradiomicsinthedistinctionofseverityofcoronavirusdisease2019covid19pneumonia AT jianwang novelctbasedradiomicsinthedistinctionofseverityofcoronavirusdisease2019covid19pneumonia AT hexu novelctbasedradiomicsinthedistinctionofseverityofcoronavirusdisease2019covid19pneumonia AT shuhuali novelctbasedradiomicsinthedistinctionofseverityofcoronavirusdisease2019covid19pneumonia AT cancanzhao novelctbasedradiomicsinthedistinctionofseverityofcoronavirusdisease2019covid19pneumonia AT yuqinggao novelctbasedradiomicsinthedistinctionofseverityofcoronavirusdisease2019covid19pneumonia AT xiaoleiwang novelctbasedradiomicsinthedistinctionofseverityofcoronavirusdisease2019covid19pneumonia AT tongtongzhao novelctbasedradiomicsinthedistinctionofseverityofcoronavirusdisease2019covid19pneumonia AT shaofengduan novelctbasedradiomicsinthedistinctionofseverityofcoronavirusdisease2019covid19pneumonia AT chunhonghu novelctbasedradiomicsinthedistinctionofseverityofcoronavirusdisease2019covid19pneumonia AT weiqunao novelctbasedradiomicsinthedistinctionofseverityofcoronavirusdisease2019covid19pneumonia |