tetano
Editor, Senior Moderator
Eur J Radiol
. 2021 Jan 15;136:109552.
doi: 10.1016/j.ejrad.2021.109552. Online ahead of print.
Multi-classifier-based identification of COVID-19 from chest computed tomography using generalizable and interpretable radiomics features
Lu Wang[SUP] 1 [/SUP], Brendan Kelly[SUP] 2 [/SUP], Edward H Lee[SUP] 2 [/SUP], Hongmei Wang[SUP] 3 [/SUP], Jimmy Zheng[SUP] 2 [/SUP], Wei Zhang[SUP] 4 [/SUP], Safwan Halabi[SUP] 2 [/SUP], Jining Liu[SUP] 5 [/SUP], Yulong Tian[SUP] 6 [/SUP], Baoqin Han[SUP] 6 [/SUP], Chuanbin Huang[SUP] 6 [/SUP], Kristen W Yeom[SUP] 2 [/SUP], Kexue Deng[SUP] 3 [/SUP], Jiangdian Song[SUP] 7 [/SUP]
Affiliations
Abstract
Purpose: To investigate the efficacy of radiomics in diagnosing patients with coronavirus disease (COVID-19) and other types of viral pneumonia with clinical symptoms and CT signs similar to those of COVID-19.
Methods: Between 18 January 2020 and 20 May 2020, 110 SARS-CoV-2 positive and 108 SARS-CoV-2 negative patients were retrospectively recruited from three hospitals based on the inclusion criteria. Manual segmentation of pneumonia lesions on CT scans was performed by four radiologists. The latest version of Pyradiomics was used for feature extraction. Four classifiers (linear classifier, k-nearest neighbour, least absolute shrinkage and selection operator [LASSO], and random forest) were used to differentiate SARS-CoV-2 positive and SARS-CoV-2 negative patients. Comparison of the performance of the classifiers and radiologists was evaluated by ROC curve and Kappa score.
Results: We manually segmented 16,053 CT slices, comprising 32,625 pneumonia lesions, from the CT scans of all patients. Using Pyradiomics, 120 radiomic features were extracted from each image. The key radiomic features screened by different classifiers varied and lead to significant differences in classification accuracy. The LASSO achieved the best performance (sensitivity: 72.2%, specificity: 75.1%, and AUC: 0.81) on the external validation dataset and attained excellent agreement (Kappa score: 0.89) with radiologists (average sensitivity: 75.6%, specificity: 78.2%, and AUC: 0.81). All classifiers indicated that "Original_Firstorder_RootMeanSquared" and "Original_Firstorder_Uniformity" were significant features for this task.
Conclusions: We identified radiomic features that were significantly associated with the classification of COVID-19 pneumonia using multiple classifiers. The quantifiable interpretation of the differences in features between the two groups extends our understanding of CT imaging characteristics of COVID-19 pneumonia.
Keywords: Coronavirus infections; Machine learning; Pneumonia; Radiology; Tomography, X-Ray computed.
. 2021 Jan 15;136:109552.
doi: 10.1016/j.ejrad.2021.109552. Online ahead of print.
Multi-classifier-based identification of COVID-19 from chest computed tomography using generalizable and interpretable radiomics features
Lu Wang[SUP] 1 [/SUP], Brendan Kelly[SUP] 2 [/SUP], Edward H Lee[SUP] 2 [/SUP], Hongmei Wang[SUP] 3 [/SUP], Jimmy Zheng[SUP] 2 [/SUP], Wei Zhang[SUP] 4 [/SUP], Safwan Halabi[SUP] 2 [/SUP], Jining Liu[SUP] 5 [/SUP], Yulong Tian[SUP] 6 [/SUP], Baoqin Han[SUP] 6 [/SUP], Chuanbin Huang[SUP] 6 [/SUP], Kristen W Yeom[SUP] 2 [/SUP], Kexue Deng[SUP] 3 [/SUP], Jiangdian Song[SUP] 7 [/SUP]
Affiliations
- PMID: 33497881
- DOI: 10.1016/j.ejrad.2021.109552
Abstract
Purpose: To investigate the efficacy of radiomics in diagnosing patients with coronavirus disease (COVID-19) and other types of viral pneumonia with clinical symptoms and CT signs similar to those of COVID-19.
Methods: Between 18 January 2020 and 20 May 2020, 110 SARS-CoV-2 positive and 108 SARS-CoV-2 negative patients were retrospectively recruited from three hospitals based on the inclusion criteria. Manual segmentation of pneumonia lesions on CT scans was performed by four radiologists. The latest version of Pyradiomics was used for feature extraction. Four classifiers (linear classifier, k-nearest neighbour, least absolute shrinkage and selection operator [LASSO], and random forest) were used to differentiate SARS-CoV-2 positive and SARS-CoV-2 negative patients. Comparison of the performance of the classifiers and radiologists was evaluated by ROC curve and Kappa score.
Results: We manually segmented 16,053 CT slices, comprising 32,625 pneumonia lesions, from the CT scans of all patients. Using Pyradiomics, 120 radiomic features were extracted from each image. The key radiomic features screened by different classifiers varied and lead to significant differences in classification accuracy. The LASSO achieved the best performance (sensitivity: 72.2%, specificity: 75.1%, and AUC: 0.81) on the external validation dataset and attained excellent agreement (Kappa score: 0.89) with radiologists (average sensitivity: 75.6%, specificity: 78.2%, and AUC: 0.81). All classifiers indicated that "Original_Firstorder_RootMeanSquared" and "Original_Firstorder_Uniformity" were significant features for this task.
Conclusions: We identified radiomic features that were significantly associated with the classification of COVID-19 pneumonia using multiple classifiers. The quantifiable interpretation of the differences in features between the two groups extends our understanding of CT imaging characteristics of COVID-19 pneumonia.
Keywords: Coronavirus infections; Machine learning; Pneumonia; Radiology; Tomography, X-Ray computed.