Dataset Information

Multi-classifier-based identification of COVID-19 from chest computed tomography using generalizable and interpretable radiomics features.

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.

SUBMITTER: Wang L

PROVIDER: S-EPMC7810032 | biostudies-literature | 2021 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Multi-classifier-based identification of COVID-19 from chest computed tomography using generalizable and interpretable radiomics features.

Wang Lu L Kelly Brendan B Lee Edward H EH Wang Hongmei H Zheng Jimmy J Zhang Wei W Halabi Safwan S Liu Jining J Tian Yulong Y Han Baoqin B Huang Chuanbin C Yeom Kristen W KW Deng Kexue K Song Jiangdian J

European journal of radiology 20210115

<h4>Purpose</h4>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.<h4>Methods</h4>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 radiol ...[more]

PMID: 33497881

Similar Datasets

Project description:ObjectiveTo investigate the application of computed tomography (CT)-based radiomics model for prediction of thyroid capsule invasion (TCI) in papillary thyroid carcinoma (PTC).MethodsThis retrospective study recruited 412 consecutive PTC patients from two independent institutions and randomly assigned to training (n=265), internal test (n=114) and external test (n=33) cohorts. Radiomics features were extracted from non-contrast (NC) and artery phase (AP) CT scans. We also calculated delta radiomics features, which are defined as the absolute differences between the extracted radiomics features. One-way analysis of variance and least absolute shrinkage and selection operator were used to select optimal radiomics features. Then, six supervised machine learning radiomics models (k-nearest neighbor, logistic regression, decision tree, linear support vector machine [L-SVM], Gaussian-SVM, and polynomial-SVM) were constructed. Univariate was used to select clinicoradiological risk factors. Combined models including optimal radiomics features and clinicoradiological risk factors were constructed by these six classifiers. The prediction performance was evaluated using the receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA).ResultsIn the internal test cohort, the best combined model (L-SVM, AUC=0.820 [95% CI 0.758-0.888]) performed better than the best radiomics model (L-SVM, AUC = 0.733 [95% CI 0.654-0.812]) and the clinical model (AUC = 0.709 [95% CI 0.649-0.783]). Combined-L-SVM model combines 23 radiomics features and 1 clinicoradiological risk factor (CT-reported TCI). In the external test cohort, the AUC was 0.776 (0.625-0.904) in the combined-L-SVM model, showing that the model is stable. DCA demonstrated that the combined model was clinically useful.ConclusionsOur combined model based on machine learning incorporated with CT radiomics features and the clinicoradiological risk factor shows good predictive ability for TCI in PTC.

Project description:ObjectiveThe aim of our study was to assess the effect of a short-term treatment with low-moderate corticosteroid (CS) doses by both a quantitative and qualitative assessment of chest HRCT of COVID-19 pneumonia.MethodsCORTICOVID is a single-center, cross-sectional, retrospective study involving severe/critical COVID-19 patients with mild/moderate ARDS. Lung total severity score was obtained according to Chung and colleagues. Moreover, the relative percentages of lung total severity score by ground glass opacities, consolidations, crazy paving, and linear bands were computed. Chest HRCT scores, P/F ratio, and laboratory parameters were evaluated before (pre-CS) and 7-10 days after (post-CS) methylprednisolone of 0.5-0.8 mg/kg/day.FindingsA total of 34 severe/critical COVID-19 patients were included in the study, of which 17 received Standard of Care (SoC) and 17 CS therapy in add-on. CS treatment disclosed a significant decrease in HRCT total severity score [median = 6 (IQR: 5-7.5) versus 10 (IQR: 9-13) in SoC, p < 0.001], as well in single consolidations [median = 0.33 (IQR: 0-0.92) versus 6.73 (IQR: 2.49-8.03) in SoC, p < 0.001] and crazy paving scores [mean = 0.19 (SD = 0.53) versus 1.79 (SD = 2.71) in SoC, p = 0.010], along with a significant increase in linear bands [mean = 2.56 (SD = 1.65) versus 0.97 (SD = 1.30) in SoC, p = 0.006]. GGO score instead did not significantly differ at the end of treatment between the two groups. Most post-CS GGO, however, derived from previous consolidations and crazy paving [median = 1.5 (0.35-3.81) versus 2 (1.25-3.8) pre-CS; p = 0.579], while pre-CS GGO significantly decreased after methylprednisolone therapy [median = 0.66 (0.05-1.33) versus 1.5 (0.35-3.81) pre-CS; p = 0.004]. CS therapy further determined a significant improvement in P/F levels [median P/F = 310 (IQR: 235.5-370) versus 136 (IQR: 98.5-211.75) in SoC; p < 0.001], and a significant increase in white blood cells, lymphocytes, and neutrophils absolute values.ConclusionThe improvement of all chest HRCT findings further supports the role of CS adjunctive therapy in severe/critical COVID-19 pneumonia.

Project description:ObjectiveTo evaluate the diagnostic performance of chest computed tomography (CT)-based qualitative and radiomics models for predicting residual axillary nodal metastasis after neoadjuvant chemotherapy (NAC) for patients with clinically node-positive breast cancer.Materials and methodsThis retrospective study included 226 women (mean age, 51.4 years) with clinically node-positive breast cancer treated with NAC followed by surgery between January 2015 and July 2021. Patients were randomly divided into the training and test sets (4:1 ratio). The following predictive models were built: a qualitative CT feature model using logistic regression based on qualitative imaging features of axillary nodes from the pooled data obtained using the visual interpretations of three radiologists; three radiomics models using radiomics features from three (intranodal, perinodal, and combined) different regions of interest (ROIs) delineated on pre-NAC CT and post-NAC CT using a gradient-boosting classifier; and fusion models integrating clinicopathologic factors with the qualitative CT feature model (referred to as clinical-qualitative CT feature models) or with the combined ROI radiomics model (referred to as clinical-radiomics models). The area under the curve (AUC) was used to assess and compare the model performance.ResultsClinical N stage, biological subtype, and primary tumor response indicated by imaging were associated with residual nodal metastasis during the multivariable analysis (all P < 0.05). The AUCs of the qualitative CT feature model and radiomics models (intranodal, perinodal, and combined ROI models) according to post-NAC CT were 0.642, 0.812, 0.762, and 0.832, respectively. The AUCs of the clinical-qualitative CT feature model and clinical-radiomics model according to post-NAC CT were 0.740 and 0.866, respectively.ConclusionCT-based predictive models showed good diagnostic performance for predicting residual nodal metastasis after NAC. Quantitative radiomics analysis may provide a higher level of performance than qualitative CT features models. Larger multicenter studies should be conducted to confirm their performance.

Project description:ObjectiveTo develop an automatic COVID-19 Reporting and Data System (CO-RADS)-based classification in a multi-demographic setting.MethodsThis multi-institutional review boards-approved retrospective study included 2720 chest CT scans (mean age, 58 years [range 18-100 years]) from Italian and Russian patients. Three board-certified radiologists from three countries assessed randomly selected subcohorts from each population and provided CO-RADS-based annotations. CT radiomic features were extracted from the selected subcohorts after preprocessing steps like lung lobe segmentation and automatic noise reduction. We compared three machine learning models, logistic regression (LR), multilayer perceptron (MLP), and random forest (RF) for the automated CO-RADS classification. Model evaluation was carried out in two scenarios, first, training on a mixed multi-demographic subcohort and testing on an independent hold-out dataset. In the second scenario, training was done on a single demography and externally validated on the other demography.ResultsThe overall inter-observer agreement for the CO-RADS scoring between the radiologists was substantial (k = 0.80). Irrespective of the type of validation test scenario, suspected COVID-19 CT scans were identified with an accuracy of 84%. SHapley Additive exPlanations (SHAP) interpretation showed that the "wavelet_(LH)_GLCM_Imc1" feature had a positive impact on COVID prediction both with and without noise reduction. The application of noise reduction improved the overall performance between the classifiers for all types.ConclusionUsing an automated model based on the COVID-19 Reporting and Data System (CO-RADS), we achieved clinically acceptable performance in a multi-demographic setting. This approach can serve as a standardized tool for automated COVID-19 assessment.Keypoints• Automatic CO-RADS scoring of large-scale multi-demographic chest CTs with mean AUC of 0.93 ± 0.04. • Validation procedure resembles TRIPOD 2b and 3 categories, enhancing the quality of experimental design to test the cross-dataset domain shift between institutions aiding clinical integration. • Identification of COVID-19 pneumonia in the presence of community-acquired pneumonia and other comorbidities with an AUC of 0.92.

Dataset Information

Multi-classifier-based identification of COVID-19 from chest computed tomography using generalizable and interpretable radiomics features.

Purpose

Methods

Results

Conclusions

Publications

Multi-classifier-based identification of COVID-19 from chest computed tomography using generalizable and interpretable radiomics features.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets