Dataset Information

Identification of common and severe COVID-19: the value of CT texture analysis and correlation with clinical characteristics.

ABSTRACT: OBJECTIVE:To explore the value of CT texture analysis (CTTA) for determining coronavirus disease 2019 (COVID-19) severity. METHODS:The clinical and CT data of 81 patients with COVID-19 were retrospectively analyzed. The texture features were extracted using LK2.1. The two-sample t test or Mann-Whitney U test was used to find the significant features. Minimum redundancy and maximum relevance (MRMR) method was performed to find the features with maximum correlation and minimum redundancy. These features were then used to construct a radiomics texture model to discriminate the severe patients using multivariate logistic regression method. Besides, a clinical model was also built. ROC analyses were conducted to evaluate the performance of two models. The correlations of clinical features and textural features were analyzed using the Spearman correlation analysis. RESULTS:Of the total cases included, 60 were common and 21 were severe. (1) For textural features, 20 radiomics features selected by MRMR showed good performance in discriminating the two groups (AUC >?70%). (2) For clinical features, chi-square tests or Mann-Whitney U tests identified 16 clinical features as significant, and 12 were discriminative (p ?70%. (3) Prediction models for textural features and clinical features were established, and both showed high predictive accuracy. The AUC values of textural features and clinical features were 0.93 (0.86-1.00) and 0.95 (0.95-0.99), respectively. (4) The Spearman correlation analysis showed that most textural and clinical features had above-moderate correlations with disease severity (>?0.4). CONCLUSION:Texture analysis can provide reliable and objective information for differential diagnosis of COVID-19. KEY POINTS:• CT texture analysis can well differentiate common and severe COVID-19 patients. • Some textural features showed above-moderate correlations with clinical factors. • CT texture analysis can provide useful information to judge the severity of COVID-19.

SUBMITTER: Wei W

PROVIDER: S-EPMC7327490 | biostudies-literature | 2020 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Identification of common and severe COVID-19: the value of CT texture analysis and correlation with clinical characteristics.

Wei Wei W Hu Xiao-Wen XW Cheng Qi Q Zhao Ying-Ming YM Ge Ya-Qiong YQ

European radiology 20200701 12

<h4>Objective</h4>To explore the value of CT texture analysis (CTTA) for determining coronavirus disease 2019 (COVID-19) severity.<h4>Methods</h4>The clinical and CT data of 81 patients with COVID-19 were retrospectively analyzed. The texture features were extracted using LK2.1. The two-sample t test or Mann-Whitney U test was used to find the significant features. Minimum redundancy and maximum relevance (MRMR) method was performed to find the features with maximum correlation and minimum redun ...[more]

PMID: 32613287

Similar Datasets

Project description:OBJECTIVE:To investigate the computed tomography (CT) characteristics and diagnostic value of novel coronavirus pneumonia (NCP or COVID-19) in pregnancy. METHODS:This study included ten pregnant women infected with COVID-19, treated in the Zhongnan Hospital of Wuhan University from January 20, 2020 to February 6, 2020. Clinical and chest CT data were collected and clinical symptoms, laboratory indicators, and CT images were analyzed to explore CT characteristics and diagnostic value for COVID-19 during pregnancy. RESULTS:Laboratory examination showed that white blood cell count was normal in nine patients, and slightly higher in one patient (10.23 × 109). The lymphocyte ratio decreased in two patients by 12% and 14%, respectively. The levels of C-reactive protein was elevated in seven patients (range, 21.16-60.3 mg/L) and the levels of D-dimer was increased in eight patients (range, 507-2141 ng/mL). Six patients had low levels of total protein (range, 35.3-56.5 mg/L). Two patients showed small patchy ground glass opacity (GGO) involving single lung, while eight patients showed multilobe GGO in both the lungs, with partial consolidation. Peripheral and non-peripheral lesion distributions were seen in ten (100%) and four (40%) patients, respectively. There were four patients who had signs of intra-bronchial air-bronchogram, six patients had small bilateral pleural effusions, while none had lymphadenopathy. Dynamic observations were performed in four patients after COVID-19 treatment. Among these four patients, one patient showed normal on the initial examination, and new lesions were observed after 3 days; 1 patient showed progression after 7 days of treatment, with expansion of the lesion area; and the other 2 patients showed improvement after 14 days of treatment, with reduction in the density and area of lesions and appearance of linear opacity. CONCLUSIONS:The CT characteristics of COVID-19 in pregnancy were mainly observed in early and progressive stages, and multiple new lesions were common. And there were consolidations of varying sizes and degrees within the lesion. Moreover, the original ground glass lesions could be fused or partially absorbed. Six patients had small bilateral pleural effusion. In summary, CT scans can play an important role in early screening, dynamic observation, and efficacy evaluation of suspected or confirmed cases of pregnant women with COVID-19.

Project description:BackgroundGas exchange in COVID-19 pneumonia is impaired and vessel obstruction has been suspected to cause ventilation-perfusion mismatch. Dual-energy CT (DECT) can depict pulmonary perfusion by regional assessment of iodine uptake.ObjectiveThe purpose of this study was the analysis of pulmonary perfusion using dual-energy CT in a cohort of 27 consecutive patients with severe COVID-19 pneumonia.MethodWe retrospectively analyzed pulmonary perfusion with DECT in 27 consecutive patients (mean age 57 years, range 21-73; 19 men and 8 women) with severe COVID-19 pneumonia. Iodine uptake (IU) in regions-of-interest placed into normally aerated lung, ground-glass opacifications (GGO) and consolidations was measured using a dedicated postprocessing software. Vessel enlargement (VE) within opacifications and presence of pulmonary embolism (PE) was assessed by subjective analysis. Linear mixed models were used for statistical analyses.ResultsCompared to normally aerated lung 106/151 (70.2%) opacifications without upstream PE demonstrated an increased IU, 9/151 (6.0%) an equal IU and 36/151 (23.8%) a decreased IU. The estimated mean iodine uptake (EMIU) in opacifications without upstream PE (GGO 1.77 mg/mL; 95%-CI: 1.52-2.02; p = 0.011, consolidations 1.82 mg/mL; 95%-CI: 1.56-2.08, p = 0.006) was significantly higher compared to normal lung (1.22 mg/mL; 95%-CI: 0.95-1.49). In case of upstream PE, EMIU of opacifications (combined GGO and consolidations) was significantly decreased compared to normal lung (0.52 mg/mL; 95%-CI: -0.07-1.12; p = 0.043). The presence of VE in opacifications correlated significantly with iodine uptake (p<0.001).ConclusionsDECT revealed the opacifications in a subset of patients with severe COVID-19 pneumonia to be perfused non-uniformly with some being hypo- and others being hyperperfused. Mean iodine uptake in opacifications (both ground-glass and consolidation) was higher compared to normally aerated lung except for areas with upstream pulmonary embolism. Vessel enlargement correlated with iodine uptake: In summary, in a cohort of 27 consecutive patients with severe COVID-19 pneumonia, dual-energy CT demonstrated a wide range of iodine uptake in pulmonary ground-glass opacifications and consolidations as a surrogate marker for hypo- and hyperperfusion compared to normally aerated lung. Applying DECT to determine which pathophysiology is predominant might help to tailor therapy to the individual patient´s needs.

Project description:ObjectiveThe objective of this study was to evaluate the robustness and reproducibility of computed tomography-based texture analysis (CTTA) metrics extracted from CT images of a customized texture phantom built for assessing the association of texture metrics to three-dimensional (3D) printed progressively increasing textural heterogeneity.Materials and methodsA custom-built 3D-printed texture phantom comprising of six texture patterns was used to evaluate the robustness and reproducibility of a radiomics panel under a variety of routine abdominal imaging protocols. The phantom was scanned on four CT scanners (Philips, Canon, GE, and Siemens) to assess reproducibility. The robustness assessment was conducted by imaging the texture phantom across different CT imaging parameters such as slice thickness, field of view (FOV), tube voltage, and tube current for each scanner. The texture panel comprised of 387 features belonging to 15 subgroups of texture extraction methods (e.g., Gray-level Co-occurrence Matrix: GLCM). Twelve unique image settings were tested on all the four scanners (e.g., FOV125). Interclass correlation two-way mixed with absolute agreement (ICC3) was used to assess the robustness and reproducibility of radiomic features. Linear regression was used to test the association between change in radiomic features and increased texture heterogeneity. Results were summarized in heat maps.ResultsA total of 5612 (23.2%) of 24 090 features showed excellent robustness and reproducibility (ICC ≥ 0.9). Intensity, GLCM 3D, and gray-level run length matrix (GLRLM) 3D features showed best performance. Among imaging variables, changes in slice thickness affected all metrics more intensely compared to other imaging variables in reducing the ICC3. From the analysis of linear trend effect of the CTTA metrics, the top three metrics with high linear correlations across all scanners and scanning settings were from the GLRLM 2D/3D and discrete cosine transform (DCT) texture family.ConclusionThe choice of scanner and imaging protocols affect texture metrics. Furthermore, not all CTTA metrics have a linear association with linearly varying texture patterns.

Dataset Information

Identification of common and severe COVID-19: the value of CT texture analysis and correlation with clinical characteristics.

Publications

Identification of common and severe COVID-19: the value of CT texture analysis and correlation with clinical characteristics.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets