Chest CT features and progression of patients with coronavirus disease 2019

Objectives:Coronavirus disease 2019 (COVID-19) is a major public health emergency. It poses a grave threat to human life and health. The purpose of the study is to investigate the chest CT findings and progression of the disease observed in COVID-19 patients.Methods:Forty-nine confirmed cases of adult COVID-19 patients with common type, severe and critically severe type were included in this retrospective single-center study. The thin-section chest CT features and progress of the disease were evaluated. The clinical and chest imaging findings of COVID-19 patients with different severity types were compared. The CT severity score and MuLBSTA score (a prediction of mortality risk) were calculated in those patients.Results:Among the 49 patients, 35 patients (71%) were common type and 14 patients (28%) were severe and critically severe type. Nearly all patients (98%) had pure ground-glass opacities (GGO) in CT imaging. Of the severe and critically severe type patients, 86% exhibited GGO with consolidation, in comparison with 54% of the patients with common type. Fibrosis presented in 79% of the severe and critically severe type patients and 43% of the common type patients. The severe and critically severe type patients were significantly more prone to experience five-lobe involvement compared to the common type patients (p = 0.002). The severe and critically severe type patients also had higher CT severity and MuLBSTA scores than the common type patients (5.43 ± 2.38 vs 3.37 ± 2.40, p < 0.001;and 10.21 ± 3.83 vs 4.63 ± 3.43, p < 0.001, respectively). MuLBSTA score was positively correlated with admittance to the intensive care unit (p = 0.005, r = 0.351). Nineteen patients underwent three times CT scan. The interval between first and second CT scan was 4[4,8] days, second and third was 3[2,4] days. There were greater improvements in the third CT follow-up findings compared to the second (p = 0.002).Conclusions:The severe and critically severe type patients often experienced more severe lung lesions, including GGO with consolidation. The CT severity score and MuLBSTA score may be helpful for the assessment of COVID-19 severity and progression.Advances in knowledge:Chest CT has the value of evaluated radiographical features of COVID-19 and allow for dynamic observation of the disease progression. Considering coagulation disorder of COVID-19, MuLBSTA score may need to be updated to increase new understanding of COVID-19.     

Quantitative assessment of lung involvement on chest CT at admission: Impact on hypoxia and outcome in COVID-19 patients

BackgroundThe aim of this study was to quantify COVID-19 pneumonia features using CT performed at time of admission to emergency department in order to predict patients' hypoxia during the hospitalization and outcome.MethodsConsecutive chest CT performed in the emergency department between March 1st and April 7th 2020 for COVID-19 pneumonia were analyzed. The three features of pneumonia (GGO, semi-consolidation and consolidation) and the percentage of well-aerated lung were quantified using a HU threshold based software. ROC curves identified the optimal cut-off values of CT parameters to predict hypoxia worsening and hospital discharge. Multiple Cox proportional hazards regression was used to analyze the capability of CT quantitative features, demographic and clinical variables to predict the time to hospital discharge.ResultsSeventy-seven patients (median age 56-years-old, 51 men) with COVID-19 pneumonia at CT were enrolled. The quantitative features of COVID-19 pneumonia were not associated to age, sex and time-from-symptoms onset, whereas higher number of comorbidities was correlated to lower well-aerated parenchyma ratio (rho = −0.234, p = 0.04) and increased semi-consolidation ratio (rho = −0.303, p = 0.008).Well-aerated lung (≤57%), semi-consolidation (≥17%) and consolidation (≥9%) predicted worst hypoxemia during hospitalization, with moderate areas under curves (AUC 0.76, 0.75, 0.77, respectively). Multiple Cox regression identified younger age (p < 0.01), female sex (p < 0.001), longer time-from-symptoms onset (p = 0.049), semi-consolidation ≤17% (p < 0.01) and consolidation ≤13% (p = 0.03) as independent predictors of shorter time to hospital discharge.ConclusionQuantification of pneumonia features on admitting chest CT predicted hypoxia worsening during hospitalization and time to hospital discharge in COVID-19 patients.     

Radiomics of Non-Contrast-Enhanced T1 Mapping: Diagnostic and Predictive Performance for Myocardial Injury in Acute ST-Segment-Elevation Myocardial Infarction

ObjectiveTo evaluate the feasibility of texture analysis on non-contrast-enhanced T1 maps of cardiac magnetic resonance (CMR) imaging for the diagnosis of myocardial injury in acute myocardial infarction (MI).Materials and MethodsThis study included 68 patients (57 males and 11 females; mean age, 55.7 ± 10.5 years) with acute ST-segment-elevation MI who had undergone 3T CMR after a percutaneous coronary intervention. Forty patients of them also underwent a 6-month follow-up CMR. The CMR protocol included T2-weighted imaging, T1 mapping, rest first-pass perfusion, and late gadolinium enhancement. Radiomics features were extracted from the T1 maps using open-source software. Radiomics signatures were constructed with the selected strongest features to evaluate the myocardial injury severity and predict the recovery of left ventricular (LV) longitudinal systolic myocardial contractility.ResultsA total of 1088 segments of the acute CMR images were analyzed; 103 (9.5%) segments showed microvascular obstruction (MVO), and 557 (51.2%) segments showed MI. A total of 640 segments were included in the 6-month follow-up analysis, of which 160 (25.0%) segments showed favorable recovery of LV longitudinal systolic myocardial contractility. Combined radiomics signature and T1 values resulted in a higher diagnostic performance for MVO compared to T1 values alone (area under the curve [AUC] in the training set; 0.88, 0.72, p = 0.031: AUC in the test set; 0.86, 0.71, p002). Combined radiomics signature and T1 values also provided a higher predictive value for LV longitudinal systolic myocardial contractility recovery compared to T1 values (AUC in the training set; 0.76, 0.55, p < 0.001: AUC in the test set; 0.77, 0.60, p < 0.001).ConclusionThe combination of radiomics of non-contrast-enhanced T1 mapping and T1 values could provide higher diagnostic accuracy for MVO. Radiomics also provides incremental value in the prediction of LV longitudinal systolic myocardial contractility at six months.     

Utility of visual coronary artery calcification on non-cardiac gated thoracic CT in predicting clinical severity and outcome in COVID-19

BackgroundAssessment of visual-coronary artery calcification on non-cardiac gated CT in COVID-19 patients could provide an objective approach to rapidly identify and triage clinically severe patients for early hospital admission to avert worse prognosis.PurposeTo ascertain the role of semi-quantitative scoring in visual-coronary artery calcification score (V-CACS) for predicting the clinical severity and outcome in patients with COVID-19.Materials and methodsWith institutional review board approval this study included 67 COVID-19 confirmed patients who underwent non-cardiac gated CT chest in an inpatient setting. Two blinded radiologist (Radiologist-1 &2) assessed the V-CACS, CT Chest severity score (CT-SS). The clinical data including the requirement for oxygen support, assisted ventilation, ICU admission and outcome was assessed, and patients were clinically subdivided depending on clinical severity. Logistic regression analyses were performed to identify independent predictors. ROC curves analysis is performed for the assessment of performance and Pearson correlation were performed to looks for the associations.ResultsV-CACS cut off value of 3 (82.67% sensitivity and 54.55% specificity; AUC 0.75) and CT-SS with a cut off value of 21.5 (95.7% sensitivity and 63.6% specificity; AUC 0.87) are independent predictors for clinical severity and also the need for ICU admission or assisted ventilation. The pooling of both CT-SS and V-CACS (82.67% sensitivity and 86.4% specificity; AUC 0.92) are more reliable in terms of predicting the primary outcome of COVID-19 patients. On regression analysis, V-CACS and CT-SS are individual independent predictors of clinical severity in COVID-19 (Odds ratio, 1.72; 95% CI, 0.99–2.98; p = 0.05 and Odds ratio, 1.22; 95% CI, 1.08–1.39; p = 0.001 respectively). The area under the curve (AUC) for pooled V-CACS and CT-SS was 0.96 (95% CI 0.84–0.98) which correctly predicted 82.1% cases.ConclusionLogistic regression model using pooled Visual-Coronary artery calcification score and CT Chest severity score in non-cardiac gated CT can predict clinical severity and outcome in patients with COVID-19.     

Correlation of chest radiography findings with the severity and progression of COVID-19 pneumonia

PurposeAim is to assess the temporal changes and prognostic value of chest radiograph (CXR) in COVID-19 patients.Material and methodsWe performed a retrospective study of confirmed COVID-19 patients presented to the emergency between March 07–17, 2020. Clinical & radiological findings were reviewed. Clinical outcomes were classified into critical & non-critical based on severity. Two independent radiologists graded frontal view CXRs into COVID-19 pneumonia category 1 (CoV-P1) with <4 zones and CoV-P2 with ≥4 zones involvement. Interobserver agreement of CoV-P category for the CXR preceding the clinical outcome was assessed using Kendall's τ coefficient. Association between CXR findings and clinical deterioration was calculated along with temporal changes of CXR findings with disease progression.ResultsSixty-two patients were evaluated for clinical features. 56 of these (total: 325 CXRs) were evaluated for radiological findings. Common patterns were progression from lower to upper zones, peripheral to diffuse involvement, & from ground glass opacities to consolidation. Consolidations starting peripherally were noted in 76%, 93% and 48% with critical outcomes, respectively. The interobserver agreement of the CoV-P category of CXRs in the critical and non-critical outcome groups were good and excellent, respectively (τ coefficient = 0.6 & 1.0). Significant association was observed between CoV-P2 and clinical deterioration into a critical status (χ2 = 27.7, p = 0.0001) with high sensitivity (95%) and specificity (71%) within a median interval time of 2 days (range: 0–4 days).ConclusionInvolvement of predominantly 4 or more zones on frontal chest radiograph can be used as predictive prognostic indicator of poorer outcome in COVID-19 patients.     

Combination of 18F-Fluorodeoxyglucose PET/CT Radiomics and Clinical Features for Predicting Epidermal Growth Factor Receptor Mutations in Lung Adenocarcinoma

ObjectiveTo identify epidermal growth factor receptor (EGFR) mutations in lung adenocarcinoma based on ¹⁸F-fluorodeoxyglucose (FDG) PET/CT radiomics and clinical features and to distinguish EGFR exon 19 deletion (19 del) and exon 21 L858R missense (21 L858R) mutations using FDG PET/CT radiomics.Materials and MethodsWe retrospectively analyzed 179 patients with lung adenocarcinoma. They were randomly assigned to training (n = 125) and testing (n = 54) cohorts in a 7:3 ratio. A total of 2632 radiomics features were extracted from the tumor region of interest from the PET (1316) and CT (1316) images. Six PET/CT radiomics features that remained after the feature selection step were used to calculate the radiomics model score (rad-score). Subsequently, a combined clinical and radiomics model was constructed based on sex, smoking history, tumor diameter, and rad-score. The performance of the combined model in identifying EGFR mutations was assessed using a receiver operating characteristic (ROC) curve. Furthermore, in a subsample of 99 patients, a PET/CT radiomics model for distinguishing 19 del and 21 L858R EGFR mutational subtypes was established, and its performance was evaluated.ResultsThe area under the ROC curve (AUROC) and accuracy of the combined clinical and PET/CT radiomics models were 0.882 and 81.6%, respectively, in the training cohort and 0.837 and 74.1%, respectively, in the testing cohort. The AUROC and accuracy of the radiomics model for distinguishing between 19 del and 21 L858R EGFR mutational subtypes were 0.708 and 66.7%, respectively, in the training cohort and 0.652 and 56.7%, respectively, in the testing cohort.ConclusionThe combined clinical and PET/CT radiomics model could identify the EGFR mutational status in lung adenocarcinoma with moderate accuracy. However, distinguishing between EGFR 19 del and 21 L858R mutational subtypes was more challenging using PET/CT radiomics.     

Typical chest CT features can determine the severity of COVID-19: A systematic review and meta-analysis of the observational studies

BackgroundIt remains unclear whether a specific chest CT characteristic is associated with the clinical severity of COVID-19. This meta-analysis was performed to assess the relationship between different chest CT features and severity of clinical presentation in COVID-19.MethodsPubMed, Embase, Scopus, web of science databases (WOS), Cochrane library, and Google scholar were searched up to May 19, 2020 for observational studies that assessed the relationship of different chest CT manifestations and the severity of clinical presentation in COVID-19 infection. Risk of bias assessment was evaluated applying the Newcastle-Ottawa Scale. A random-effects model or fixed-effects model, as appropriately, were used to pool results. Heterogeneity was assessed using Forest plot, Cochran's Q test, and I2. Publication bias was assessed applying Egger's test.ResultsA total of 18 studies involving 3323 patients were included. Bronchial wall thickening (OR 11.64, 95% CI 1.81–74.66) was more likely to be associated with severe cases of COVID-19 infection, followed by crazy paving (OR 7.60, 95% CI 3.82–15.14), linear opacity (OR 3.27, 95% CI 1.10–9.70), and GGO (OR 1.37, 95% CI 1.08–1.73). However, there was no significant association between the presence of consolidation and severity of clinical presentation (OR 2.33, 95% CI 0.85–6.36). Considering the lesion distribution bilateral lung involvement was more frequently associated with severe clinical presentation (OR 3.44, 95% CI 1.74–6.79).ConclusionsOur meta-analysis of observational studies indicates some specific chest CT features are associated with clinical severity of COVID-19.     

Automated quantitative thin slice volumetric low dose CT analysis predicts disease severity in COVID-19 patients

PurposeThis study aimed to identify predictive (bio-)markers for COVID-19 severity derived from automated quantitative thin slice low dose volumetric CT analysis, clinical chemistry and lung function testing.MethodsSeventy-four COVID-19 patients admitted between March 16th and June 3rd 2020 to the Asklepios Lung Clinic Munich-Gauting, Germany, were included in the study. Patients were categorized in a non-severe group including patients hospitalized on general wards only and in a severe group including patients requiring intensive care treatment. Fully automated quantification of CT scans was performed via IMBIO CT Lung Texture analysis™ software. Predictive biomarkers were assessed with receiver-operator-curve and likelihood analysis.ResultsFifty-five patients (44% female) presented with non-severe COVID-19 and 19 patients (32% female) with severe disease. Five fatalities were reported in the severe group. Accurate automated CT analysis was possible with 61 CTs (82%). Disease severity was linked to lower residual normal lung (72.5% vs 87%, p = 0.003), increased ground glass opacities (GGO) (8% vs 5%, p = 0.031) and increased reticular pattern (8% vs 2%, p = 0.025). Disease severity was associated with advanced age (76 vs 59 years, p = 0.001) and elevated serum C-reactive protein (CRP, 92.2 vs 36.3 mg/L, p < 0.001), lactate dehydrogenase (LDH, 485 vs 268 IU/L, p < 0.001) and oxygen supplementation (p < 0.001) upon admission. Predictive risk factors for the development of severe COVID-19 were oxygen supplementation, LDH >313 IU/L, CRP >71 mg/L, <70% normal lung texture, >12.5% GGO and >4.5% reticular pattern.ConclusionAutomated low dose CT analysis upon admission might be a useful tool to predict COVID-19 severity in patients.     

Prediction of Prognosis in Glioblastoma Using Radiomics Features of Dynamic Contrast-Enhanced MRI

ObjectiveTo develop a radiomics risk score based on dynamic contrast-enhanced (DCE) MRI for prognosis prediction in patients with glioblastoma.Materials and MethodsOne hundred and fifty patients (92 male [61.3%]; mean age ± standard deviation, 60.5 ± 13.5 years) with glioblastoma who underwent preoperative MRI were enrolled in the study. Six hundred and forty-two radiomic features were extracted from volume transfer constant (K^trans), fractional volume of vascular plasma space (V_p), and fractional volume of extravascular extracellular space (V_e) maps of DCE MRI, wherein the regions of interest were based on both T1-weighted contrast-enhancing areas and non-enhancing T2 hyperintense areas. Using feature selection algorithms, salient radiomic features were selected from the 642 features. Next, a radiomics risk score was developed using a weighted combination of the selected features in the discovery set (n = 105); the risk score was validated in the validation set (n = 45) by investigating the difference in prognosis between the “radiomics risk score” groups. Finally, multivariable Cox regression analysis for progression-free survival was performed using the radiomics risk score and clinical variables as covariates.Results16 radiomic features obtained from non-enhancing T2 hyperintense areas were selected among the 642 features identified. The radiomics risk score was used to stratify high- and low-risk groups in both the discovery and validation sets (both p < 0.001 by the log-rank test). The radiomics risk score and presence of isocitrate dehydrogenase (IDH) mutation showed independent associations with progression-free survival in opposite directions (hazard ratio, 3.56; p = 0.004 and hazard ratio, 0.34; p = 0.022, respectively).ConclusionWe developed and validated the “radiomics risk score” from the features of DCE MRI based on non-enhancing T2 hyperintense areas for risk stratification of patients with glioblastoma. It was associated with progression-free survival independently of IDH mutation status.     

Lung perfusion changes in COVID-19 pneumonia: a dual energy computerized tomography study

Objective:There is limited and contradictory information about pulmonary perfusion changes detected with dual energy computed tomography (DECT) in COVID-19 cases. The purpose of this study was to define lung perfusion changes in COVID-19 cases with DECT, as well as to reveal any possible links between perfusion changes and laboratory findings.Methods:Patients who had a positive RT-PCR for SARS-CoV-2 and a contrast-enhanced chest DECT examination were included in the study. The pattern and severity of perfusion deficits were evaluated, as well as the relationships between perfusion deficit severity and laboratory results and CT severity ratings. The paired t-test, Wilcoxon test, and Student’s t-test were used to examine the changes in variables and perfusion deficits. p < 0.05 was regarded as statistically significant.Results:Study population consisted of 40 patients. Mean age was 60.73 ± 14.73 years. All of the patients had perfusion deficits at DECT images. Mean perfusion deficit severity score of the population was 8.45 ± 4.66 (min.-max, 1–19). In 24 patients (60%), perfusion deficits and parenchymal lesions matched completely. In 15 patients (37.5%), there was partial match. D dimer, CRP levels, CT severity score, and perfusion deficit severity score all had a positive correlationConclusions:Perfusion deficits are seen not only in opacification areas but also in parenchyma of normal appearance. The CT severity score, CRP, D-dimer, and SpO2 levels of the patients were determined to be related with perfusion deficit severity.Advances in knowledge:Findings of the current study may confirm the presence of micro-thrombosis in COVID-19 pneumonia.     

Structured reporting of chest CT provides high sensitivity and specificity for early diagnosis of COVID-19 in a clinical routine setting

Objectives:Although chest CT has been widely used in patients with COVID-19, its role for early diagnosis of COVID-19 is unclear. We report the diagnostic performance of chest CT using structured reporting in a routine clinical setting during the early phase of the epidemic in Germany.Methods:Patients with clinical suspicion of COVID-19 and moderate-to-severe symptoms were included in this retrospective study. CTs were performed and reported before RT-PCR results (reference standard) became available. A structured reporting system was used that concluded in a recently described five-grade score (“CO-RADS”), indicating the level of suspicion for pulmonary involvement of COVID-19 from 1 = very low to 5 = very high. Structured reporting was performed by three Radiologists in consensus.Results:In 96 consecutive patients (50 male, mean age 64), RT-PCR was positive in 20 (21%) cases. CT features significantly more common in RT-PCR-positive patients were ground-glass opacities as dominant feature, crazy paving, hazy margins of opacities, and multifocal bilateral distribution (p < 0.05). Using a cut-off point between CO-RADS 3 and 4, sensitivity was 90%, specificity 91%, positive predictive value 72%, negative predictive value 97%, and accuracy 91%. ROC analysis showed an AUC of 0.938.Conclusions:Structured reporting of chest CT with a five-grade scale provided accurate diagnosis of COVID-19. Its use was feasible and helpful in clinical routine.Advances in knowledge:Chest CT with structured reporting may be a provisional diagnostic alternative to RT-PCR testing for early diagnosis of COVID-19, especially when RT-PCR results are delayed or test capacities are limited.     

Role of complementary Ct chest in patients presenting with acute abdominal symptoms during covid-19 pandemic: a UK experience

BackgroundIn March 2020, the UK Intercollegiate General Surgery Guidance on COVID-19 recommended that patients undergoing emergency abdominal CT should have a complementary CT chest for COVID-19 screening.PurposeTo establish if complementary CT chest was performed as recommended, and if CT chest influenced surgical intervention decision. To assess detection rate of COVID-19 on CT and its correlation with RT-PCR swab results. To determine if COVID-19 changes is reliably detected within the lung bases which are usually imaged in standard abdominal CT.MethodsPatients with acute abdominal symptoms presenting to a single institution between 1st and 30th April 2020 who had abdominal CT and complementary CT chest were retrospectively extracted from Computerised Radiology Information System. CT COVID-19 changes were categorised according to British Society of Thoracic Radiology reporting guidance. Patient demographics (age and gender), RT-PCR swab results and management pathway (conservative or intervention) were recorded from electronic patient records. Statistical analyses were performed to evaluate any significant association between variables. p values ≤0.05 were regarded as statistically significant.ResultsCompliancy rate in performing complementary CT chest was 92.5% (148/160). Thirty-five patients (35/148,23.6%) underwent intervention during admission. There was no significant association (p = 0.9085) between acquisition of CT chest and management pathway (conservative vs intervention). CT chest had 57% sensitivity (CI 18.41% to 90.1%) and 100% specificity (CI 92% to 100%) in COVID-19 diagnosis. Three of ten patients who had classic COVID-19 changes on CT chest did not have corresponding changes in lung bases.ConclusionCompliance with performing complementary CT chest in acute abdomen patients for COVID-19 screening was high and it did not influence subsequent surgical or interventional management.     

治疗前CT影像组学结合机器学习预测非小细胞肺癌患者EGFR突变亚型

目的探讨基于治疗前胸部平扫CT影像组学特征和临床特征结合机器学习算法预测非小细胞肺癌(NSCLC)患者表皮生长因子受体(EGFR)突变状态和突变亚型(19Del/21L858R)的可行性和价值。方法回顾性分析南华大学附属第一医院和附属第二医院经活检病理证实和接受EGFR基因检测的280例NSCLC患者的治疗前胸部平扫CT和临床特征数据, 其中EFGR突变患者为136例。由两位高年资影像和肿瘤医师勾画原发肺部大体肿瘤区域(GTV), 然后提取851个影像组学特征, 采用Spearman相关分析和RELIEFF算法筛选具有预测性的特征, 两家医院分别为训练组和验证组。经特征选择的影像组学特征和临床特征构建临床-影像组学模型, 并与单独采用影像组学特征和临床特征模型进行比较。采用序贯建模流程, 使用支持向量机(SVM)建立机器学习模型预测EGFR突变状态和突变亚型。受试者工作曲线下面积(AUC-ROC)评估预测模型的诊断效能。结果经特征筛选各有21个影像组学特征在预测EGFR突变和突变亚型时具有预测效能并用于建立影像组学模型。临床-影像组学模型表现出最好的预测效能, 预测EGFR突变状态的模...     

Características en tomografía computarizada de la neumonía por coronavirus-2019 (COVID-19) en tres grupos de pacientes iraníes: estudio de un solo centro

Introduction and ObjectivesThe pivotal role of chest computed tomographic (CT) to diagnosis and prognosis coronavirus disease-2019 (COVID-19) is still an open field to be explored. This study was conducted to assess the CT features in confirmed cases with COVID-19.Materials and MethodsRetrospectively, initial chest CT data of 363 confirmed cases with COVID-19 were reviewed. All subjects were stratified into three groups based on patients’ clinical outcomes; non-critical group (n=194), critical group (n=65), and death group (n=104). The detailed of CT findings were collected from patients’ medical records and then evaluated for each group. In addition, multinomial logistic regression was used to analyze risk factors according to CT findings in three groups of patients with COVID-19.ResultsCompared with the non-critical group, mixed ground-glass opacities (GGO) and consolidation lesion, pleural effusion lesion, presence of diffuse opacity in cases, more than 2 lobes involved and opacity scores were significantly higher in the critical and death groups (P<0.05). Having more mixed GGO with consolidation, pleural effusion, lack of pure GGO, more diffuse opacity, involvement of more than 2 lobes and high opacity score identified as independent risk factors of critical and death groups.ConclusionCT images of non-critical, critical and death groups with COVID-19 had definite characteristics. CT examination plays a vital role in managing the current COVID-19 outbreak, for early detection of COVID-19 pneumonia. In addition, initial CT findings may be useful to stratify patients, which have a potentially important utility in the current global medical situation.     

Performance of Prediction Models for Diagnosing Severe Aortic Stenosis Based on Aortic Valve Calcium on Cardiac Computed Tomography: Incorporation of Radiomics and Machine Learning

ObjectiveWe aimed to develop a prediction model for diagnosing severe aortic stenosis (AS) using computed tomography (CT) radiomics features of aortic valve calcium (AVC) and machine learning (ML) algorithms.Materials and MethodsWe retrospectively enrolled 408 patients who underwent cardiac CT between March 2010 and August 2017 and had echocardiographic examinations (240 patients with severe AS on echocardiography [the severe AS group] and 168 patients without severe AS [the non-severe AS group]). Data were divided into a training set (312 patients) and a validation set (96 patients). Using non-contrast-enhanced cardiac CT scans, AVC was segmented, and 128 radiomics features for AVC were extracted. After feature selection was performed with three ML algorithms (least absolute shrinkage and selection operator [LASSO], random forests [RFs], and eXtreme Gradient Boosting [XGBoost]), model classifiers for diagnosing severe AS on echocardiography were developed in combination with three different model classifier methods (logistic regression, RF, and XGBoost). The performance (c-index) of each radiomics prediction model was compared with predictions based on AVC volume and score.ResultsThe radiomics scores derived from LASSO were significantly different between the severe AS and non-severe AS groups in the validation set (median, 1.563 vs. 0.197, respectively, p < 0.001). A radiomics prediction model based on feature selection by LASSO + model classifier by XGBoost showed the highest c-index of 0.921 (95% confidence interval [CI], 0.869–0.973) in the validation set. Compared to prediction models based on AVC volume and score (c-indexes of 0.894 [95% CI, 0.815–0.948] and 0.899 [95% CI, 0.820–0.951], respectively), eight and three of the nine radiomics prediction models showed higher discrimination abilities for severe AS. However, the differences were not statistically significant (p > 0.05 for all).ConclusionModels based on the radiomics features of AVC and ML algorithms may perform well for diagnosing severe AS, but the added value compared to AVC volume and score should be investigated further.     

Radiomics Analysis of Susceptibility Weighted Imaging for Hepatocellular Carcinoma: Exploring the Correlation between Histopathology and Radiomics Features

Purpose:No previous researches have extracted radiomics features from susceptibility weighted imaging (SWI) for biomedical applications. This research aimed to explore the correlation between histopathology of hepatocellular carcinoma (HCC) and radiomics features extracted from SWI.Methods:A total of 53 patients were ultimately enrolled into this retrospective study with MR examinations undertaken at a 3T scanner. About 107 radiomics features were extracted from SWI images of each patient. Then, the Spearman correlation test was performed to evaluate the correlation between the SWI-derived radiomics features and histopathologic indexes including histopathologic grade, microvascular invasion (MVI) as well as the expression status of cytokeratin 7 (CK-7), cytokeratin 19 (CK-19) and Glypican-3 (GPC-3). With SWI-derived radiomics features utilized as independent variables, four logistic regression-based diagnostic models were established for diagnosing patients with positive CK-7, CK-19, GPC-3 and high histopathologic grade, respectively. Then, receiver operating characteristic analysis was performed to evaluate the diagnostic performance.Results:A total of 11, 32, 18 and one SWI-derived radiomics features were significantly correlated with histopathologic grade, the expression of CK-7, the expression of CK-19 and the expression of GPC-3 (P < 0.05), respectively. None of the SWI-derived radiomics features was correlated with MVI status. The areas under the curve were 0.905, 0.837, 0.800 and 0.760 for diagnosing patients with positive CK-19, positive CK-7, high histopathologic grade and positive GPC-3.Conclusion:Extracting the radiomics features from SWI images was feasible to evaluate multiple histopathologic indexes of HCC.