ABSTRACT
PurposeTo identify differences in CT imaging and clinical features between COVID-19 and influenza pneumonia in the early stage, and to identify the most valuable features in the differential diagnosis. Materials and MethodA consecutive cohort of 73 COVID-19 and 48 influenza pneumonia patients were retrospectively recruited from five independent institutions. The courses of both diseases were confirmed to be in the early stages (2.66 {+/-} 2.62 days for COVID-19 and 2.19 {+/-} 2.10 days for influenza pneumonia after onset). The chi-square test, students t-test, and Kruskal-Wallis H-test were performed to compare CT imaging and clinical features between the two groups. Spearman or Kendall correlation tests between feature metrics and diagnosis outcomes were also assessed. The diagnostic performance of each feature in differentiating COVID-19 from influenza pneumonia was evaluated with univariate analysis. The corresponding area under the curve (AUC), accuracy, specificity, sensitivity and threshold were reported. ResultsThe ground-glass opacification (GGO) was the most common imaging feature in COVID-19, including pure-GGO (75.3%) and mixed-GGO (78.1%), mainly in peripheral distribution. For clinical features, most COVID-19 patients presented normal white blood cell (WBC) count (89.04%) and neutrophil count (84.93%). Twenty imaging features and 6 clinical features were identified to be significantly different between the two diseases. The diagnosis outcomes correlated significantly with the WBC count (r=-0.526, P<0.001) and neutrophil count (r=-0.500, P<0.001). Four CT imaging features had absolute correlations coefficients higher than 0.300 (P<0.001), including crazy-paving pattern, mixed-GGO in peripheral area, pleural effusions, and consolidation. ConclusionsAmong a total of 1537 lesions and 62 imaging and clinical features, 26 features were demonstrated to be significantly different between COVID-19 and influenza pneumonia. The crazy-paving pattern was recognized as the most powerful imaging feature for the differential diagnosis in the early stage, while WBC count yielded the highest diagnostic efficacy in clinical manifestations.
ABSTRACT
Objective@#To explore the value of dynamic contrast-enhanced MRI (DCE-MRI) based radiomics model in predicting the pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) of breast cancer.@*Methods@#In this retrospective study, 91 patients who had received NAC and had pathological response results were collected in Meizhou people′s hospital from January 2016 to August 2018. A primary cohort consisted of 63 patients and an independent validation cohort consisted of 28 patients. The patients were divided into pCR group of 23 cases and non-pathological complete response (Non-pCR) group of 68 cases. All the patients underwent dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) before NAC. A list of radiomics features were extracted using the A.K software and the corresponding radiomics signature was constructed. Logistic regression was used to develop the prediction model. The predictive ability of the model was tested by using the area under the curve (AUC) of ROC analysis.@*Results@#The discrimination performance of radiomics signature yielded a AUC of 0.750 in the primary dataset and a AUC of 0.789 in the validation dataset. The model that incorporated estrogen receptor (ER), progesterone receptor (PR) and radiomics features was developed, and had an AUC of 0.859 in the primary dataset and an AUC of 0.905 in the validation dataset.@*Conclusion@#The radiomics predictive model, which integrated with the DCE-MRI based radiomics signature, ER and PR, can be used as a promising and applicable adjunct approach for predicting the pCR to NAC of breast cancer.
ABSTRACT
Objective ToinvestigatethefeasibilityofspectralvirtualnonGcontrast(VNC)takingtheplaceoftruenonGcontrast (TNC)inthyroiddiseases.Methods CTimagesof30patientswiththyroiddiseasewerecollected,includingTNC,spectraldualGphase contrastandconventionaldelayedcontrastimaging.36lesionswithcorrespondingsurgeryandpathologicalconditionswereselected forretrospectiveanalysis.Theradiationdose,imagequality,meanCTvalues,SNRanddiagnosticefficacybetweenTNCand VNC werecompared.Results Theeffectivedose(ED)andtotaldoseGlengthproduct(DLP)ofthespectraldualGphasecontrastscanswere bothsignificantlylowerthanthoseofTNCincombinationwithconventionaldualGphasecontrast(P＜0.05).Thesubjectivequality scoreofVNCwasslightlylowerthanthatofTNC (P＜0.05),howeveritwasacceptableforradiologistwithascoreabove3.The SNRofVNCimageswassignificantlylowerthanthatofTNC (P＜0.05).The meanCTvaluesofVNCimageswerelowerthan thoseofTNCimagesbutwithoutasignificantdifference(P＞0.05).TheabilityofVNCtodelineatenecrosis,calcification,andlymph nodemetastasisinthelesionwasconsistentwithTNC (k＞0.75).Conclusion TheimagequalityofVNCissatisfiedinthediagnosis ofthyroiddiseases.VNChassimilardiagnosticefficacytoTNCwitheffectivelyreducdingradiationdose,whichisapromisingclinical application.
ABSTRACT
Objective To explore the value of dynamic contrast-enhanced MRI (DCE-MRI) based radiomics model in predicting the pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) of breast cancer. Methods In this retrospective study, 91 patients who had received NAC and had pathological response results were collected in Meizhou people′s hospital from January 2016 to August 2018. A primary cohort consisted of 63 patients and an independent validation cohort consisted of 28 patients. The patients were divided into pCR group of 23 cases and non-pathological complete response (Non-pCR) group of 68 cases. All the patients underwent dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) before NAC. A list of radiomics features were extracted using the A. K software and the corresponding radiomics signature was constructed. Logistic regression was used to develop the prediction model. The predictive ability of the model was tested by using the area under the curve (AUC) of ROC analysis. Results The discrimination performance of radiomics signature yielded a AUC of 0.750 in the primary dataset and a AUC of 0.789 in the validation dataset. The model that incorporated estrogen receptor (ER), progesterone receptor (PR) and radiomics features was developed, and had an AUC of 0.859 in the primary dataset and an AUC of 0.905 in the validation dataset. Conclusion The radiomics predictive model, which integrated with the DCE-MRI based radiomics signature, ER and PR, can be used as a promising and applicable adjunct approach for predicting the pCR to NAC of breast cancer.
ABSTRACT
Objective ToinvestigatethecorrelationandthediagnosticefficiencyofquantitativeDCE-MRIparametersandADC valueinhistopathologicalgradeinpatients withinvasiveductalbreastcancer.Methods The DCE-MRIquantitativeparameters (Ktrans,KepandVe),semiquantitativeparameters(W-in,W-outandTTP)andtheADCvaluewereanalyzedandcomparedaccording bydifferenthistopathologicalgradein90invasiveductalbreastcancerpatients.Results ThemeanvalueofKtrans washigheringradeⅢgroupthanthatingradeⅡgroup,andthemeanvalueofADCwasloweringradeⅢgroupthanthatingradeⅡgroup.Thedifferenceswere statisticallysignificant(P<0.05),butthecorrelationswereweak(|r|<0.30).TherewerenostatisticallysignificantdifferencesamongKep, Ve,W-in,W-out,TTPingradeⅡandgradeⅢ (P>0.05).TheAUCofKtrans,ADCandKtranscombinedwithADCwere0.647,0.685 and0.749,respectively.Conclusion TheDCE-MRIquantitativeparametersKtransandADCvaluehavecorrelationswithhistopathologicalgradeof invasiveductalbreastcancer.HigherKtransandlowerADCvalueindicatehigherhistologicalgrade,andKtranscombinedwithADCcould improvethediagnosticefficiency.
