Diagnostic Value Of CT Radiomics For Differentiation Of Adrenal Nodular Hyperplasia And Lipid-poor Adenoma

Part Ⅰ:Diagnostic value of non-contrast-based CT radiomics nomogram for adrenal nodular hyperplasia and lipid-poor adenomaObjective To investigate the benefit of CT radiomics nomogram derived from noncontrast CT images to differentiate adrenal nodular hyperplasia from adrenal lipid-poor adenoma.Methods Forty four patients with adrenal lipid-poor adenoma and 55 with adrenal nodular hyperplasia confirmed by pathology were retrospectively enrolled and the clinical factors of all patients were analyzed.Radiomics features extracted from non-contrast CT and radiomics score(Rad-score)were calculated to construct a radiomics model.Clinical factors were selected to construct a clinical model.Radiomics nomogram was constructed combining clinical factors and Rad-score.The diagnostic values of the three models were compared.Results A radiomics signature was established containing a total of 13 radiomics features.The area under the receiver operator characteristic curve(AUC),sensitivity and specificity of the radiomics signature were 0.91,84.6%and 81.3%,respectively.Both univariate and multivariate Logistic regression showed that renin and maximum diameter were the independent influencing factors in the clinical model.The AUC,sensitivity and specificity of the clinical model were 0.57,53.9%and 68.8%,respectively.The AUC,sensitivity and specificity of the radiomics nomogram were 0.94,84.6%and 93.8%,respectively.The diagnostic efficiency of the radiomics signature and nomogram was significantly better than the diagnostic efficiency of the clinical model(z=3.188,P<0.001;z=3.409,P<0.001).Conclusion The radiomics nomogram based on non-contrast CT has a high efficiency to differentiate adrenal lipid-poor adenoma from adrenal nodular hyperplasia.Part Ⅱ:Diagnostic value of non-enhanced-based and enhanced-based CT radiomics nomogram for adrenal nodular hyperplasia and lipidpoor adenomaBackground To establish and verify a radiomics nomogram for differentiating isolated micronodular adrenal hyperplasia(iMAD)from lipid-poor adenoma(LPA)based on computed tomography(CT)-extracted radiomic features.Methods A total of 148 patients with iMAD or LPA were divided into three cohorts:a training cohort(n=72;37 iMAD and 35 LPA),a validation cohort(n=36;22 iMAD and 14 LPA),and an external validation cohort(n=40;20 iMAD and 20 LPA).Radiomics features were extracted from contrast-enhanced and non-contrast CT images.The least absolute shrinkage and selection operator(LASSO)method was applied to develop a triphasic radiomics model and unenhanced radiomics model using reproducible radiomics features.A clinical model was constructed using certain laboratory variables and CT findings.Nomogram performance was assessed by calibration curve,the areas under receiver operating characteristic curves(AUC),and decision curve analysis(DCA).Results Eleven and eight extracted features were finally selected to construct an unenhanced radiomics model and a triphasic radiomics model,respectively.There was no significant difference of diagnostic performance between unenhanced and triphasic model in the external validation cohort(0.838 vs.0.843,P=0.949).The radiomics nomogram inclusive of the unenhanced model,maximum diameter,and aldosterone showed the AUC of 0.951,0.938,and 0.893 for the training,validation,and external validation cohorts,respectively.The nomogram showed good calibration,and the DCA demonstrated the superiority of the nomogram compared with the clinical factors model alone in terms of clinical usefulness.Conclusions A radiomics nomogram based on unenhanced CT images and clinical variables showed favorable performance for distinguishing iMAD from LPA.In addition,an efficient unenhanced model can help avoid extra contrast-enhanced scanning and radiation risk.