A Novel Radiomics-Based Noninvasive Methods For The Prediction Of High-Risk Gastroesophageal Varices In Cirrhosis

Background and aims:Gastroesophageal varices(GEV)are the principal complication of cirrhotic portal hypertension.Given to the mortality and morbidity associated with GEV,guidelines recommend that all cirrhotic patients should be screened for GEV.Upper endoscopy is recommended as the golden standard for GEV.However,endoscopic examination is invasive.Additionally,a large proportion of cirrhotic patients do not present with high-risk varices(HRV),so the majority of cirrhotic patients are exposed to the risk of invasive procedure and sedation complications without detecting HRV.Highly accurate noninvasive methods for predicting high-risk varices(HRV)are desired.Radiomics is a newly emerging technology of image analysis.Previous studies suggest that the potential application of radiomics in predicting VNT.However,the previous radiomics models do not contain the esophageal and gastric radiomics features which are important evidence for the radiologist to determine the existence and severity of GEV.Therefore,in this study,we aimed to develop a novel radiomics model containing the esophageal and gastric radiomics features for predicting HRV and to assess its performance in clinical application,particularly to assess its efficacy and safety.Methods:In this retrospective-prospective study,a total of 245 cirrhotic patients were divided as the training set,internal validation set and external validation set.The liver at the porta hepatis level,the spleen at splenic hilum level,and the level from the lower esophagus to gastric fundus were selected as the region of interest(ROI).Radiomics features were extracted from portal-phase computed tomography(CT)images of each patient.A radiomics signature(Rad-score)was constructed with the least absolute shrinkage and selection operator algorithm and 10-fold cross-validation in the training set.Combined with independent risk factors,a radiomics nomogram was built with a multivariate logistic regression model.The predictive accuracy of the radiomics signature was quantified by the area under the receiver operator characteristic(ROC)curve(AUC)in both training and validation sets.Additionally,a decision curve analysis was performed to evaluate the clinical usefulness and net benefits of the developed radiomics nomogram.Results:The rad-score,consisting of 14 features from the gastroesophageal region and 5 from the splenic hilum region,was effective for VNT classification.The Rad-score showed a good diagnostic performance for identifying VNT in cirrhotic patients with the AUC of 0.983(95%CI,0.964-1.00)in the training set.And the rad-score yielded the AUC of 0.970(95%CI,0.930-1.00)and 0.932(95%CI,0.853-1.00)in internal and external validation sets,respectively.The diagnostic performance was further improved by combining the Rad-score with platelet counts,achieving an AUC of 0.987(95%CI,0.969-1.00),0.973(95%CI,0.939-1.00)and 0.947(95%CI,0.876-1.00)in the training set,internal validation set and external validation set respectively.In efficacy and safety assessment,the radiomics nomogram could spare more than 40%of endoscopic examinations with a low risk of missing VNT(<5%),and no more than 8.3%of unnecessary endoscopic examinations still be performed.Conclusions:In this study,we developed and validated a novel,diagnostic radiomics-based nomogram which is a reliable and noninvasive method to predict VNT in cirrhotic patients.