Application value of fibrous adipose tissue infiltration in rectal cancer using MRI-based radiomics
Objective To evaluate the value of preoperative prediction of fibrous adipose tissue infiltration around rectal cancer using MRI-based radiomics.Methods The preoperative MRI of 75 patients with rectal cancer confirmed by pathology in The People's Hospital of Tongling City from December 2019 to March 2022 were analyzed retrospectively.According to the pathological results,the patients were divided into two groups:the fibrous adipose tissue infiltration group(n=33)and the fibrous adipose tissue noninfiltration group(n=42).The image group features for T2WI and arterial phase contrast-enhanced T1-weighted imaging(CE-T1WI)were extracted.The data were divided into a training group(n=54)and a verification group(n=21)at a ratio of 7:3.The training set data were reduced by maximum correlation minimum redundancy and LASSO regression,and feature dimension reduction was used to select the optimal imaging features.Three image group models(T2WI model,CE-T1WI model,T2WI+CE-T1WI model)were constructed.The best model had been selected in the three models.Based on the ROC curves and multivariate Logistic regression analysis in accordance with such parameters as upper and lower diameter of tumour,thickest diameter of tumour,unsmoothed edges,blurred boundary,CE-T1WI relative signal intensity(RCE-T1WI),T2WI relative signal intensity(RT2),DWI relative signal intensity(RDWI)and ADC,a combined model was constructed,and its predictive efficiency and clinical benefits were evaluated.Results In total,851 imaging features were extracted from T2WI and CE-T1WI,and 10 and 14 optimal features were obtained,respectively,which were used to construct the combined model.In the training group,the AUC for the T2WI model,CE-T1WI model and T2WI+CE-T1WI model for predicting fibrous adipose tissue infiltration around rectal cancer were 0.87(95%CI:0.75-0.95),0.82(95%CI:0.70-0.91)and 0.84(95%CI:0.71-0.92),respectively.In the verification group,the AUC were 0.76(95%CI:0.53-0.92),0.73(95%CI:0.50-0.90)and 0.76(95%CI:0.52-0.92),respectively.The T2WI modle was the best model.For the combined model,the AUC for predicting fibrous adipose tissue infiltration of rectal cancer was 0.91(95%CI:0.80-0.97)in the training group and 0.80(95%CI:0.57-0.94)in the verification group.Decision curve analysis suggested that when the threshold was 0:1,the net return of combined model was higher than that of the T2WI model.Conclusion The combined model of MRI-based radiomics is effective in inevaluateing the preoperative of fibrous adipose tissue infiltration in rectal cancer.
万方数据
维普
