Exploration Of Risk Factors For Postoperative Recurrence Of Stage Ⅱ Colorectal Cancer And Construction Of Prognostic Models Based On CT Radiomics

Objective Approximately one quarter of patients with colorectal cancer present with stage Ⅱ disease.Surgery is the first choice for treatment plan,with good prognosis show in patients after surgery.Nevertheless,20%-25% of resected stage Ⅱ colorectal cancer patients will have disease recurrence.Stage II colorectal cancer patients who are at high risk for disease recurrence may show benefit of long-term survival form adjuvant chemotherapy after surgery.However,there remains a unmet clinical need for the accurate identification of resected stage Ⅱ colorectal cancer patients who are at high risk for disease recurrence.Radiomics,through mining of data form images and subsequent implementation in assessment of therapy response and prediction of prognosis,offers new perspective for quantitative stratification of risk of disease recurrence of resected stage Ⅱ colorectal cancer.The aim of this study is to evaluate whether a radiomics signature could improve stratification of postoperative risk and prediction of chemotherapy benefit in stage Ⅱ colorectal cancer patients.Material and Methods From January 2010 to December 2015,consecutive patients with histologically proven stage Ⅱ colorectal cancer and available follow-up information were included.All patients received surgucal resection within two weeks after preoperative CT scan.The exclusion criteria were as follows:(1)patients previously treated with any anticancer therapy,(2)patients with co-malignancy,(3)patients with lack of available baseline demographics and CT images,and(4)patients lost to follow-up within 3 years and those with incomplete clinicopathological data.For temporally independent validation,patients were randomly separated into two cohorts at a 7 to 3 ratio: 210 for training and 89 for validation.The clinicopathological risk factors included gender,age,T stage,CT-reported tumor location(Ascending colon,Transverse colon,Descending colon,Sigmoid colon and Rectum),histologic grade of the tumor,smoking history,hypertension history,diabetes history,family history of cancer,internal obstruction or perforation(IOP)status,number of lymph nodes examined(≥12 vs <12),lymphovascular invasion(LVI)status,perineural invasion(PNI)status,mismatch repair status,Ki-67 expression level and history of postoperative adjunctive chemotherapy(present/absent).Laboratory analysis included tests for carcinoembryonic antigen(CEA)with the values of 5 ng/m L,carbohydrate antigen 724(CA724)with 6 U/m L,carbohydrate antigen 242(CA242)with 20 U/m L and carbohydrate antigen 199(CA199)with 39 U/Ml.The end-point was 3-year disease-free survival(DFS).Volume of interests(VOIs)were semiautomatically delineated using the open-source software 3D Slicer.Use the open-source python package “Pyradiomics V1.3.0” to extract each radiomics features,and use the Least Absolute Shrinkage and Selection Operator(LASSO)method to reduce the dimensionality.The minority group was balanced by the synthetic minority over-sampling technique(SMOTE).Analysis of univariate and multivariate Cox proportional hazard models to screen clinical pathological independent predictors with predictive value for postoperative recurrence of stage Ⅱ colorectal cancer.Predictive models were built with the Rad-score and clinicopathological factors,and the area under the curve(AUC)was used to evaluate their performance.A nomogram was also constructed for predicting3-year disease-free survival(DFS).The performance of the nomogram was assessed with a concordance index(C-index)and calibration plots.Results: Overall,299 patients(median [interquartile range {IQR}] age,59 [30-82]years)were enrolled in our study,including 187 male(median [IQR] age,59 [31-82]years)and 112 female(median [IQR] age,58 [30-80]).The training cohort and the testing cohort had 210 and 89 patients respectively.114 features were selected to construct the Rad-score,which was significantly associated with the 3-year DFS.Multivariate analysis demonstrated that the Rad-score,CA724 level,mismatch repair status and perineural invasion were independent predictors of recurrence.Results showed that the Rad-score can classify patients into high-risk and low-risk groups in the training cohort(AUC 0.886)and the validation cohort(AUC 0.874).On this basis,a nomogram that integrated the Rad-score and clinical variables demonstrated superior performance(AUC 0.954,0.906)than the clinical model alone(AUC 0.765,0.705)in the training and validation cohorts respectively.The C-index of the nomogram was 0.872,and the performance was acceptable.Our radiomics-based classifier indicated that patients in the high-risk group derived a greater survival benefit from adjuvant chemotherapy(HR 0.303,95% CI 0.181–0.506,P<0.001).Conclusion: Rad-score,CA724 level,mismatch repair status and perineural invasion were independent predictors of recurrence.Our radiomics-based model can reliably predict recurrence risk in stage Ⅱ colorectal cancer patients and potentially provide complementary prognostic value to the traditional clinicopathological risk factors for better identification of patients who are most likely to benefit from adjuvant therapy.The combined model constructed in conjunction with clinicopathological factors further improves the predictive performance.The proposed nomogram promises to be an effective tool for personalized postoperative surveillance for stage Ⅱ colorectal cancer patients.