Radiomics And Texture Analysis In Imaging Study In The Evaluation Of Therapeutic Effect Of Soft Tissue Sarcoma

Part I Prediction of the therapeutic efficacy of epirubicin combined with ifosfamide in patients with lung metastases from soft tissue sarcoma based on contrastenhanced CT radiomics features[Background and objective]Epirubicin combined with ifosfamide is the first-line treatment for patients with lung metastasis of soft tissue sarcoma.This study attempts to investigate the value of contrast-enhanced computed tomography(CECT)radiomics features in predicting the efficacy of epirubicin combined with ifosfamide in patients with pulmonary metastases from soft tissue sarcoma.Through the establishment and analysis of multiple radiomics models,the best radiomics model was selected for efficacy prediction.The purpose of this study is to find a non-invasive and accurate method to evaluate the therapeutic effect and assist further clinical diagnosis and treatment.[Materials and Methods]51 patients with lung metastases of soft tissue sarcoma who received epirubicin combined with ifosfamide chemotherapy regimen were retrospectively analyzed,and the efficacy was evaluated by the Recist 1.1.Each patient selected 1 or 2 pulmonary metastatic tumors as target lesions,and 86 target lesions were finally selected.The patients were divided into a progressive group(n=29)and a nonprogressive group(n=57).The non-progressive group included stable group(n=34)and partial response group(n=23).All target lesions were delineated by ITK-SNAP software manually or semiautomatically,and the radiomics features of target lesions before chemotherapy was extracted from the CECT images.After feature selecting,6 radiomics models(random forest classifier,logistic regression,support vector machine,naive Bayesian classification,decision tree classifier,and K-nearest neighbour)were constructed.The receiver operating characteristic(ROC)curve was used to analyze the prediction efficiency of each model,and the decision curve analysis(DCA)was used to evaluate the clinical application value of the radiomics model.[Result]851 CECT radiomics features were extracted from each target lesion.The decision tree model is the best among the six models.In the decision tree model,two radiomics features were finally included in the construction of the model.The area under the curve(AUC)of the training group and testing group is 0.917 and 0.856,respectively.The sensitivity,specificity and accuracy in the training group were 0.75,0.95 and 0.88 respectively;The testing group is 0.57,0.88 and 0.77,respectively.[Conclusion]The model established based on the radiomics features of CECT before treatment has certain predictive value for assessing the efficacy of chemotherapy for patients with soft tissue sarcoma lung metastases.Part II Predicting pathological complete response of neoadjuvant radiotherapy and targeted therapy for soft tissue sarcoma by whole-tumor texture analysis of multisequence MRI imaging[Background and purpose]To construct effective prediction models for neoadjuvant radiotherapy(RT)and targeted therapy based on whole-tumor texture analysis of multisequence MRI for soft tissue sarcoma(STS)patients.[Materials and Methods]Thirty patients with STS of the extremities or trunk from a prospective phase II trial were enrolled for this analysis.All patients underwent pre-and post-neoadjuvant RT MRI examinations from which whole-tumor texture features were extracted,including T1-weighted with fat saturation and contrast enhancement(T1FSGd),T2-weighted with fat saturation(T2FS),and diffusion-weighted imaging(DWI)sequences and their corresponding apparent diffusion coefficient(ADC)maps.According to the postoperative pathological results,the patients were divided into pathological complete response(pCR)and non-pCR(N-pCR)groups.pCR was defined as less than 5%of residual tumor cells by postoperative pathology.Delta features were defined as the percentage change in a texture feature from pre-to post-neoadjuvant RT MRI.After data reduction and feature selection,logistic regression was used to build prediction models.ROC analysis was performed to assess the diagnostic performance.[Result]Five of 30 patients(16.7%)achieved pCR.The Delta_Model(AUC 0.92)had a better predictive ability than the Pre_Model(AUC 0.78)and Post_Model(AUC 0.76)and was better than AJCC staging(AUC 0.52)and RECIST 1.1 criteria(AUC 0.52).The Combined Model(Pre,Post,and Delta features)had the best predictive performance(AUC 0.95).[Conclusion]Whole-tumor texture analysis of multisequence MRI can well predict pCR status after neoadjuvant RT and targeted therapy in STS patients,with better performance than RECIST 1.1 and AJCC staging.