Computed tomography-based delta-radiomics enabling early prediction ofshort-term responses to concurrent chemoradiotherapy for patients withnon-small cell lung cancer

Objective:To explore the potential of computed tomography(CT)-based delta-radiomics in predicting early shortterm responses to concurrent chemoradiotherapy for patients with non-small cell lung cancer(NSCLC),in order to determine the optimal time point for the prediction.Methods:A total of 20 patients with pathologically confirmed NSCLC were prospectively enrolled in this study,who did not receive surgical treatment between February 2021 and February 2022.For each case,a total of 1,210 radiomic features(RFs)were extracted from both planning CT(pCT)images along with each of the subsequent three weeks of CT images.EffectiveΔRFs were selected using intra-class correlation coefficient(ICC)analysis,Pearson's correlation,ANOVA test(or Mann-Whitney U-test),and univariate logistic regression.The area under the curve(AUC)of the receiver operating characteristic(ROC)curve was used to evaluate the potential to predict short-term responses of different time points.Results:Among the 1,210ΔRFs for 1-3 weeks,121 common features were retained after processing using ICC analysis and Pearson's correlation.These retained features included 54 and 58 of all time points that differed significantly between the response and non-response groups for the first and third months,respectively(P<0.05).After univariate logistic regression,11 and 44 features remained for the first and third months,respectively.Finally,eightΔRFs(P<0.05,AUC=0.77-0.91)that can discriminate short-term responses in both at 1 and 3 months with statistical accuracy were identified.Conclusion:CT-based delta-radiomics has the potential to provide reasonable biomarkers of short-term responses to concurrent chemoradiotherapy for NSCLC patients,and it can help improve clinical decisions for early treatment adaptation.

Computed tomography-based radiomics to predict early recurrence of hepatocellular carcinoma post-hepatectomy in patients background on cirrhosis

BACKGROUND The prognosis for hepatocellular carcinoma(HCC)in the presence of cirrhosis is unfavourable,primarily attributable to the high incidence of recurrence.AIM To develop a machine learning model for predicting early recurrence(ER)of posthepatectomy HCC in patients with cirrhosis and to stratify patients’overall survival(OS)based on the predicted risk of recurrence.METHODS In this retrospective study,214 HCC patients with cirrhosis who underwent curative hepatectomy were examined.Radiomics feature selection was conducted using the least absolute shrinkage and selection operator and recursive feature elimination methods.Clinical-radiologic features were selected through univariate and multivariate logistic regression analyses.Five machine learning methods were used for model comparison,aiming to identify the optimal model.The model’s performance was evaluated using the receiver operating characteristic curve[area under the curve(AUC)],calibration,and decision curve analysis.Additionally,the Kaplan-Meier(K-M)curve was used to evaluate the stratification effect of the model on patient OS.RESULTS Within this study,the most effective predictive performance for ER of post-hepatectomy HCC in the background of cirrhosis was demonstrated by a model that integrated radiomics features and clinical-radiologic features.In the training cohort,this model attained an AUC of 0.844,while in the validation cohort,it achieved a value of 0.790.The K-M curves illustrated that the combined model not only facilitated risk stratification but also exhibited significant discriminatory ability concerning patients’OS.CONCLUSION The combined model,integrating both radiomics and clinical-radiologic characteristics,exhibited excellent performance in HCC with cirrhosis.The K-M curves assessing OS revealed statistically significant differences.