Purpose: Although tumor mutation burden (TMB) has been well known to predict the response to immune checkpoint inhibitors (ICIs), lacking of randomized clinical trial data has restricted its clinical application. This study aimed at exploring the significance and feasibility of biomarker combination based on TMB and copy number alteration (CNA) for the prognosis of each tumor and prediction for ICI therapy in metastatic pan-cancer milieu. Experimental Design: Non-ICI treated MSK pan-cancer cohort was used for prognosis analysis. Three independent immunotherapy cohorts including non-small cell lung cancer (NSCLC, n = 240), skin cutaneous melanoma (SKCM, n = 174) and mixed cancer (Dana-Farber, n=98) patients from previous studies were analyzed for efficacy of ICIs therapy. Results: TMB and CNA showed optimized combination for the prognosis of most metastatic cancer types, patients with TMB^lowCNA^low showed better survival. In the predictive analysis, both TMB and CNA were independent predictive factors for ICI therapy. Remarkably, when TMB and CNA were jointly analyzed, those with TMB^highCNA^low showed favorable responses to ICI therapy. Meanwhile, TMB^highCNA^low as a new biomarker showed better prediction for ICI efficacy compared with either TMB-high or CNA-low alone. Furthermore, analysis of the non-ICI treated MSK pan-cancer cohort supported that the joint stratification of TMB and CNA can be used to categorize tumors into distinct sensitivity to ICI therapy across pan-tumors. Conclusions: The combination of TMB and CNA can jointly stratify multiple metastatic tumors into groups with different prognosis and heterogenous clinical responses to ICI treatment. Patients with TMB^highCNA^low cancer can be an optimal subgroup for ICI therapy.

Background We attempted to train and validate a model of deep learning for the preoperative prediction of the response of patients with intermediate-stage hepatocellular carcinoma (HCC) undergoing transarterial chemoembolization (TACE). Method All computed tomography (CT) images were acquired for 562 patients from the Nan Fang Hospital (NFH), 89 patients from Zhu Hai Hospital Affiliated with Jinan University (ZHHAJU), and 138 patients from the Sun Yat-sen University Cancer Center (SYUCC). We built a predictive model from the outputs using the transfer learning techniques of a residual convolutional neural network (ResNet50). The prediction accuracy for each patch was revaluated in two independent validation cohorts. Results In the training set (NFH), the deep learning model had an accuracy of 84.3% and areas under curves (AUCs) of 0.97, 0.96, 0.95, and 0.96 for complete response (CR), partial response (PR), stable disease (SD), and progressive disease (PD), respectively. In the other two validation sets (ZHHAJU and SYUCC), the deep learning model had accuracies of 85.1% and 82.8% for CR, PR, SD, and PD. The ResNet50 model also had high AUCs for predicting the objective response of TACE therapy in patches and patients of three cohorts. Decision curve analysis (DCA) showed that the ResNet50 model had a high net benefit in the two validation cohorts. Conclusion The deep learning model presented a good performance for predicting the response of TACE therapy and could help clinicians in better screening patients with HCC who can benefit from the interventional treatment. Key Points • Therapy response of TACE can be predicted by a deep learning model based on CT images. • The probability value from a trained or validation deep learning model showed significant correlation with different therapy responses. • Further improvement is necessary before clinical utilization.

Diagnostic and Interventional Radiology