A CT-Based Radiomics Nomogram in Predicting the Postoperative Prognosis of Colorectal Cancer: A Two-center Study

Rationale and Objectives: This retrospective study aimed to develop a practical model to determine overall survival after surgery in patients with colorectal cancer according to radiomics signatures based on computed tomography (CT) images and clinical predictors.Materials and Methods: A total of 121 colorectal cancer (CRC) patients were selected to construct the model, and 51 patients and 114 patients were selected for internal validation and external testing. The radiomics features were extracted from each patient's CT images. Univariable Cox regression and least absolute shrinkage and selection operator regression were used to select radiomics features. The performance of the nomogram was evaluated by calibration curves and the c-index. Kaplan-Meier analysis was used to compare the overall survival between these subgroups.Results: The radiomics features of the CRC patients were significantly correlated with survival time. The c-indexes of the nomogram in the training cohort, internal validation cohort and external test cohort were 0.782, 0.721, and 0.677. Our nomogram integrated the optimal radiomics signature with clinical predictors showed a significant improvement in the prediction of CRC patients' overall survival. The cali-bration curves showed that the predicted survival time was close to the actual survival time. According to Kaplan-Meier analysis, the 1-, 2-, and 3-year survival rates of the low-risk group were higher than those of the high-risk group.Conclusion: The nomogram combining the optimal radiomics signature and clinical predictors further improved the predicted accuracy of survival prognosis for CRC patients. These findings might affect treatment strategies and enable a step forward for precise medicine.

Automated summary

The objective of this retrospective study was to develop a practical model, based on CT images and clinical predictors, to determine overall survival after surgery in patients with colorectal cancer. The model showed good performance in internal validation and external testing, and improved the prediction of overall survival for the patients.