Predicting Overall Survival of Local Advanced Rectal Cancer Patients Treated With Neoadjuvant Chemoradiation Therapy by Radiomic Features Extracted From Planning CTs

Abstract

To investigate the feasibility of predicting the prognosis of local advanced rectal cancer patients using a variety of radiomic features extracted from planning Computed Tomography (CT). We hypothesize that informative radiomic features will allow us to predict patient survival. A total of 93 local advanced rectal cancer patients treated with neoadjuvant chemo-radiotherapy (CRT) were enrolled in this study. In these patients, 52 of them were stage 3, 22 of them were stage 2, others were stage 1 or stage 4. All patients underwent planning CT scans before CRT. The Gross Tumor Volume (GTV) on the CT images were applied to define the area of primary lesion in this research. The CT images were filtered by Laplacian of Gaussian (LoG) filters to reduce image noise. A total of 170 radiomics features were extracted from the filtered images, including 3 geometry features, 12 histogram features, 100 GLCM (Gray-Level Co-Occurrence Matrix) texture features, and 55 GLRLM (Gray Level Run Length Matrix) texture features. A univariate Cox regression analysis were preformed upon all features to select the most predictive features. The first 4 features with the lowest p-value in univariate analysis were used to build a Cox regression model for predicting overall survival of these patients. The model was bootstrapped for 200 times to validate the accuracy of its result. A training C-index and a validation C-index of the Cox model were calculated to evaluate the performance of the prediction. 17 of 93 patients were deceased over a median follow-up time of 3 years. The 4 features most frequently selected in the univariate Cox regression analysis were Entropy of the histogram features, Maximal Correlation Coefficient and Homogeneity of the GLCM texture features, and High Gray Level Run Emphasis of the GLRLMS texture features. The final Cox regression model had a training C-index of 0.69 (0.55-0.79) and a validation C-index of 0.59 (0.39-0.65). Our results demonstrate that radiomic features extracted from planning CT scans are related to overall survival of rectal cancer patients. The Cox regression model built upon the informative radiomic features has promising performance for predicting overall survival of rectal cancer patients.