Develop a Deep Radiomics Model for Predicting the Response to Neoadjuvant Chemoradiotherapy (nCRT) in Patients with Locally Advanced Esophageal Cancer Using Three-Stage Longitudinal CT Images

Abstract

To develop a deep radiomics model for predicting the response to neoadjuvant chemoradiotherapy (nCRT) of patients with locally advanced esophageal cancer using three stage longitudinal CT images. In this study, 189 patients were used to train our model, 80 patients were used to test the performance of the trained model. All patients enrolled in this study underwent nCRT followed by esophagectomy, and all patients underwent three stage longitudinal CT scans (before nCRT, after nCRT and before esophagectomy). The number of radiomics features for each CT images was 2153, the number of longitudinal radiomic features for each patient was 6459. Then, we used the least absolute shrinkage and selection operator regression for feature importance analysis. After this, the selected features of each stage were feed to the disentangled representation network to explore the relationship between the dynamic changes of tumors before and after nCRT and the pathological complete response (pCR). In addition, in order to further evaluate the effect of the time interval between nCRT and esophagectomy on the response to nCRT, we conducted subgroup analysis on different time frames. The performance of our model was evaluated by area under curve (AUC), accuracy, sensitivity and specificity. Compared with only using single-stage CT images (the AUC of only using before nCRT CT images, after nCRT CT images, before esophagectomy CT images were 73.27%, 74.21%, and 74.95%, respectively), effectively exploring the dynamic changes of the tumor can achieve better performance in predicting the response to nCRT in the testing cohort (the AUC was 84.29%, 95% CI, 81.14%-87.44%). In addition, the performance of our proposed method outperforms any combinations of two stage CT images (the AUC using the CT images of before nCRT and after nCRT was 77.92%, the AUC using the CT images of before nCRT and before esophagectomy was 79.31%, the AUC using the CT images of after nCRT and before esophagectomy was 80.01%). Finally, the results showed that exploring the dynamic changes of the tumor using the three-stage CT images outperformed using single-stage CT images and any combinations of two-stage CT images in predicting the response to nCRT. The study also found that the time interval between nCRT and esophagectomy had some influence on the accuracy of pCR prediction, with the prediction accuracy tending to increase from 1 to 6 weeks and stabilizing after 6 weeks. By exploring the dynamic changes of tumors, the designed disentangled representation network can effectively predict the response to nCRT of patients with esophageal cancer. In addition, the time interval between nCRT and esophagectomy also has a certain impact on the response to nCRT.