An Artificial Neural Network-based Radiomics model for Predicting Radiotherapy response of Advanced Esophageal Squamous Cell Carcinoma patients: A multi-center Study

Abstract

Abstract Radiotherapy benefits patients with advanced esophageal squamous cell carcinoma (ESCC) on symptom relief and long-term survival. Contrarily, a substantial proportion of ESCC patients have not benefited from radiotherapy. This study aimed to establish and validate an artificial neural network-based radiomics model for the pre-treatment predicting radiotherapy response of advanced ESCC by using integrated data combined with feasible baseline characteristics of computer tomography. The 248 patients with advanced ESCC patients who underwent baseline CT and received radiotherapy were enrolled in this study and were analyzed by two types of radiomics models, including machine learning and deep learning. As a result, the Att. Resnet50 pretrained network model indicated a superior performance, with AUCs of 0.876, 0.802 and o.732 in the training, internal validation, and external validation cohort. Similarly, our Att. Resnet50 pretrained network model showed excellent calibration and significant clinical benefit according to the C index and the decision curve analysis.Herein, a novel pre-treatment radiomics model was established based on deep learning methods and could be used for radiotherapy response prediction in advanced ESCC patients, thus providing reliable evidence for therapeutic decision-making.