Disclosed are a radiotherapy system, a data processing method and a storage medium, relating to the technical field of radiotherapy. The system comprises: a calibration database (10), a training module (20) and a data processing module (30), wherein the calibration database (10) is capable of acquiring a plurality of pieces of sample data generated during the process of clinical treatment； the training module (20) is capable of carrying out deep learning on the plurality of pieces of sample data stored in the calibration database (10) to obtain a treatment algorithm model； and the data processing module (30) is capable of processing, according to the treatment algorithm model, detection data received during the process of the clinical treatment and generating preliminary treatment data. Since the treatment algorithm model is obtained by carrying out deep learning on a large amount of clinical data, the treatment algorithm model is relatively highly reliable. Accordingly, the accuracy rate of the preliminary treatment data generated by means of the treatment algorithm model is relatively high. The preliminary treatment data can be directly used for clinical treatment, or can be used for clinical treatment simply after a small amount of amendment by clinical personnel, thereby effectively improving the treatment efficiency of the radiotherapy system.L'invention concerne un système de radiothérapie, un procédé de traitement de données et un support de stockage, se rapportant au domaine technique de la radiothérapie. Le système comprend : une base de données d'étalonnage (10), un module d'apprentissage (20) et un module de traitement de données (30), la base de données d'étalonnage (10) étant en mesure d'acquérir une pluralité d'éléments de données d'échantillon générées pendant le procédé de traitement clinique ； le module d'apprentissage (20) étant en mesure de réaliser un apprentissage profond sur la pluralité d'éléments de données d'échantillon stockées dans la base
