A feasibility study of tumor motion monitoring for SBRT of lung cancer based on 3D point cloud detection and stacking ensemble learning

To construct a tumor motion monitoring model for stereotactic body radiation therapy (SBRT) of lung cancer from a feasibility perspective. A total of 32 treatment plans for 22 patients were collected, whose planning CT and the centroid position of the planning target volume (PTV) were used as the reference. Images of different respiratory phases in 4DCT were acquired to redefine the targets and obtain the floating PTV centroid positions. In accordance with the planning CT and CBCT registration parameters, data augmentation was accomplished, yielding 2130 experimental recordings for analysis. We employed a stacking multi-learning ensemble approach to fit the 3D point cloud variations of body surface and the change of target position to construct the tumor motion monitoring model, and the prediction accuracy was assess using root mean squared error (RMSE) and R-Square (R2). The prediction displacement of the stacking ensemble model shows a high degree of agreement with the reference value in each direction. In the first layer of model, the X direction (RMSE =0.019 ∼ 0.145mm, R2 =0.9793∼0.9996) and the Z direction (RMSE = 0.051 ∼ 0.168 mm, R2 = 0.9736∼0.9976) show the best results, while the Y direction ranked behind (RMSE = 0.088 ∼ 0.224 mm, R2 = 0.9553∼ 0.9933). The second layer model summarizes the advantages of unit models of first layer, and RMSE of 0.015 mm, 0.083 mm, 0.041 mm, and R2 of 0.9998, 0.9931, 0.9984 respectively for X, Y, Z were obtained. The tumor motion monitoring method for SBRT of lung cancer has potential application of non-ionization, non-invasive, markerless, and real-time. Construire un modèle de surveillance des mouvements tumoraux pour la radiothérapie stéréotaxique corporelle (RSC) du cancer du poumon du point de vue de la faisabilité. Un total de 32 plans de traitement pour 22 patients ont été recueillis, dont la TDM de planification et la position centroïde du volume cible de planification (VCP) ont été utilisées comme référence. Des images de différentes phases respiratoires en 4DCT ont été acquises pour redéfinir les cibles et obtenir les positions flottantes du centroïde du VCP. Conformément aux paramètres d'enregistrement de la TDM de planification et de la TVFC, l'augmentation des données a été réalisée, ce qui a permis d'obtenir 2130 enregistrements expérimentaux pour l'analyse. Nous avons utilisé une approche d'ensemble d'apprentissage multiple par empilement pour ajuster les variations du nuage de points 3D de la surface