Three-Dimensional Dose Prediction for Lung IMRT Patients with Deep Neural Networks: Robust Learning from Heterogeneous Beam Configurations
This work addresses the need for more comprehensive and clinically easier-to-implement automatic planning in radiation therapy for lung cancer patients, though it appears incremental by extending existing methods to handle heterogeneous beam configurations.
The paper tackled the problem of predicting 3D dose distributions for lung IMRT patients by developing a model that incorporates variable beam configurations, achieving a more general approach for automatic planning without needing separate models for different beam settings.
The use of neural networks to directly predict three-dimensional dose distributions for automatic planning is becoming popular. However, the existing methods only use patient anatomy as input and assume consistent beam configuration for all patients in the training database. The purpose of this work is to develop a more general model that, in addition to patient anatomy, also considers variable beam configurations, to achieve a more comprehensive automatic planning with a potentially easier clinical implementation, without the need of training specific models for different beam settings.