Homogeneity and Conformity of Neural Network-Based Lung-IMRT Planning

The IMRT planning technique applies the concept of irradiation, which is controlled automatically by a computer. An plan aligned with trial-and-error approach and still involves non-intuitive, iterative steps based on planner’s subjective decision. Neural Network method used in radiotherapy determining plans lung cancer cases. This to predict dose distribution previous data. purpose using this neural network PTV volume validation plan, also predicting for doses that cover 95% target volume. So, can make it easier planner decisions objectively. obtained results show quality produced modelling has homogeneity index (HI) 0,09 ± 0,02, conformity (CI) 1,2 0,27 an average 1,02 0,01 was mean received at organ. maximum at-risk right organ 0,82 0,22 Gy, left 0,75 0,29 heart 0,77 0,14 spinal cord 0,50 Gy.