RANDOM-FOREST MODEL PREDICTION OF DOSE DISTRIBUTION IN IMRT PLANNING FOR LUNG CANCER

Introduction: Machine-learning models have been widely used to predict dose distribution in therapy planning such as Intensity Modulated Radiation Therapy (IMRT). Random-forest is one of the machine learning models which can reduce output bias by using the average value all of estimators.
Material and Methods: Planning data in Digital Imaging and Communications in Medicine (DICOM) format is exported to Comma Separated Values (CSV). Then, used to random-forest algorithm that will be trained using 7-fold validation and then the model will be evaluated with new data, i.e., data that the model has never seen before. The data evaluated were the parameters to obtain Homogenety Index (HI) for the target organ, whereas the mean and max dose for organs at risk (OARs) were evaluated. Statistical analysis were also carried out to assess the significant difference between the predicted value and the true value.
Results: Random-forest was able to predict the true value with errors evaluated using Mean Absolute Error (MAE) on Planning Target Volume (PTV) features D2 (0.012), D50 (0.015) and D98 (0.018) as well as at OAR features (Dmean and Dmax) of the right lung (0.104 and 0.228), left lung (0.094 and 0.27), heart (0.088 and 0.267), spinal cord (0.069 and 0.121) and (V95) Body (0.094). Based on the results of statistical tests, p >0.05, there is no significant difference between the two data.
Conclusion: Random-forest regressor is able to predict the dose value with the smallest difference in PTV features.