Encrypted login | home

Program Information

Patient Features Based Dosimetric Pareto Front Prediction In Esophagus Cancer Radiotherapy

no image available
J Wang

J Wang1*, X Jin2 , K Zhao1 , J Peng1 , W Hu1 , (1) Fudan University Shanghai Cancer Center, Shanghai, Shanghai, (2) 1st Affiliated Hospital of Wenzhou Medical College, Wenzhou

Presentations

TU-C-17A-10 Tuesday 10:15AM - 12:15PM Room: 17A

Purpose: The purpose of this study is to study the feasibility of the dosimetric pareto front (PF) prediction based on patient anatomic and dosimetric parameters for esophagus cancer patients.

Methods: Sixty esophagus patients in our institution were enrolled in this study. A total 2920 IMRT plans were created to generated PF for each patient. On average, each patient had 48 plans. The anatomic and dosimetric features were extracted from those plans. The mean lung dose (MLD), mean heart dose (MHD), spinal cord max dose and PTV homogeneous index (PTVHI) were recorded for each plan. The principal component analysis (PCA) was used to extract overlap volume histogram (OVH) features between PTV and other critical organs. The full dataset was separated into two parts include the training dataset and the validation dataset. The prediction outcomes were the MHD and MLD for the current study. The spearman rank correlation coefficient was used to evaluate the correlation between the anatomical features and dosimetric features. The PF was fit by the the stepwise multiple regression method. The crossâ‚‹validation method was used to evaluation the model.

Results: The mean prediction error of the MHD was 465 cGy with 100 repetitions. The most correlated factors were the first principal components of the OVH between heart and PTV, and the overlap between heart and PTV in Zâ‚‹axis. The mean prediction error of the MLD was 195 cGy. The most correlated factors were the first principal components of the OVH between lung and PTV, and the overlap between lung and PTV in Z-axis.

Conclusion: It is feasible to use patients anatomic and dosimetric features to generate a predicted PF. Additional samples and further studies were required to get a better prediction model.


Contact Email: