Premium
DVHnet: A deep learning‐based prediction of patient‐specific dose volume histograms for radiotherapy planning
Author(s) -
Chen Xinyuan,
Men Kuo,
Zhu Ji,
Yang Bining,
Li Minghui,
Liu Zhiqiang,
Yan Xuena,
Yi Junlin,
Dai Jianrong
Publication year - 2021
Publication title -
medical physics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.473
H-Index - 180
eISSN - 2473-4209
pISSN - 0094-2405
DOI - 10.1002/mp.14758
Subject(s) - dose volume histogram , nuclear medicine , dosimetry , histogram , radiation therapy , radiation treatment planning , medicine , convolutional neural network , mathematics , artificial intelligence , pattern recognition (psychology) , computer science , radiology , image (mathematics)
Purpose To develop a deep learning method to predict patient‐specific dose volume histograms (DVHs) for radiotherapy planning. Methods Patient data included 180 cases with nasopharyngeal cancer, of which 153 cases were used for training and 27 for testing. A network (named “DVHnet”) based on a convolutional neural network (CNN) was designed for directly predicting DVHs of organs at risk (OARs). Two‐channel images with contoured structures were generated as the inputs for training the model. A one‐dimensional array consisting of 256 continuous volume percentages on a DVH curve for each slice was calculated as the corresponding output. The combined DVH was then calculated. Sixteen OARs were modeled in the study. Prediction accuracy was evaluated against the corresponding DVH curve of ground truth (GT) plans. A global DVH analysis and critical dosimetry metrics for each OAR were calculated for quantitative evaluation. The performance of DVHnet also was evaluated against two baselines: DosemapNet (developed by our research group) and commercial RapidPlan software. Results The predicted mean difference in average dose of all OARs using DVHnet was 0.30 ± 0.95 Gy. And the predicted differences in D2% and D50 can be control within 2.32 and 0.69 Gy. For most OARs, there were no obvious differences between the dosimetric metrics of the predicted and GT values for both DVHnet and DosemapNet ( P ≥ 0.05). Only the predicted D2% of the optic organs for DVHnet, and of brain stem PRV for DosemapNet displayed statistically significant differences. Except for the optic organs, DVHnet performs better than or comparably with RapidPlan. The mean difference in proportion of points of interest was 3.59% ± 7.78%. Conclusions A deep learning network model was developed to automatically extract useful features for accurate prediction of patient‐specific DVH curves directly. The performance of DVHnet was comparable to DosemapNet and RapidPlan.