Zhiqiang Liu1, Xinyuan Chen1, Kuo Men1, Junlin Yi1, Jianrong Dai1. 1. National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, No. 17 Panjiayuannanli, Chaoyang District, Beijing, 100021, China.
Abstract
PURPOSE: To develop a deep learning-based model to predict achievable dose-volume histograms (DVHs) of organs at risk (OARs) for automation of inverse planning. METHODS: The model was based on a connected residual deconvolution network (CResDevNet) and compared with UNet as a baseline. The DVHs of OARs are dependent on patient anatomical features of the planning target volumes and OARs, and these spatial relationships can be learned automatically from prior high-quality plans. The contours of planning target volumes and OARs were parsed from the plan database and used as the input to the model, and the dose-area histograms (DAHs) of the OARs were output from the model. The model was trained from scratch by correlating anatomical features with DAHs of OARs, then accumulating these histograms to obtain the final predicted DVH for each OAR. Helical tomotherapy plans for 170 nasopharyngeal cancer patients were used to train and validate the model. An additional 60 patient treatment plans were used to test the predictive accuracy of the model. The DVHs and dose-volume indices (DVIs) of clinical interest for each OAR in the testing dataset were predicted to evaluate the accuracy of the models. The mean absolute errors in the DVIs for each OAR were calculated using each model and statistically compared using a paired-samples t-test. Dice similarity coefficients for areas of the DVHs were also evaluated. RESULTS: Dose-volume histograms of 21 OARs in nasopharyngeal cancer were predicted using the models. For each patient, 63 DVIs for all OARs were calculated. Using the 60 patient treatment plans in the testing dataset, 79% and 73% of the DVIs predicted using the CResDevNet and UNet models, respectively, were within 5% of the clinical values. The median value of the DVIs' mean absolute errors was 3.2 ± 2.5% and 3.7 ± 2.9% for the CResDevNet and UNet models, respectively. The average dice similarity coefficient for all OARs was 0.965 using the CResDevNet model and 0.958 using the UNet model. CONCLUSIONS: A deep learning model was developed for predicting achievable DVHs of OARs. The prediction accuracy of the CResDevNet model was evaluated using a planning database of nasopharyngeal cancer cases and shown to be more accurate than the UNet model. Prediction accuracy was also higher for larger-volume OARs. The model can be used for automation of inverse planning and quality assessment of individual treatment plans.
PURPOSE: To develop a deep learning-based model to predict achievable dose-volume histograms (DVHs) of organs at risk (OARs) for automation of inverse planning. METHODS: The model was based on a connected residual deconvolution network (CResDevNet) and compared with UNet as a baseline. The DVHs of OARs are dependent on patient anatomical features of the planning target volumes and OARs, and these spatial relationships can be learned automatically from prior high-quality plans. The contours of planning target volumes and OARs were parsed from the plan database and used as the input to the model, and the dose-area histograms (DAHs) of the OARs were output from the model. The model was trained from scratch by correlating anatomical features with DAHs of OARs, then accumulating these histograms to obtain the final predicted DVH for each OAR. Helical tomotherapy plans for 170 nasopharyngeal cancerpatients were used to train and validate the model. An additional 60 patient treatment plans were used to test the predictive accuracy of the model. The DVHs and dose-volume indices (DVIs) of clinical interest for each OAR in the testing dataset were predicted to evaluate the accuracy of the models. The mean absolute errors in the DVIs for each OAR were calculated using each model and statistically compared using a paired-samples t-test. Dice similarity coefficients for areas of the DVHs were also evaluated. RESULTS: Dose-volume histograms of 21 OARs in nasopharyngeal cancer were predicted using the models. For each patient, 63 DVIs for all OARs were calculated. Using the 60 patient treatment plans in the testing dataset, 79% and 73% of the DVIs predicted using the CResDevNet and UNet models, respectively, were within 5% of the clinical values. The median value of the DVIs' mean absolute errors was 3.2 ± 2.5% and 3.7 ± 2.9% for the CResDevNet and UNet models, respectively. The average dice similarity coefficient for all OARs was 0.965 using the CResDevNet model and 0.958 using the UNet model. CONCLUSIONS: A deep learning model was developed for predicting achievable DVHs of OARs. The prediction accuracy of the CResDevNet model was evaluated using a planning database of nasopharyngeal cancer cases and shown to be more accurate than the UNet model. Prediction accuracy was also higher for larger-volume OARs. The model can be used for automation of inverse planning and quality assessment of individual treatment plans.