PO35

Purpose The purpose of this work is to develop a voxel-wise dose prediction system using convolutional neural network (CNN) for cervical cancer high-dose-rate (HDR) intracavitary brachytherapy treatment planning with tandem-and-ovoid (T&O) or tandem-and-ring (T&R) applicators. Materials and Methods A 3D U-NET CNN was implemented to generate voxel-wise dose predictions based on high-risk clinical target volume (HRCTV) and organs at risk (OAR) contour information. A multi-institutional cohort of 77 retrospective clinical HDR brachytherapy plans treated to a prescription dose in the range of 4.8-7.0 Gy/fx was used in this study. Those plans were randomly divided into 60%/20%/20% as training, validating, and testing cohorts. Data augmentation techniques like flip diagonally, flip left and right, flipping up and down, and rotating 90 degrees were implemented in the training and validation cohort data to increase the number of plans to 252. The model was trained using the mean-squared loss function, Adam optimization algorithm, a learning rate of 0.001, 250 epochs, and a batch size of 8. The model performance was evaluated on the testing dataset by analyzing the outcomes in terms of maximum dose values and derived dose-volume-histogram (DVH) indices from 3D dose distributions and comparing the generated dose distributions against the ground-truth dose distributions using dose statistics and clinically meaningful dosimetric indices. Results The proposed 3D U-Net model showed competitive accuracy in predicting 3D dose distributions that closely resemble the ground truth dose distributions. The average value of mean absolute error was 0.108±3.617 Gy for HRCTV, 0.074±1.315 Gy for bladder, 0.093±0.981 Gy for rectum, and 0.035±2.789 Gy for sigmoid. The median absolute error was 0.126 Gy for HRCTV, 0.041 Gy for the bladder, 0.0013 Gy for rectum, and 0.019 Gy for sigmoid. Our results showed that the predicted mean D2cc OAR doses in the bladder, rectum, sigmoid were 3.51±1.25, 3.11±1.23 and 4.02±2.23 Gy in comparison to 4.21±1.23, 4.20±1.02, 4.80±1.59 Gy in clinical plans respectively. The predicted D90 of the HRCTV was 6.72±0.99 Gy in comparison with 6.83±1.72 Gy in clinical plans. The predicted maximum dose to bladder, sigmoid, and rectum were 7.51±1.10, 3.81±1.27, 3.61±1.16 Gy in comparison to 7.33±1.03, 4.66±2.06, 4.33±1.75 Gy in clinical plans, respectively, indicating a good potential to predict useful dosimetric indices and facilitate an improvement in brachytherapy treatment workflow. The proposed model needs less than 5 seconds to predict a full 3D dose distribution of 64 × 64 × 64 voxels for any new patient plan, thus making it sufficient for near real-time applications and aid in decision-making in clinic. Conclusions The 3D U-Net model we have implemented demonstrates competitive capability in predicting accurate dose distributions and DVH indices with consistent quality. The proposed model can be used to predict 3D dose distributions for near real-time decision-making, before planning, for quality assurance, and for guiding future automated planning for improved plan consistency, quality, and planning efficiency. Our next goal is to implement this model for direction modulated brachytherapy (DMBT) tandem applicator-based plans. The purpose of this work is to develop a voxel-wise dose prediction system using convolutional neural network (CNN) for cervical cancer high-dose-rate (HDR) intracavitary brachytherapy treatment planning with tandem-and-ovoid (T&O) or tandem-and-ring (T&R) applicators. A 3D U-NET CNN was implemented to generate voxel-wise dose predictions based on high-risk clinical target volume (HRCTV) and organs at risk (OAR) contour information. A multi-institutional cohort of 77 retrospective clinical HDR brachytherapy plans treated to a prescription dose in the range of 4.8-7.0 Gy/fx was used in this study. Those plans were randomly divided into 60%/20%/20% as training, validating, and testing cohorts. Data augmentation techniques like flip diagonally, flip left and right, flipping up and down, and rotating 90 degrees were implemented in the training and validation cohort data to increase the number of plans to 252. The model was trained using the mean-squared loss function, Adam optimization algorithm, a learning rate of 0.001, 250 epochs, and a batch size of 8. The model performance was evaluated on the testing dataset by analyzing the outcomes in terms of maximum dose values and derived dose-volume-histogram (DVH) indices from 3D dose distributions and comparing the generated dose distributions against the ground-truth dose distributions using dose statistics and clinically meaningful dosimetric indices. The proposed 3D U-Net model showed competitive accuracy in predicting 3D dose distributions that closely resemble the ground truth dose distributions. The average value of mean absolute error was 0.108±3.617 Gy for HRCTV, 0.074±1.315 Gy for bladder, 0.093±0.981 Gy for rectum, and 0.035±2.789 Gy for sigmoid. The median absolute error was 0.126 Gy for HRCTV, 0.041 Gy for the bladder, 0.0013 Gy for rectum, and 0.019 Gy for sigmoid. Our results showed that the predicted mean D2cc OAR doses in the bladder, rectum, sigmoid were 3.51±1.25, 3.11±1.23 and 4.02±2.23 Gy in comparison to 4.21±1.23, 4.20±1.02, 4.80±1.59 Gy in clinical plans respectively. The predicted D90 of the HRCTV was 6.72±0.99 Gy in comparison with 6.83±1.72 Gy in clinical plans. The predicted maximum dose to bladder, sigmoid, and rectum were 7.51±1.10, 3.81±1.27, 3.61±1.16 Gy in comparison to 7.33±1.03, 4.66±2.06, 4.33±1.75 Gy in clinical plans, respectively, indicating a good potential to predict useful dosimetric indices and facilitate an improvement in brachytherapy treatment workflow. The proposed model needs less than 5 seconds to predict a full 3D dose distribution of 64 × 64 × 64 voxels for any new patient plan, thus making it sufficient for near real-time applications and aid in decision-making in clinic. The 3D U-Net model we have implemented demonstrates competitive capability in predicting accurate dose distributions and DVH indices with consistent quality. The proposed model can be used to predict 3D dose distributions for near real-time decision-making, before planning, for quality assurance, and for guiding future automated planning for improved plan consistency, quality, and planning efficiency. Our next goal is to implement this model for direction modulated brachytherapy (DMBT) tandem applicator-based plans.