A comparative study of deep learning-based knowledge-based planning methods for 3D dose distribution prediction of head and neck.

Abstract

In this paper, we compare four novel knowledge-based planning (KBP) algorithms using deep learning to predict three-dimensional (3D) dose distributions of head and neck plans using the same patients' dataset and quantitative assessment metrics. A dataset of 340 oropharyngeal cancer patients treated with intensity-modulated radiation therapy was used in this study, which represents the AAPM OpenKBP - 2020 Grand Challenge dataset. Four 3D convolutional neural network architectures were built. The models were trained on 64% of the data set and validated on 16% for voxel-wise dose predictions: U-Net, attention U-Net, residual U-Net (Res U-Net), and attention Res U-Net. The trained models were then evaluated for their performance on a test data set (20% of the data) by comparing the predicted dose distributions against the ground-truth using dose statistics and dose-volume indices. The four KBP dose prediction models exhibited promising performance with an averaged mean absolute dose error within the body contour <3Gy on 68 plans in the test set. The average difference in predicting the D99 index for all targets was 0.92Gy (p=0.51) for attention Res U-Net, 0.94Gy (p=0.40) for Res U-Net, 2.94Gy (p=0.09) for attention U-Net, and 3.51Gy (p=0.08) for U-Net. For the OARs, the values for the and indices were 2.72Gy (p<0.01) for attention Res U-Net, 2.94Gy (p<0.01) for Res U-Net, 1.10Gy (p<0.01) for attention U-Net, 0.84Gy (p<0.29) for U-Net. All models demonstrated almost comparable performance for voxel-wise dose prediction. KBP models that employ 3D U-Net architecture as a base could be deployed for clinical use to improve cancer patient treatment by creating plans with consistent quality and making the radiotherapy workflow more efficient.