Technical Note: Dose prediction for head and neck radiotherapy using a three-dimensional dense dilated U-net architecture

Purpose Radiation therapy treatment planning is a time-consuming and iterative manual process. Consequently, plan quality varies greatly between and within institutions. Artificial intelligence shows great promise in improving plan quality and reducing planning times. This technical note describes our participation in the American Association of Physicists in Medicine Open Knowledge-Based Planning Challenge (OpenKBP), a competition to accurately predict radiation therapy dose distributions. Methods A three-dimensional (3D) densely connected U-Net with dilated convolutions was developed to predict 3D dose distributions given contoured CT images of head and neck patients as input. While traditional augmentation techniques such as rotations and translations were explored, it was found that training on random patches alone resulted in the greatest model performance. A custom-weighted mean squared error loss function was employed. Finally, an ensemble of best-performing networks was used to generate the final challenge predictions. Results Our team (SuperPod) placed second in the dose stream of the OpenKBP challenge. The average mean absolute difference between the predicted and clinical dose distributions of the testing dataset was 2.56 Gy. On average, the predicted normalized target DVH metrics were within 3% of the clinical plans, and the predicted organ at risk DVH metrics were within 2 Gy of the clinical plans. Conclusions The developed 3D dense dilated U-Net architecture can accurately predict 3D radiotherapy dose distributions and can be used as part of a fully automated radiation therapy planning pipeline.

Automated summary

A 3D densely connected U-Net with dilated convolutions was developed to accurately predict radiation therapy dose distributions in head and neck patients. The team placed second in the OpenKBP challenge, with an average absolute difference of 2.56 Gy between predicted and clinical dose distributions, and high accuracy in target and organ at risk DVH metrics. This model shows promise for improving plan quality and reducing planning times in radiation therapy.