RapidBrachyDL: Rapid Radiation Dose Calculations in Brachytherapy via Deep Learning.

Researchers

Journal

Modalities

Models

Abstract

Detailed and accurate absorbed dose calculations from radiation interactions with the human body can be obtained with the Monte Carlo (MC) method. However, the MC method can be slow for use in the time-sensitive clinical workflow. The aim of this study was to provide a solution to the accuracy-time trade-off for 192Ir -based high dose rate brachytherapy by utilizing deep learning.
RapidBrachyDL, a three-dimensional deep convolutional neural network (CNN) model is proposed to predict dose distributions calculated with the MC method given a patient’s computerized tomography images, contours of clinical target volume (CTV) and organs at risk, and treatment plan. In total 61 prostate patients and 10 cervical patients were included in this study, with 47 prostate patient’s data used to train the model.
Compared with ground truth MC simulations, the predicted dose distributions by RapidBrachyDL showed a consistent shape in the dose volume histograms (DVH), comparable DVH dosimetric indices including 0.73% difference for prostate CTV D90, 1.1% for rectum D2cc, 1.45% for urethra D0.1cc and 1.05% for bladder D2cc, and substantially smaller prediction time, a factor of 300 speed up. RapidBrachyDL also demonstrated good generalization performance to cervical data with 1.73%, 2.46%, 1.68% and 1.74% difference for CTV D90, rectum D2cc, sigmoid D2cc and bladder D2cc respectively, which was unseen during the training.
Deep CNN-based dose estimation is a promising method for patient specific brachytherapy dosimetry. Desired radiation quantities can be obtained with accuracies arbitrarily close to those of the source MC algorithm but with much faster computation times. The idea behind deep CNN-based dose estimation can be safely extended to other radiation sources and tumour sites by following a similar training process.
Copyright © 2020 Elsevier Inc. All rights reserved.