A Method for Predicting Dose Distribution of Nasopharyngeal Carcinoma Cases by Multiple Deep Neural Networks

In this paper, we propose a method for predicting dose distribution images of patients with Nasopharyngeal carcinoma (NPC) from contoured computer tomography (CT) images. The proposed system is based on our previous method [1]. The first phase is to obtain the feature maps of 2D dose images of each beam from contoured CT images of a patient by convolutional deep neural network model. In the second phase, dose distribution images are predicted from the obtained feature maps by the integration network. Our modified system predicted dose distribution images accurately. From the experimental results using 80 NPC patients' images, the average number of pixels that satisfy the dose constraints of tumors and OARs regions is 81.9 % and 86.1 %, respectively. The proposed system had a global 3D gamma passing rates varying from 82.1 % to 97.2 % for all regions and an overall mean absolute errors (MAEs) was 1.0 ±1.2. From the obtained results, our modified system is superior to the results obtained in our previous system results and conventional methods. Contribution-The use of the predicted 7-beam weights, as input, into our CNN network leads to improve the predicted dose distribution. Contribution-The use of the predicted 7-beam weights, as input, into our CNN network leads to improve the predicted dose distribution.