A framework for 3D radiotherapy dose prediction using the deep learning approach

Abstrak

Cancer is known as a dangerous disease to humans with a very high death rate. There are a lot of cancer treatment methods that have been studied and applied in the world. One of the main methods is using radiation beams to kill cancer cells. This method, also known as radiotherapy, requires experts having a high level of skill and experience. Our work focuses on the 3D dose prediction problem in radiotherapy by proposing a framework aiming to create a medical intelligent system for this problem. To do that, we created a convolutional neural network based on ResNet and U-Net to generate the predicted radiation dose. To improve the quality of the training phase, we also applied some data processing techniques based on the characteristics of the 3D computed tomography (CT) data. The experiment used the dataset from patients who were cancer-treated with radiotherapy in the OpenKBP competition. The results achieved good evaluating metrics, the first is by the Dose-score and the second is by the dose-volume histogram (DVH) score. From the training result, we built the medical system supporting 3D dose prediction and visualizing the result as slices in heatmap form.