Automatic segmentation of gross target volume of nasopharynx cancer using ensemble of multiscale deep neural networks with spatial attention

Abstract

Radiotherapy is the main treatment method for nasopharynx cancer. Delineation of Gross Target Volume (GTV) from medical images is a prerequisite for radiotherapy. As manual delineation is time-consuming and laborious, automatic segmentation of GTV has a potential to improve the efficiency of this process. This work aims to automatically segment GTV of nasopharynx cancer from Computed Tomography (CT) images. However, it is challenged by the small target region, anisotropic resolution of clinical CT images, and the low contrast between the target region and surrounding soft tissues. To deal with these problems, we propose a 2.5D Convolutional Neural Network (CNN) to handle the different in-plane and through-plane resolutions. We also propose a spatial attention module to enable the network to focus on the small target, and use channel attention to further improve the segmentation performance. Moreover, we use a multi-scale sampling method for training so that the networks can learn features at different scales, which are combined with a multi-model ensemble method to improve the robustness of segmentation results. We also estimate the uncertainty of segmentation results based on our model ensemble, which is of great importance for indicating the reliability of automatic segmentation results for radiotherapy planning. Experiments with 2019 MICCAI StructSeg dataset showed that (1) Our proposed 2.5D network has a better performance on images with anisotropic resolution than the commonly used 3D networks. (2) Our attention mechanism can make the network pay more attention to the small GTV region and improve the segmentation accuracy. (3) The proposed multi-scale model ensemble achieves more robust results, and it can simultaneously obtain uncertainty information that can indicate potential mis-segmentations for better clinical decisions.