Dilated Adversarial U-Net Network for automatic gross tumor volume segmentation of nasopharyngeal carcinoma

Nasopharyngeal carcinoma (NPC) is a malignant tumor in the nasopharyngeal epithelium and is mainly treated by radiotherapy. The accurate delineation of the target tumor can greatly improve the radiotherapy effectiveness. However, due to the small size of the NPC imaging volume, the scarcity of labeled samples, the low signal-to-noise ratio in small target areas and the lack of detailed features, automatic gross tumor volume (GTV) delineation inspired by advances in domain adaption for high-resolution image processing has become a great challenge. In addition, since computed tomography (CT) images have the low resolution of soft tissues, it is difficult to identify small volume tumors, and segmentation accuracy of this kind of small GTV is very low. In this paper, we propose an automatic segmentation model based on adversarial network and U-Net for NPC delineation. Specifically, we embed adversarial classification learning into a segmentation network to balance the distribution differences between the small targets in the sample and the large target categories. To reduce the loss weight of large target categories with large samples, and simultaneously increase the weight of small target categories, we design a new U-Net based on focal loss as a GTV segmentation model for adjusting the effect of different categories on the final loss. This method can effectively solve the feature bias caused by the imbalance of the target volume distribution. Furthermore, we conduct a pre-processing of images using an algorithm based on distribution histograms to ensure that the same or approximate CT value represents the same organization. In order to evaluate our proposed method, we perform experiments on the open datasets from StructSeg2019 and the datasets provided by Sichuan Provincial Cancer Hospital. The results of the comparison with some typical up-to-date methods demonstrate that our model can significantly enhance detection accuracy and sensitivity for NPC segmentation.