Open Access

ARTICLE

MRI Image Segmentation of Nasopharyngeal Carcinoma Using Multi-Scale Cascaded Fully Convolutional Network

by Yanfen Guo^1,2, Zhe Cui¹, Xiaojie Li^2,*, Jing Peng^1,2, Jinrong Hu², Zhipeng Yang³, Tao Wu², Imran Mumtaz⁴

1 Chengdu Institute of Computer Application, University of Chinese Academy of Sciences, Chengdu, 610041, China
2 Department of Computer Science, Chengdu University of Information Technology, 610025, China
3 Department of Electronic Engineering, Chengdu University of Information Technology, 610025, China
4 Department of Computer Science, University of Agriculture Faisalabad, Faisalabad, 38000, Pakistan

* Corresponding Author: Xiaojie Li. Email:

Intelligent Automation & Soft Computing 2022, 31(3), 1771-1782. https://doi.org/10.32604/iasc.2022.019785

Received 25 April 2021; Accepted 27 May 2021; Issue published 09 October 2021

Abstract

Nasopharyngeal carcinoma (NPC) is one of the most common malignant tumors of the head and neck, and its incidence is the highest all around the world. Intensive radiotherapy using computer-aided diagnosis is the best technique for the treatment of NPC. The key step of radiotherapy is the delineation of the target areas and organs at risk, that is, tumor images segmentation. We proposed the segmentation method of NPC image based on multi-scale cascaded fully convolutional network. It used cascaded network and multi-scale feature for a coarse-to-fine segmentation to improve the segmentation effect. In coarse segmentation, image blocks and data augmentation were used to compensate for the shortage of training samples. In fine segmentation, Atrous Spatial Pyramid Pooling (ASPP) was used to increase the receptive field and image feature transfer, which was added in the Dense block of DenseNet. In the process of up-sampling, the features of multiple views were fused to reduce false positive samples. Additionally, in order to improve the class imbalance problem, Focal Loss was used to weight the loss function of tumor voxel distance because it could reduce the weight of background category samples. The cascaded network can alleviate the problem of gradient disappearance and obtain a smoother boundary. The experimental results were quantitatively analyzed by DSC, ASSD and F1_score values, and the results showed that the proposed method was effective for nasopharyngeal carcinoma segmentation compared with other methods in this paper.

---

Keywords

---