DCNet: Densely Connected Deep Convolutional Encoder–Decoder Network for Nasopharyngeal Carcinoma Segmentation

• Published in: Sensors (Basel, Switzerland) Vol. 21; no. 23; p. 7877
• Main Authors: Li, Yang, Han, Guanghui, Liu, Xiujian
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 26.11.2021; MDPI
• Subjects: Ablation; Cancer; Datasets; Deep learning; DenseNet; Machine learning; Magnetic resonance imaging; nasopharyngeal carcinoma segmentation; Radiation therapy; Semantics; Spatial data; supervised learning; Support vector machines; Throat cancer; Tumors
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s21237877

Nasopharyngeal Carcinoma segmentation in magnetic resonance imagery (MRI) is vital to radiotherapy. Exact dose delivery hinges on an accurate delineation of the gross tumor volume (GTV). However, the large-scale variation in tumor volume is intractable, and the performance of current models is mostly unsatisfactory with indistinguishable and blurred boundaries of segmentation results of tiny tumor volume. To address the problem, we propose a densely connected deep convolutional network consisting of an encoder network and a corresponding decoder network, which extracts high-level semantic features from different levels and uses low-level spatial features concurrently to obtain fine-grained segmented masks. Skip-connection architecture is involved and modified to propagate spatial information to the decoder network. Preliminary experiments are conducted on 30 patients. Experimental results show our model outperforms all baseline models, with improvements of 4.17%. An ablation study is performed, and the effectiveness of the novel loss function is validated.