The Tumor Target Segmentation of Nasopharyngeal Cancer in CT Images Based on Deep Learning Methods

Abstract

Radiotherapy is the main treatment strategy for nasopharyngeal carcinoma. A major factor affecting radiotherapy outcome is the accuracy of target delineation. Target delineation is time-consuming, and the results can vary depending on the experience of the oncologist. Using deep learning methods to automate target delineation may increase its efficiency. We used a modified deep learning model called U-Net to automatically segment and delineate tumor targets in patients with nasopharyngeal carcinoma. Patients were randomly divided into a training set (302 patients), validation set (100 patients), and test set (100 patients). The U-Net model was trained using labeled computed tomography images from the training set. The U-Net was able to delineate nasopharyngeal carcinoma tumors with an overall dice similarity coefficient of 65.86% for lymph nodes and 74.00% for primary tumor, with respective Hausdorff distances of 32.10 and 12.85 mm. Delineation accuracy decreased with increasing cancer stage. Automatic delineation took approximately 2.6 hours, compared to 3 hours, using an entirely manual procedure. Deep learning models can therefore improve accuracy, consistency, and efficiency of target delineation in T stage, but additional physician input may be required for lymph nodes.

Automated delineation of nasopharynx gross tumor volume for nasopharyngeal carcinoma by plain CT combining contrast-enhanced CT using deep learning

“…For mean DSC, our method outperformed Lin and Men's methods (73.72% vs. 72.05% vs. 67.35%). In addition, the 2D U-Net proposed by Li et al (2015), is implemented to automatically delineate tumor of NPC patients in their datasets with DSC of 71.78% (Li et al, 2019). It has been reported in (Zou et al, 2004) that a DSC value >70% indicates good segmentation performance (Zou et al, 2004).…”

“…In this study, the proposed method was compared with three classic methods: 3D CNN (Lin et al, 2019), 2D DDNN (Men et al, 2017), 2D U-Net (Li et al, 2019). The models except for 2D U-Net were trained and validated on the same CT datasets of our department to ensure a neutral comparison.…”

“…Li et al constructed a modified 2D U-Net model by CT images to automatically segment and delineate tumor targets of NPC patients from early-stage to advanced-stage. However, the overall DSC for GTVnx delineation was 71.78%, and delineation accuracy decreased with increasing tumor stage (Li et al, 2019). However, the above three methods used 2D segmentation model, which lacked the use of relevant information between CT images layers.…”

A Collaborative Dictionary Learning Model for Nasopharyngeal Carcinoma Segmentation on Multimodalities MR Sequences

“…MvDA-VC method has achieved good performance in addressing the problem of object recognition from multiple views Zhao et al [ 12 ]: it uses fully convolutional networks with an auxiliary path to achieve automatic segmentation of NPC on dual-modality PET-CT images. The proposed method improves NPC segmentation by guiding the training of lower layers by auxiliary paths Li et al [ 13 ]: it proposes a modified version of the U-Net, which performs well on NPC segmentation by modifying the downsampling layers and upsampling layers to have a similar learning ability and predict the same spatial resolution as the source image …”

“…[ 12 ] used fully convolutional networks with auxiliary paths to achieve automatic segmentation of NPC on PET-CT images. [ 13 ] used a modified U-Net model to automatically segment NPC on CT images from 502 patients. [ 14 ] proposed an automated method based on CNN for NPC segmentation on dual-sequence MRI (i.e., T1-w and T2-w) from 44 patients.…”