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

Abstract

This study aimed to develop an automated delineation method of nasopharynx gross tumor volume (GTVnx) for nasopharyngeal carcinoma (NPC) in computed tomography (CT) image for radiotherapy applications. Inspired by ResNet and SENet's strong ability to extract image features, we proposed a modified version of the 3D U-Net model with Res-blocks and SEblock for delineation of GTVnx. Besides, an automatic pre-processing method was proposed to crop the 3D region of interest (ROI) of GTVnx. Radiotherapy simulation CT images and corresponding manually delineated target of 205 NPC patients diagnosed with stage T1-T4 were used as datasets for training. Automated delineation models were generated based on CT combining contrast-enhanced CT (CE-CT) and CT alone, respectively. We compared the automatic delineation results against the manual delineated contours by radiation oncologists with 5-fold cross-validation to evaluate the performance of the proposed model. We also compared with the framework using 3D CNN and 2D DDNN, respectively. Besides, the model generated by one medical group was assessed against the other two separate medical groups. Precision (PR), Sensitivity (SE), Dice Similarity Coefficient (DSC), Average Symmetric Surface Distance (ASSD), and 95% Hausdorff Distance (HD95) are calculated for quantitative evaluation. Experimental results show that the proposed method outperforms other automatic methods on the CT images. Automated delineation models based on CT combining CE-CT is superior to that based on CT alone. The presented method could be useful and robust for the 3D delineation of GTVnx for NPC in CT images during the planning of radiotherapy.

Application of Artificial Intelligence for Nasopharyngeal Carcinoma Management – A Systematic Review

“… 10 , 15 , 16 , 23 , 26 , 27 , 49 , 52 , 54 , 56 , 59–63 The specificity was only reported for prognosis (n=7) 12 , 14 , 28 , 34 , 39 , 40 , 43 and diagnosis (n=15). 10 , 15 , 16 , 23 , 26 , 27 , 49 , 52 , 54 , 56 , 59–63 In addition, the DSC (n=20) 15 , 18 , 22 , 24 , 30–32 , 45–53 , 55 , 65 , 67 , 69 and ASSD (n=10) 18 , 22 , 24 , 31 , 32 , 45 , 46 , 48 , 51 , 69 were the primary metrics reported in studies on auto-contouring ( Figure 2B ).…”

“…The investigation does not differentiate between radiation-induced fibrosis and residual or recurrent tumour. Wang et al (2020) 48 (China) NPC 205 (CT images) Deep learning (Auto-contouring) 1. Feature extraction: Modified 3D U-Net based on Res-block and SE-block To develop a model for automatic delineation of NPC in computed tomography 1.…”

“… ✓ ✓ ✓ ✓ ✓ ✓ Yes No Mohammed et al (2020) 26 ? ✓ ✓ ✓ ✓ ✓ ✓ Yes No Wang et al (2020) 27 ✓ ✓ ✓ ✓ ✓ ✓ ✓ No No Wang et al (2020) 48 ✓ ✓ ✓ ? ✓ ✓ ✓ Yes No Xie et al (2020) 37 ✓ ✓ ✓ ✓ ✓ ✓ ✓ No No Xue et al (2020) 69 ✓ ✓ ✓ ✓ ✓ ✓ ✓ No No Xue et al (2020) 46 ✓ ✓ ✓ ?…”

Geometric and Dosimetric Evaluation of Deep Learning-Based Automatic Delineation on CBCT-Synthesized CT and Planning CT for Breast Cancer Adaptive Radiotherapy: A Multi-Institutional Study

“…We use Res-SE-U-Net ( 31 ) as the automatic delineation network, which is a modified 3D U-Net ( 32 ). Res-SE-U-Net includes the down-sampling path, up-sampling path, and skip-connection layer, which can extract the multiscale features of images.…”

A Comprehensive Review on Radiomics and Deep Learning for Nasopharyngeal Carcinoma Imaging

“…In [ 145 ], Wang proposed a modified version of the 3D U-Net model with Res-blocks and SE-blocks to segment the gross tumour volume of the nasopharynx. The novelty of the research is that an automatic pre-processing method was proposed to crop the 3D region of interest of the nasopharynx gross tumour volume, which improved the efficiency of image pre-processing.…”