Fully-Automated Segmentation of Nasopharyngeal Carcinoma on Dual-Sequence MRI Using Convolutional Neural Networks

Abstract

In this study, we proposed an automated method based on convolutional neural network (CNN) for nasopharyngeal carcinoma (NPC) segmentation on dual-sequence magnetic resonance imaging (MRI). T1-weighted (T1W) and T2-weighted (T2W) MRI images were collected from 44 NPC patients. We developed a dense connectivity embedding U-net (DEU) and trained the network based on the two-dimensional dual-sequence MRI images in the training dataset and applied post-processing to remove the false positive results. In order to justify the effectiveness of dual-sequence MRI images, we performed an experiment with different inputs in eight randomly selected patients. We evaluated DEU's performance by using a 10-fold cross-validation strategy and compared the results with the previous studies. The Dice similarity coefficient (DSC) of the method using only T1W, only T2W and dual-sequence of 10-fold cross-validation as different inputs were 0.620 ± 0.0642, 0.642 ± 0.118 and 0.721 ± 0.036, respectively. The median DSC in 10-fold cross-validation experiment with DEU was 0.735. The average DSC of seven external subjects was 0.87. To summarize, we successfully proposed and verified a fully automatic NPC segmentation method based on DEU and dual-sequence MRI images with accurate and stable performance. If further verified, our proposed method would be of use in clinical practice of NPC.

Artificial intelligence in musculoskeletal oncological radiology

“…23 Ye et al successfully proposed and verified a fully automatic nasopharyngeal carcinoma segmentation method based on dual-sequence MRI and convolutional neural network. 24 The mean dice similarity coefficient (DSC) of the models with only T1 sequence, only T2 sequence, and dual sequence were 0.620 ± 0.0642, 0.642 ± 0.118, and 0.721 ± 0.036, respectively. The combination of different features acquired from T1 and T2 sequences significantly improved the segmentation accuracy.…”

“…The combination of different features acquired from T1 and T2 sequences significantly improved the segmentation accuracy. 24 Ability to quantitatively extract tumor features has great potential in the process of making diagnosis. With machine learning, Liu et al quantitatively represented radiological traits characteristics of lung nodules and showed improved accuracy of cancer diagnosis in pulmonary nodules.…”

“…The combination of different features acquired from T1 and T2 sequences significantly improved the segmentation accuracy. 24 …”

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

“…[ 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. Furthermore, the tumor volume varies greatly and many of them are small.…”

Non contrast-enhanced imaging as a replacement for contrast-enhanced imaging for MRI automatic delineation of nasopharyngeal carcinoma

“…Nasopharyngeal carcinoma (NPC) is a particularly challenging cancer to delineate because its boundaries can have complex anatomy owing to the many different types of tissues in the surrounding region, including the bone of the skull base. Previous literature has reported successful CNN adaptations in the automatic delineation for primary NPC [17][18][19][20][21], but the work to-date has relied on gadoliniumbased contrast-enhanced (CE) MRI to optimize the result. In addition to the extra scanning time and monetary cost, gadolinium-based contrast agents are being used more sparingly now that gadolinium is known to deposit in the human body, including the brain [22], and the long term effects of this deposition are unknown.…”