Tumor Segmentation in Contrast-Enhanced Magnetic Resonance Imaging for Nasopharyngeal Carcinoma: Deep Learning with Convolutional Neural Network

Abstract

Objectives To evaluate the application of a deep learning architecture, based on the convolutional neural network (CNN) technique, to perform automatic tumor segmentation of magnetic resonance imaging (MRI) for nasopharyngeal carcinoma (NPC). Materials and Methods In this prospective study, 87 MRI containing tumor regions were acquired from newly diagnosed NPC patients. These 87 MRI were augmented to >60,000 images. The proposed CNN network is composed of two phases: feature representation and scores map reconstruction. We designed a stepwise scheme to train our CNN network. To evaluate the performance of our method, we used case-by-case leave-one-out cross-validation (LOOCV). The ground truth of tumor contouring was acquired by the consensus of two experienced radiologists. Results The mean values of dice similarity coefficient, percent match, and their corresponding ratio with our method were 0.89±0.05, 0.90±0.04, and 0.84±0.06, respectively, all of which were better than reported values in the similar studies. Conclusions We successfully established a segmentation method for NPC based on deep learning in contrast-enhanced magnetic resonance imaging. Further clinical trials with dedicated algorithms are warranted.

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

“…The results of previous studies about NPC segmentation in MRI are shown in Table 2. The DSC in the study by Li et al (16) was 0.736, however in their study they manually selected the images of tumor for segmentation, which means that their method was semi-automatic. Deng…”

“…To overcome these limitations, other studies have applied fully convolutional network (FCN) (13) or U-net (14) structure in NPC segmentation. Men et al (15) and Li et al (16) applied an improved U-net to segment NPC in an end-to-end manner. The fully convolutional structure of U-net allows the network to realize pixel-wise segmentation and to input the whole image for NPC segmentation without extracting patches.…”

Winter is over: The use of Artificial Intelligence to individualise radiation therapy for breast cancer

“…These DL algorithms used neural networks to identify and generate contouring patterns to be combined with information from multiple sources, in order to generate volumes on CT-images that can subsequently be validated for RT dose planning by the physician. DL-based contouring has been widely explored in head & neck, lung, and prostate cancer, showing important benefit in terms of time-sparing combined with an improved inter- and intra-observer contouring variability [ 17 , [24] , [25] , [26] , [27] , [28] , [29] ].…”

Predictive Analytics in Spine Oncology Research: First Steps, Limitations, and Future Directions

“…Use of this technology saves clinicians time and produces good quality radiation planning contours. [51][52][53] The same technology can potentially be used for spine tumors to increase radiation treatment accuracy, target delineation, and standardize protocols among institutions.…”