Automatic detection and recognition of nasopharynx gross tumour volume (GTVnx) by deep learning for nasopharyngeal cancer radiotherapy through magnetic resonance imaging

doi:10.1186/s13014-023-02260-1

科研成果详情

题名	Automatic detection and recognition of nasopharynx gross tumour volume (GTVnx) by deep learning for nasopharyngeal cancer radiotherapy through magnetic resonance imaging
作者	Wang, Yandan 1; Chen, Hehe 2; Lin, Jie 3; Dong, Shi 4; Zhang, Wenyi5
发表日期	2023-05-08
发表期刊	RADIATION ONCOLOGY 影响因子和分区
语种	英语
原始文献类型	Article
关键词	Deep learning Automatic detection and recognition Nasopharyngeal cancer Magnetic resonance imaging Target delineation
其他关键词	DELINEATION
摘要	BackgroundIn this study, we propose the deep learning model-based framework to automatically delineate nasopharynx gross tumor volume (GTVnx) in MRI images.MethodsMRI images from 200 patients were collected for training-validation and testing set. Three popular deep learning models (FCN, U-Net, Deeplabv3) are proposed to automatically delineate GTVnx. FCN was the first and simplest fully convolutional model. U-Net was proposed specifically for medical image segmentation. In Deeplabv3, the proposed Atrous Spatial Pyramid Pooling (ASPP) block, and fully connected Conditional Random Field(CRF) may improve the detection of the small scattered distributed tumor parts due to its different scale of spatial pyramid layers. The three models are compared under same fair criteria, except the learning rate set for the U-Net. Two widely applied evaluation standards, mIoU and mPA, are employed for the detection result evaluation.ResultsThe extensive experiments show that the results of FCN and Deeplabv3 are promising as the benchmark of automatic nasopharyngeal cancer detection. Deeplabv3 performs best with the detection of mIoU 0.8529 +/- 0.0017 and mPA 0.9103 +/- 0.0039. FCN performs slightly worse in term of detection accuracy. However, both consume similar GPU memory and training time. U-Net performs obviously worst in both detection accuracy and memory consumption. Thus U-Net is not suggested for automatic GTVnx delineation.ConclusionsThe proposed framework for automatic target delineation of GTVnx in nasopharynx bring us the desirable and promising results, which could not only be labor-saving, but also make the contour evaluation more objective. This preliminary results provide us with clear directions for further study.
出版者	BMC
ISSN	1748-717X
EISSN	1748-717X
卷号	18 期号:1
DOI	10.1186/s13014-023-02260-1
页数	9
WOS类目	Oncology ; Radiology, Nuclear Medicine & Medical Imaging
WOS研究方向	Oncology ; Radiology, Nuclear Medicine & Medical Imaging
WOS记录号	WOS:000983995100003
收录类别	SCIE ; PUBMED ; SCOPUS
URL	查看原文
PubMed ID	37158943
SCOPUSEID	2-s2.0-85158138988
通讯作者地址	[Zhang, Wenyi]Department of Radiotherapy,The First Affiliated Hospital of Wenzhou Medical University,WenZhou,China
Scopus学科分类	Oncology;Radiology, Nuclear Medicine and Imaging
引用统计
文献类型	期刊论文
条目标识符	https://kms.wmu.edu.cn/handle/3ETUA0LF/180067
专题	附属第一医院其他_定理临床学院（温州市中心医院）
通讯作者	Zhang, Wenyi
作者单位	1.Faculty of Computer Science and Technology,Wenzhou University,WenZhou,China; 2.College of Intelligent Manufacturing,Wenzhou Polytechnic,Wenzhou,China; 3.Department of Radiology,The First Affiliated Hospital of Wenzhou Medical University,WenZhou,China; 4.Department of Radiotherapy,Wenzhou Central Hospital,Dingli Clinical Medical School of Wenzhou Medical University,Wenzhou,China; 5.Department of Radiotherapy,The First Affiliated Hospital of Wenzhou Medical University,WenZhou,China
通讯作者单位	附属第一医院
推荐引用方式 GB/T 7714	Wang, Yandan,Chen, Hehe,Lin, Jie,et al. Automatic detection and recognition of nasopharynx gross tumour volume (GTVnx) by deep learning for nasopharyngeal cancer radiotherapy through magnetic resonance imaging[J]. RADIATION ONCOLOGY,2023,18(1).
APA	Wang, Yandan, Chen, Hehe, Lin, Jie, Dong, Shi, & Zhang, Wenyi. (2023). Automatic detection and recognition of nasopharynx gross tumour volume (GTVnx) by deep learning for nasopharyngeal cancer radiotherapy through magnetic resonance imaging. RADIATION ONCOLOGY, 18(1).
MLA	Wang, Yandan,et al."Automatic detection and recognition of nasopharynx gross tumour volume (GTVnx) by deep learning for nasopharyngeal cancer radiotherapy through magnetic resonance imaging".RADIATION ONCOLOGY 18.1(2023).