The Accuracy and Radiomics Feature Effects of Multiple U-net-Based Automatic Segmentation Models for Transvaginal Ultrasound Images of Cervical Cancer

doi:10.1007/s10278-022-00620-z

科研成果详情

题名	The Accuracy and Radiomics Feature Effects of Multiple U-net-Based Automatic Segmentation Models for Transvaginal Ultrasound Images of Cervical Cancer
作者	Jin, Juebin1; Zhu, Haiyan 2,3; Teng, Yingyan 4; Ai, Yao5; Xie, Congying5,6; Jin, Xiance5,7
发表日期	2022-08
发表期刊	JOURNAL OF DIGITAL IMAGING 影响因子和分区
语种	英语
原始文献类型	Article ; Early Access
关键词	Automatic segmentation U-net Radiomics Ultrasound images
其他关键词	VARIABILITY ; TARGET
摘要	Ultrasound (US) imaging has been recognized and widely used as a screening and diagnostic imaging modality for cervical cancer all over the world. However, few studies have investigated the U-net-based automatic segmentation models for cervical cancer on US images and investigated the effects of automatic segmentations on radiomics features. A total of 1102 transvaginal US images from 796 cervical cancer patients were collected and randomly divided into training (800), validation (100) and test sets (202), respectively, in this study. Four U-net models (U-net, U-net with ResNet, context encoder network (CE-net), and Attention U-net) were adapted to segment the target of cervical cancer automatically on these US images. Radiomics features were extracted and evaluated from both manually and automatically segmented area. The mean Dice similarity coefficient (DSC) of U-net, Attention U-net, CE-net, and U-net with ResNet were 0.88, 0.89, 0.88, and 0.90, respectively. The average Pearson coefficients for the evaluation of the reliability of US image-based radiomics were 0.94, 0.96, 0.94, and 0.95 for U-net, U-net with ResNet, Attention U-net, and CE-net, respectively, in their comparison with manual segmentation. The reproducibility of the radiomics parameters evaluated by intraclass correlation coefficients (ICC) showed robustness of automatic segmentation with an average ICC coefficient of 0.99. In conclusion, high accuracy of U-net-based automatic segmentations was achieved in delineating the target area of cervical cancer US images. It is feasible and reliable for further radiomics studies with features extracted from automatic segmented target areas.
资助项目	Wenzhou Municipal Science and Technology Bureau [Y20190183]; Zhejiang Engineering Research Center of Intelligent Medicine [2016E10011]; National Natural Science Foundation of China [11675122]
出版者	SPRINGER
出版地	NEW YORK
ISSN	0897-1889
EISSN	1618-727X
卷号	35 期号:4 页码:983-992
DOI	10.1007/s10278-022-00620-z
页数	10
WOS类目	Radiology, Nuclear Medicine & Medical Imaging
WOS研究方向	Radiology, Nuclear Medicine & Medical Imaging
WOS记录号	WOS:000775768000001
收录类别	SCIE ; EI ; SCOPUS ; PUBMED
EI入藏号	20221411913890
EI主题词	Image segmentation
EI分类号	461.6 Medicine and Pharmacology ; 753.1 Ultrasonic Waves
URL	查看原文
PubMed ID	35355160
SCOPUSEID	2-s2.0-85127380013
通讯作者地址	[Xie, Congying]Department of Radiotherapy Center,Wenzhou Medical University First Affiliated Hospital,Shangcai Village,Wenzhou,325000,China ; [Jin, Xiance]Department of Radiotherapy Center,Wenzhou Medical University First Affiliated Hospital,Shangcai Village,Wenzhou,325000,China
Scopus学科分类	Radiological and Ultrasound Technology;Radiology, Nuclear Medicine and Imaging;Computer Science Applications
引用统计	被引频次：2[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	https://kms.wmu.edu.cn/handle/3ETUA0LF/148624
专题	第一临床医学院（信息与工程学院）、附属第一医院基础医学院（机能实验教学中心）附属第二医院附属第一医院_超声影像科第二临床医学院、附属第二医院、育英儿童医院第一临床医学院（信息与工程学院）、附属第一医院_妇产科学_妇科
通讯作者	Xie, Congying; Jin, Xiance
作者单位	1.Department of Medical Engineering,Wenzhou Medical University First Affiliated Hospital,Shangcai Village,Wenzhou,325000,China; 2.Department of Gynecology,Shanghai First Maternal and Infant Hospital,Tongji University School of Medicine,Shanghai,200126,China; 3.Department of Gynecology,Wenzhou Medical University First Affiliated Hospital,Shangcai Village,Wenzhou,325000,China; 4.Department of Ultrasound Imaging,Wenzhou Medical University First Affiliated Hospital,Shangcai Village,Wenzhou,325000,China; 5.Department of Radiotherapy Center,Wenzhou Medical University First Affiliated Hospital,Shangcai Village,Wenzhou,325000,China; 6.Department of Radiation and Medical Oncology,Wenzhou Medical University Second Affiliated Hospital,Wenzhou,325000,China; 7.School of Basic Medical Science,Wenzhou Medical University,Wenzhou,325000,China
第一作者单位	附属第一医院
通讯作者单位	附属第一医院
第一作者的第一单位	附属第一医院
推荐引用方式 GB/T 7714	Jin, Juebin,Zhu, Haiyan,Teng, Yingyan,et al. The Accuracy and Radiomics Feature Effects of Multiple U-net-Based Automatic Segmentation Models for Transvaginal Ultrasound Images of Cervical Cancer[J]. JOURNAL OF DIGITAL IMAGING,2022,35(4):983-992.
APA	Jin, Juebin, Zhu, Haiyan, Teng, Yingyan, Ai, Yao, Xie, Congying, & Jin, Xiance. (2022). The Accuracy and Radiomics Feature Effects of Multiple U-net-Based Automatic Segmentation Models for Transvaginal Ultrasound Images of Cervical Cancer. JOURNAL OF DIGITAL IMAGING, 35(4), 983-992.
MLA	Jin, Juebin,et al."The Accuracy and Radiomics Feature Effects of Multiple U-net-Based Automatic Segmentation Models for Transvaginal Ultrasound Images of Cervical Cancer".JOURNAL OF DIGITAL IMAGING 35.4(2022):983-992.