Ultrasound-based radiomics score: a potential biomarker for the prediction of microvascular invasion in hepatocellular carcinoma

doi:10.1007/s00330-018-5797-0

	Ultrasound-based radiomics score: a potential biomarker for the prediction of microvascular invasion in hepatocellular carcinoma
	Hu, Hang-tong 1; Wang, Zhu 1; Huang, Xiao-wen 2; Chen, Shu-ling 1; Zheng, Xin 1; Ruan, Si-min 1; Xie, Xiao-yan 1; Lu, Ming-de 3,4; Yu, Jie 5; Tian, Jie 6
刊名	EUROPEAN RADIOLOGY
	2019-06-01
卷号	29 期号:6 页码:2890-2901
关键词	Nomogram Radiomics Ultrasonography
ISSN号	0938-7994
DOI	10.1007/s00330-018-5797-0
通讯作者	Wang, Wei(wangw73@mail.sysu.edu.cn) ; Kuang, Ming(kuangm@mail.sysu.edu.cn)
英文摘要	PurposeTo develop an ultrasound (US)-based radiomics score for preoperative prediction of microvascular invasion (MVI) in hepatocellular carcinoma (HCC).MethodsBetween January 1, 2012, and October 31, 2017, a total of 482 HCC patients who underwent contrast-enhanced ultrasound (CEUS) were retrospectively reviewed. The study population was divided into a training cohort (n=341) and a validation cohort (n=141) based on a cutoff time of January 1, 2016. Radiomics features were extracted from the grayscale US images of HCC. After features selection, a radiomics score was developed from the training cohort. The incremental value of the radiomics score to the clinic-pathological factors for MVI prediction was assessed in the validation cohort with respect to discrimination, calibration, and clinical usefulness.ResultsThe US-based radiomics score consisted of six selected features. Multivariate logistic regression analysis showed that the radiomics score, alpha-fetoprotein (AFP), and tumor size were independent predictors of MVI. The radiomics nomogram (based on the three factors) showed better performance for MVI detection (area under the curve [AUC] 0.731[0.647, 0.815] than the clinical nomogram (based on AFP and tumor size) (0.634 [0.543, 0.724]) (p=0.015). Both nomograms showed good calibration. Decision curve analysis demonstrated that in terms of clinical usefulness, the radiomics nomogram outperformed the clinical nomogram.ConclusionThe US-based radiomics score was an independent predictor of MVI in HCC. Combining the radiomics score with clinical factors improved the prediction efficacy.Key points center dot Radiomics can be applied in US images.center dot US-based radiomics score was an independent predictor of MVI.center dot Radiomics nomogram incorporated with the radiomics score showed good performance for MVI prediction.
资助项目	National Nature Science Foundation of China[81701701] ; Guangdong Natural Science Foundation[2017A030313661] ; Training Project for Young Teacher of Sun Yat-sen University[16YKPY37] ; Guangdong Science and Technology Foundation[2017A020215195]
WOS关键词	CONTRAST-ENHANCED ULTRASOUND ; COMPUTER-AIDED DIAGNOSIS ; GENE-EXPRESSION PROGRAMS ; LIVER-TRANSPLANTATION ; PREOPERATIVE CT ; CANCER ; RESECTION ; RECURRENCE ; SURVIVAL ; CLASSIFICATION
WOS研究方向	Radiology, Nuclear Medicine & Medical Imaging
语种	英语
出版者	SPRINGER
WOS记录号	WOS:000467646300017
资助机构	National Nature Science Foundation of China ; Guangdong Natural Science Foundation ; Training Project for Young Teacher of Sun Yat-sen University ; Guangdong Science and Technology Foundation
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/24581]
专题	中国科学院自动化研究所
通讯作者	Wang, Wei; Kuang, Ming
作者单位	1.Sun Yat Sen Univ, Affiliated Hosp 1, Inst Diagnost & Intervent Ultrasound, Dept Med Ultrason, 58 Zhongshan Rd 2, Guangzhou, Guangdong, Peoples R China 2.Guangzhou Univ Chinese Med, Zhongshan Hosp Tradit Chinese Med, Dept Ultrasonog, Zhongshan, Peoples R China 3.Sun Yat Sen Univ, Affiliated Hosp 1, Div Intervent Ultrasound, Guangzhou, Guangdong, Peoples R China 4.Sun Yat Sen Univ, Affiliated Hosp 1, Dept Liver Surg, Guangzhou, Guangdong, Peoples R China 5.Chinese Peoples Liberat Army Gen Hosp, Dept Intervent Ultrasound, Beijing 100853, Peoples R China 6.Chinese Acad Sci, Key Lab Mol Imaging, Beijing, Peoples R China 7.Sun Yat Sen Univ, Affiliated Hosp 1, Dept Hepatobiliary Surg, 58 Zhongshan Rd 2, Guangzhou 510080, Guangdong, Peoples R China
推荐引用方式 GB/T 7714	Hu, Hang-tong,Wang, Zhu,Huang, Xiao-wen,et al. Ultrasound-based radiomics score: a potential biomarker for the prediction of microvascular invasion in hepatocellular carcinoma[J]. EUROPEAN RADIOLOGY,2019,29(6):2890-2901.
APA	Hu, Hang-tong.,Wang, Zhu.,Huang, Xiao-wen.,Chen, Shu-ling.,Zheng, Xin.,...&Kuang, Ming.(2019).Ultrasound-based radiomics score: a potential biomarker for the prediction of microvascular invasion in hepatocellular carcinoma.EUROPEAN RADIOLOGY,29(6),2890-2901.
MLA	Hu, Hang-tong,et al."Ultrasound-based radiomics score: a potential biomarker for the prediction of microvascular invasion in hepatocellular carcinoma".EUROPEAN RADIOLOGY 29.6(2019):2890-2901.