CORC  > 自动化研究所  > 中国科学院自动化研究所
Radiomic analysis of multiparametric magnetic resonance imaging for differentiating skull base chordoma and chondrosarcoma
Li, Longfei1,2; Wang, Ke3,4; Ma, Xiujian3,4; Liu, Zhenyu2,5; Wang, Shuo2; Du, Jiang6; Tian, Kaibing3,4; Zhou, Xuezhi7; Wei, Wei7; Sun, Kai7
刊名EUROPEAN JOURNAL OF RADIOLOGY
2019-09-01
卷号118页码:81-87
关键词Radiomics Chordoma Chondrosarcoma Multiparametric MRI
ISSN号0720-048X
DOI10.1016/j.ejrad.2019.07.006
通讯作者Lin, Yusong(yslin@ha.edu.cn) ; Wu, Zhen(wuzhen1966@aliyun.com) ; Tian, Jie(jie.tian@ia.ac.cn)
英文摘要Purpose: Patients with skull base chordoma and chondrosarcoma have different prognoses and are not readily differentiated preoperatively on imaging. Multiparametric magnetic resonance imaging (MRI) is a routine diagnostic tool that can noninvasively characterize the salient characteristics of tumors. In the present study, we developed and validated a preoperative multiparametric MRI-based radiomic signature for differentiating these tumors. Method: This retrospective study enrolled 210 patients and consecutively divided them into the primary and validation cohorts. A total of 1941 radiomic features were acquired from preoperative T1-weighted imaging, T2-weighted imaging and contrast-enhanced Tl-weighted imaging for each patient. The most discriminative features were selected by minimum-redundancy maximum-relevancy and recursive feature elimination algorithms in the primary cohort. The multiparametric and single-sequence MRI signatures were constructed with the selected features using a support vector machine model in the primary cohort. The ability of the novel radiomic signatures to differentiate chordoma from chondrosarcoma were assessed using receiver operating characteristic curve analysis in the validation cohort. Results: The multiparametric radiomic signature, which consisted of 11 selected features, reached an area under the receiver operating characteristic curve of 0.9745 and 0.8720 in the primary and validation cohorts, respectively. Moreover, compared with each single-sequence MRI signature, the multiparametric radiomic signature exhibited better classification performance with significant improvement (p < 0.05, Delong's test) in the primary cohorts. Conclusion: By combining features from three MRI sequences, the multiparametric radiomics signature can accurately and robustly differentiate skull base chordoma from chondrosarcoma.
资助项目National Natural Science Foundation of China[81772009] ; National Natural Science Foundation of China[81227901] ; National Natural Science Foundation of China[81772012] ; National Natural Science Foundation of China[81672506] ; National Natural Science Foundation of China[81802683] ; National Key Research and Development Plan of China[2017YFA0205200] ; Scientific and Technological Research Project of Henan Province[182102310162] ; Youth Innovation Promotion Association CAS[2019136] ; Beijing Natural Science Foundation[7182109] ; Beijing Municipal Science & Technology Commission[Z171100000117023] ; Beijing Municipal Science & Technology Commission[Z161100002616022] ; Chinese Academy of Sciences
WOS关键词CLASSIFICATION ; INFORMATION ; SELECTION ; FEATURES ; IMAGES
WOS研究方向Radiology, Nuclear Medicine & Medical Imaging
语种英语
出版者ELSEVIER IRELAND LTD
WOS记录号WOS:000481609300013
资助机构National Natural Science Foundation of China ; National Key Research and Development Plan of China ; Scientific and Technological Research Project of Henan Province ; Youth Innovation Promotion Association CAS ; Beijing Natural Science Foundation ; Beijing Municipal Science & Technology Commission ; Chinese Academy of Sciences
内容类型期刊论文
源URL[http://ir.ia.ac.cn/handle/173211/27559]  
专题中国科学院自动化研究所
通讯作者Lin, Yusong; Wu, Zhen; Tian, Jie
作者单位1.Zhengzhou Univ, Collaborat Innovat Ctr Internet Healthcare, 75 Daxue Rd, Zhengzhou 450052, Henan, Peoples R China
2.Chinese Acad Sci, Inst Automat, CAS Key Lab Mol Imaging, Beijing 100190, Peoples R China
3.Capital Med Univ, Beijing Tian Tan Hosp, Dept Neurosurg, Beijing, Peoples R China
4.China Natl Clin Res Ctr Neurol Dis, Beijing 100050, Peoples R China
5.Univ Chinese Acad Sci, Beijing 100080, Peoples R China
6.Beijing Neurosurg Inst, Dept Neuropathol, Beijing 100050, Peoples R China
7.Xidian Univ, Sch Life Sci & Technol, Xian 710071, Shaanxi, Peoples R China
8.Zhengzhou Univ, Sch Software, Zhengzhou 450003, Henan, Peoples R China
9.Beihang Univ, Sch Med, Beijing Adv Innovat Ctr Big Data Based Precis Med, Beijing, Peoples R China
推荐引用方式
GB/T 7714
Li, Longfei,Wang, Ke,Ma, Xiujian,et al. Radiomic analysis of multiparametric magnetic resonance imaging for differentiating skull base chordoma and chondrosarcoma[J]. EUROPEAN JOURNAL OF RADIOLOGY,2019,118:81-87.
APA Li, Longfei.,Wang, Ke.,Ma, Xiujian.,Liu, Zhenyu.,Wang, Shuo.,...&Tian, Jie.(2019).Radiomic analysis of multiparametric magnetic resonance imaging for differentiating skull base chordoma and chondrosarcoma.EUROPEAN JOURNAL OF RADIOLOGY,118,81-87.
MLA Li, Longfei,et al."Radiomic analysis of multiparametric magnetic resonance imaging for differentiating skull base chordoma and chondrosarcoma".EUROPEAN JOURNAL OF RADIOLOGY 118(2019):81-87.
个性服务
查看访问统计
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。


©版权所有 ©2017 CSpace - Powered by CSpace