Exploring the predictive value of additional peritumoral regions based on deep learning and radiomics: A multicenter study

doi:10.1002/mp.14767

CORC > 自动化研究所 > 中国科学院自动化研究所 > 中国科学院分子影像重点实验室

	Exploring the predictive value of additional peritumoral regions based on deep learning and radiomics: A multicenter study
	Wu, Xiangjun 4,5; Dong, Di 4,5; Zhang, Lu 3; Fang, Mengjie 4,5; Zhu, Yongbei 4,5; He, Bingxi 4,5; Ye, Zhaoxiang 2; Zhang, Minming 1; Zhang, Shuixing 3; Tian, Jie 4,6
刊名	MEDICAL PHYSICS
	2021-03-30
页码	12
关键词	deep learning peritumor radiomics
ISSN号	0094-2405
DOI	10.1002/mp.14767
通讯作者	Ye, Zhaoxiang(yezhaoxiang@163.com) ; Zhang, Minming(zhangminming@zju.edu.cn) ; Zhang, Shuixing(shui7515@126.com) ; Tian, Jie(jie.tian@ia.ac.cn)
英文摘要	Purpose The present study assessed the predictive value of peritumoral regions on three tumor tasks, and further explored the influence of peritumors with different sizes. Methods We retrospectively collected 333 samples of gastrointestinal stromal tumors from the Second Affiliated Hospital of Zhejiang University School of Medicine, and 183 samples of gastrointestinal stromal tumors from Tianjin Medical University Cancer Hospital. We also collected 211 samples of laryngeal carcinoma and 233 samples of nasopharyngeal carcinoma from the First Affiliated Hospital of Jinan University. The tasks of three tumor datasets were risk assessment (gastrointestinal stromal tumor), T3/T4 staging prediction (laryngeal carcinoma), and distant metastasis prediction (nasopharyngeal carcinoma), respectively. First, deep learning and radiomics were respectively used to construct peritumoral models, to study whether the peritumor had predictive value on three tumor datasets. Furthermore, we defined different sizes peritumors including fixed size (not considering tumor size) and adaptive size (according to average tumor radius) to explore the influence of peritumor of different sizes and types of tumors. Finally, we visualized the deep learning and radiomic models to observe the influence of the peritumor in three datasets. Results The performance of intra-peritumors are better than intratumors alone in three datasets. Specifically, the comparisons of area under receiver operating characteristic curve in the testing set between intra-peritumoral and intratumoral models are: 0.908 vs 0.873 (P value: 0.037) in gastrointestinal stromal tumor datasets, 0.796 vs 0.756 (P value: 0.188) in laryngeal carcinoma datasets and 0.660 vs 0.579 (P value: 0.431) in nasopharyngeal carcinoma datasets. Furthermore, for gastrointestinal stromal tumor datasets, deep learning is more stable to learn peritumors with both fixed and adaptive size than radiomics. For laryngeal carcinoma datasets, the intra-peritumoral radiomic model could make model performance more balanced. For nasopharyngeal carcinoma datasets, radiomics is also more suitable for modeling peritumors than deep learning. The size of the peritumor is critical in this task, and only the performance of 1.5 mm-4.5 mm peritumors is stable. Conclusions Our results indicate that peritumors have additional predictive value in three tumor datasets through deep learning or radiomics. The definitions of the peritumoral region and artificial intelligence method also have great influence on the performance of the peritumor.
资助项目	National Key R&D Program of China[2017YFC1309100] ; National Key R&D Program of China[2017YFC1308700] ; National Key R&D Program of China[2017YFA0205200] ; National Key R&D Program of China[2017YFA0700401] ; National Natural Science Foundation of China[82022036] ; National Natural Science Foundation of China[91959130] ; National Natural Science Foundation of China[81971776] ; National Natural Science Foundation of China[81771924] ; National Natural Science Foundation of China[6202790004] ; National Natural Science Foundation of China[81930053] ; National Natural Science Foundation of China[81527805] ; Beijing Natural Science Foundation[L182061] ; Strategic Priority Research Program of Chinese Academy of Sciences[XDB 38040200] ; Instrument Developing Project of the Chinese Academy of Sciences[YZ201502] ; Chinese Academy of Sciences[GJJSTD20170004] ; Chinese Academy of Sciences[QYZDJ-SSW-JSC005] ; Youth Innovation Promotion Association CAS[2017175]
WOS研究方向	Radiology, Nuclear Medicine & Medical Imaging
语种	英语
出版者	WILEY
WOS记录号	WOS:000634759600001
资助机构	National Key R&D Program of China ; National Natural Science Foundation of China ; Beijing Natural Science Foundation ; Strategic Priority Research Program of Chinese Academy of Sciences ; Instrument Developing Project of the Chinese Academy of Sciences ; Chinese Academy of Sciences ; Youth Innovation Promotion Association CAS
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/44126]
专题	自动化研究所_中国科学院分子影像重点实验室
通讯作者	Ye, Zhaoxiang; Zhang, Minming; Zhang, Shuixing; Tian, Jie
作者单位	1.Zhejiang Univ, Affiliated Hosp 2, Dept Radiol, Sch Med, Hangzhou, Peoples R China 2.Tianjin Med Univ Canc Inst & Hosp, Dept Radiol, Tianjin, Peoples R China 3.Jinan Univ, Affiliated Hosp 1, Dept Radiol, Guangzhou, Peoples R China 4.Chinese Acad Sci, Inst Automat, CAS Key Lab Mol Imaging, Beijing, Peoples R China 5.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China 6.Beihang Univ, Beijing Adv Innovat Ctr Big Data Based Precis Med, Sch Med & Engn, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Wu, Xiangjun,Dong, Di,Zhang, Lu,et al. Exploring the predictive value of additional peritumoral regions based on deep learning and radiomics: A multicenter study[J]. MEDICAL PHYSICS,2021:12.
APA	Wu, Xiangjun.,Dong, Di.,Zhang, Lu.,Fang, Mengjie.,Zhu, Yongbei.,...&Tian, Jie.(2021).Exploring the predictive value of additional peritumoral regions based on deep learning and radiomics: A multicenter study.MEDICAL PHYSICS,12.
MLA	Wu, Xiangjun,et al."Exploring the predictive value of additional peritumoral regions based on deep learning and radiomics: A multicenter study".MEDICAL PHYSICS (2021):12.