A multi-view co-training network for semi-supervised medical image-based prognostic prediction

doi:10.1016/j.neunet.2023.04.030

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

	A multi-view co-training network for semi-supervised medical image-based prognostic prediction
	Li, Hailin 3,5; Wang, Siwen 4,5; Liu, Bo 1,2; Fang, Mengjie 3,5; Cao, Runnan 4,5; He, Bingxi 3,5; Liu, Shengyuan 4,5; Hu, Chaoen 5; Dong, Di 4,5; Wang, Ximing 1
刊名	NEURAL NETWORKS
	2023-07-01
卷号	164 页码:455-463
关键词	Deep neural network Medical image analysis Prognostic prediction Semi-supervised learning
ISSN号	0893-6080
DOI	10.1016/j.neunet.2023.04.030
通讯作者	Dong, Di(di.dong@ia.ac.cn) ; Wang, Ximing(wxming369@163.com) ; Wang, Hexiang(wanghexiang@qdu.edu.cn) ; Tian, Jie(jie.tian@ia.ac.cn)
英文摘要	Prognostic prediction has long been a hotspot in disease analysis and management, and the de-velopment of image-based prognostic prediction models has significant clinical implications for current personalized treatment strategies. The main challenge in prognostic prediction is to model a regression problem based on censored observations, and semi-supervised learning has the potential to play an important role in improving the utilization efficiency of censored data. However, there are yet few effective semi-supervised paradigms to be applied. In this paper, we propose a semi -supervised co-training deep neural network incorporating a support vector regression layer for survival time estimation (Co-DeepSVS) that improves the efficiency in utilizing censored data for prognostic prediction. First, we introduce a support vector regression layer in deep neural networks to deal with censored data and directly predict survival time, and more importantly to calculate the labeling confidence of each case. Then, we apply a semi-supervised multi-view co-training framework to achieve accurate prognostic prediction, where labeling confidence estimation with prior knowledge of pseudo time is conducted for each view. Experimental results demonstrate that the proposed Co-DeepSVS has a promising prognostic ability and surpasses most widely used methods on a multi-phase CT dataset. Besides, the introduction of SVR layer makes the model more robust in the presence of follow-up bias. (c) 2023 Published by Elsevier Ltd.
资助项目	Strategic Priority Research Program of Chinese Academy of Sciences[XDB38040200] ; 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[62027901] ; National Natural Science Foundation of China[81930053] ; National Natural Science Foundation of China[81971580] ; National Natural Science Foundation of China[91959205] ; National Natural Science Foundation of China[81971619] ; National Natural Science Foundation of China[81227901] ; National Natural Science Foundation of China[81871354] ; National Key R&D Program of China[2017YFA0205200] ; Beijing Natural Science Foundation, China[Z20J00105] ; Chinese Academy of Sciences[GJJSTD20170004] ; Chinese Academy of Sciences[QYZDJ-SSW-JSC005] ; Project of High-Level Talents Team Introduction in Zhuhai City, China[Zhuhai HLHPTP201703] ; Youth Innovation Promotion Association CAS, China[Y2021049] ; Taishan Scholars Project ; Academic Promotion Programme of Shandong First Medical University, China[2019QL023]
WOS关键词	LYMPH-NODE METASTASIS ; REGRESSION ; CANCER ; MODELS ; CLASSIFICATION
WOS研究方向	Computer Science ; Neurosciences & Neurology
语种	英语
出版者	PERGAMON-ELSEVIER SCIENCE LTD
WOS记录号	WOS:000999170100001
资助机构	Strategic Priority Research Program of Chinese Academy of Sciences ; National Natural Science Foundation of China ; National Key R&D Program of China ; Beijing Natural Science Foundation, China ; Chinese Academy of Sciences ; Project of High-Level Talents Team Introduction in Zhuhai City, China ; Youth Innovation Promotion Association CAS, China ; Taishan Scholars Project ; Academic Promotion Programme of Shandong First Medical University, China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/53408]
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	Dong, Di; Wang, Ximing; Wang, Hexiang; Tian, Jie
作者单位	1.Shandong Univ, Shandong Med Univ 1, Shandong Prov Hosp, Dept Radiol, Jinan 250021, Shandong, Peoples R China 2.Lanzhou Univ, Hosp 2, Lanzhou 730050, Gansu, Peoples R China 3.Beihang Univ, Beijing Adv Innovat Ctr Big Data Based Precis Med, Sch Engn Med, Beijing 100191, Peoples R China 4.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 5.Chinese Acad Sci, Inst Automat, CAS Key Lab Mol Imaging, Beijing 100190, Peoples R China 6.Qingdao Univ, Affiliated Hosp, Dept Radiol, Qingdao 266000, Shandong, Peoples R China
推荐引用方式 GB/T 7714	Li, Hailin,Wang, Siwen,Liu, Bo,et al. A multi-view co-training network for semi-supervised medical image-based prognostic prediction[J]. NEURAL NETWORKS,2023,164:455-463.
APA	Li, Hailin.,Wang, Siwen.,Liu, Bo.,Fang, Mengjie.,Cao, Runnan.,...&Tian, Jie.(2023).A multi-view co-training network for semi-supervised medical image-based prognostic prediction.NEURAL NETWORKS,164,455-463.
MLA	Li, Hailin,et al."A multi-view co-training network for semi-supervised medical image-based prognostic prediction".NEURAL NETWORKS 164(2023):455-463.