Structure attention co-training neural network for neovascularization segmentation in intravascular optical coherence tomography

doi:10.1002/mp.15477

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

	Structure attention co-training neural network for neovascularization segmentation in intravascular optical coherence tomography
	Wu, Xiangjun 2,3,4; Zhang, Yingqian 1; Zhang, Peng 5; Hui, Hui 2,3,6; Jing, Jing 1; Tian, Feng 1; Jiang, Jingying 4; Yang, Xin 2,3; Chen, Yundai 1,7; Tian, Jie 2,3,4,8
刊名	MEDICAL PHYSICS
	2022-01-28
页码	16
关键词	co-training IVOCT neovascularization segmentation structural attention mechanism
ISSN号	0094-2405
DOI	10.1002/mp.15477
通讯作者	Chen, Yundai(cyundai@vip.163.com) ; Tian, Jie(jie.tian@ia.ac.cn)
英文摘要	Purpose To development and validate a neovascularization (NV) segmentation model in intravascular optical coherence tomography (IVOCT) through deep learning methods. Methods and materials A total of 1950 2D slices of 70 IVOCT pullbacks were used in our study. We randomly selected 1273 2D slices from 44 patients as the training set, 379 2D slices from 11 patients as the validation set, and 298 2D slices from the last 15 patients as the testing set. Automatic NV segmentation is quite challenging, as it must address issues of speckle noise, shadow artifacts, high distribution variation, etc. To meet these challenges, a new deep learning-based segmentation method is developed based on a co-training architecture with an integrated structural attention mechanism. Co-training is developed to exploit the features of three consecutive slices. The structural attention mechanism comprises spatial and channel attention modules and is integrated into the co-training architecture at each up-sampling step. A cascaded fixed network is further incorporated to achieve segmentation at the image level in a coarse-to-fine manner. Results Extensive experiments were performed involving a comparison with several state-of-the-art deep learning-based segmentation methods. Moreover, the consistency of the results with those of manual segmentation was also investigated. Our proposed NV automatic segmentation method achieved the highest correlation with the manual delineation by interventional cardiologists (the Pearson correlation coefficient is 0.825). Conclusion In this work, we proposed a co-training architecture with an integrated structural attention mechanism to segment NV in IVOCT images. The good agreement between our segmentation results and manual segmentation indicates that the proposed method has great potential for application in the clinical investigation of NV-related plaque diagnosis and treatment.
资助项目	National Key Research and Development Program of China[2017YFA0700401] ; National Key Research and Development Program of China[2016YFC0103803] ; National Natural Science Foundation of China[81827808] ; National Natural Science Foundation of China[62027901] ; National Natural Science Foundation of China[81800221] ; National Natural Science Foundation of China[81870178] ; National Natural Science Foundation of China[81971662] ; National Natural Science Foundation of China[81671851] ; National Natural Science Foundation of China[81527805] ; CAS Youth Innovation Promotion Association[2018167] ; CAS Key Technology Talent Program ; Natural Science Foundation of Beijing City[7202105] ; Project of High-Level Talents Team Introduction in Zhuhai City[HLHPTP201703]
WOS关键词	ATHEROSCLEROTIC PLAQUE ; LUMEN SEGMENTATION ; VULNERABILITY ; IMPLANTATION ; NET
WOS研究方向	Radiology, Nuclear Medicine & Medical Imaging
语种	英语
出版者	WILEY
WOS记录号	WOS:000747983100001
资助机构	National Key Research and Development Program of China ; National Natural Science Foundation of China ; CAS Youth Innovation Promotion Association ; CAS Key Technology Talent Program ; Natural Science Foundation of Beijing City ; Project of High-Level Talents Team Introduction in Zhuhai City
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/47307]
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	Chen, Yundai; Tian, Jie
作者单位	1.Peoples Liberat Army Gen Hosp, Dept Cardiol, Med Ctr 6, Beijing 100853, Peoples R China 2.Beijing Key Lab Mol Imaging, Beijing, Peoples R China 3.Inst Automat, CAS Key Lab Mol Imaging, State Key Lab Management & Control Complex Syst, Beijing, Peoples R China 4.Beihang Univ, Beijing Adv Innovat Ctr Big Data Based Precis Med, Sch Med & Engn, Beijing, Peoples R China 5.Beijing Jiaotong Univ, Sch Comp & Informat Technol, Dept Biomed Engn, Beijing, Peoples R China 6.Univ Chinese Acad Sci, Beijing, Peoples R China 7.Southern Med Univ, Guangzhou, Peoples R China 8.Jinan Univ, Zhuhai Peoples Hosp, Zhuhai Precis Med Ctr, Zhuhai, Peoples R China
推荐引用方式 GB/T 7714	Wu, Xiangjun,Zhang, Yingqian,Zhang, Peng,et al. Structure attention co-training neural network for neovascularization segmentation in intravascular optical coherence tomography[J]. MEDICAL PHYSICS,2022:16.
APA	Wu, Xiangjun.,Zhang, Yingqian.,Zhang, Peng.,Hui, Hui.,Jing, Jing.,...&Tian, Jie.(2022).Structure attention co-training neural network for neovascularization segmentation in intravascular optical coherence tomography.MEDICAL PHYSICS,16.
MLA	Wu, Xiangjun,et al."Structure attention co-training neural network for neovascularization segmentation in intravascular optical coherence tomography".MEDICAL PHYSICS (2022):16.