Rubik's Cube plus : A self-supervised feature learning framework for 3D medical image analysis

doi:10.1016/j.media.2020.101746

CORC > 计算技术研究所 > 中国科学院计算技术研究所 > 中国科学院计算技术研究所期刊论文 > 英文

	Rubik's Cube plus : A self-supervised feature learning framework for 3D medical image analysis
	Zhu, Jiuwen 1; Li, Yuexiang 2; Hu, Yifan 2; Ma, Kai 2; Zhou, S. Kevin 1; Zheng, Yefeng 2
刊名	MEDICAL IMAGE ANALYSIS
	2020-08-01
卷号	64 页码:11
关键词	Self-supervised learning 3D Medical imaging data Rubik's cube recovery
ISSN号	1361-8415
DOI	10.1016/j.media.2020.101746
英文摘要	Due to the development of deep learning, an increasing number of research works have been proposed to establish automated analysis systems for 3D volumetric medical data to improve the quality of patient care. However, it is challenging to obtain a large number of annotated 3D medical data needed to train a neural network well, as such manual annotation by physicians is time consuming and laborious. Self-supervised learning is one of the potential solutions to mitigate the strong requirement of data annotation by deeply exploiting raw data information. In this paper, we propose a novel self-supervised learning framework for volumetric medical data. Specifically, we propose a pretext task, i.e., Rubik's cube+, to pre-train 3D neural networks. The pretext task involves three operations, namely cube ordering, cube rotating and cube masking, forcing networks to learn translation and rotation invariant features from the original 3D medical data, and tolerate the noise of the data at the same time. Compared to the strategy of training from scratch, fine-tuning from the Rubik's cube+ pre-trained weights can remarkablely boost the accuracy of 3D neural networks on various tasks, such as cerebral hemorrhage classification and brain tumor segmentation, without the use of extra data. (C) 2020 Elsevier B.V. All rights reserved.
资助项目	Natural Science Foundation of China[61702339] ; Key Area Research and Development Program of Guangdong Province, China[2018B010111001]
WOS研究方向	Computer Science ; Engineering ; Radiology, Nuclear Medicine & Medical Imaging
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:000551766800020
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/15895]
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Li, Yuexiang
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China 2.Tencent Jarvis Lab, Shenzhen, Peoples R China
推荐引用方式 GB/T 7714	Zhu, Jiuwen,Li, Yuexiang,Hu, Yifan,et al. Rubik's Cube plus : A self-supervised feature learning framework for 3D medical image analysis[J]. MEDICAL IMAGE ANALYSIS,2020,64:11.
APA	Zhu, Jiuwen,Li, Yuexiang,Hu, Yifan,Ma, Kai,Zhou, S. Kevin,&Zheng, Yefeng.(2020).Rubik's Cube plus : A self-supervised feature learning framework for 3D medical image analysis.MEDICAL IMAGE ANALYSIS,64,11.
MLA	Zhu, Jiuwen,et al."Rubik's Cube plus : A self-supervised feature learning framework for 3D medical image analysis".MEDICAL IMAGE ANALYSIS 64(2020):11.