Multi -task contrastive learning for automatic CT and X-ray diagnosis of COVID-19

doi:10.1016/j.patcog.2021.107848

CORC > 自动化研究所 > 中国科学院自动化研究所 > 类脑智能研究中心 > 神经计算及脑机交互

	Multi -task contrastive learning for automatic CT and X-ray diagnosis of COVID-19
	Li, Jinpeng 1,2,5; Zhao, Gangming 4,5; Tao, Yaling 1,5; Zhai, Penghua 5; Chen, Hao 5; He, Huiguang 2,3; Cai, Ting 1,2,5
刊名	PATTERN RECOGNITION
	2021-06-01
卷号	114 页码:12
关键词	Computed tomography X-ray COVID-19 Deep learning Multi-task learning Contrastive learning
ISSN号	0031-3203
DOI	10.1016/j.patcog.2021.107848
通讯作者	Cai, Ting(caiting@ucas.ac.cn)
英文摘要	Computed tomography (CT) and X-ray are effective methods for diagnosing COVID-19. Although several studies have demonstrated the potential of deep learning in the automatic diagnosis of COVID-19 using CT and X-ray, the generalization on unseen samples needs to be improved. To tackle this problem, we present the contrastive multi-task convolutional neural network (CMT-CNN), which is composed of two tasks. The main task is to diagnose COVID-19 from other pneumonia and normal control. The auxiliary task is to encourage local aggregation though a contrastive loss: first, each image is transformed by a series of augmentations (Poisson noise, rotation, etc.). Then, the model is optimized to embed represen-tations of a same image similar while different images dissimilar in a latent space. In this way, CMT-CNN is capable of making transformation-invariant predictions and the spread-out properties of data are pre-served. We demonstrate that the apparently simple auxiliary task provides powerful supervisions to en-hance generalization. We conduct experiments on a CT dataset (4,758 samples) and an X-ray dataset (5,821 samples) assembled by open datasets and data collected in our hospital. Experimental results demonstrate that contrastive learning (as plugin module) brings solid accuracy improvement for deep learning models on both CT (5.49%-6.45%) and X-ray (0.96%-2.42%) without requiring additional annota-tions. Our codes are accessible online. (c) 2021 Elsevier Ltd. All rights reserved.
资助项目	Zhejiang Provincial Natural Science Foundation of China[LQ20F030013] ; Research Foundation of HwaMei Hospital, University of Chinese Academy of Sciences, China[2020HMZD22] ; Ningbo Public Service Technology Foundation, China[202002N3181] ; Medical Scientific Research Foundation of Zhejiang Province, China[2021431314]
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	ELSEVIER SCI LTD
WOS记录号	WOS:000632383600009
资助机构	Zhejiang Provincial Natural Science Foundation of China ; Research Foundation of HwaMei Hospital, University of Chinese Academy of Sciences, China ; Ningbo Public Service Technology Foundation, China ; Medical Scientific Research Foundation of Zhejiang Province, China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/44173]
专题	类脑智能研究中心_神经计算及脑机交互
通讯作者	Cai, Ting
作者单位	1.Univ Chinese Acad Sci, HwaMei Hosp, 41 Northwest St, Ningbo 315010, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.Chinese Acad Sci, Inst Automat, 95 Zhongguancun East Rd, Beijing 100190, Peoples R China 4.Univ Hong Kong, Hong Kong, Peoples R China 5.Univ Chinese Acad Sci, Ningbo Inst Life & Hlth Ind, 159 Beijiao St, Ningbo 315000, Peoples R China
推荐引用方式 GB/T 7714	Li, Jinpeng,Zhao, Gangming,Tao, Yaling,et al. Multi -task contrastive learning for automatic CT and X-ray diagnosis of COVID-19[J]. PATTERN RECOGNITION,2021,114:12.
APA	Li, Jinpeng.,Zhao, Gangming.,Tao, Yaling.,Zhai, Penghua.,Chen, Hao.,...&Cai, Ting.(2021).Multi -task contrastive learning for automatic CT and X-ray diagnosis of COVID-19.PATTERN RECOGNITION,114,12.
MLA	Li, Jinpeng,et al."Multi -task contrastive learning for automatic CT and X-ray diagnosis of COVID-19".PATTERN RECOGNITION 114(2021):12.