Variational deep embedding-based active learning for the diagnosis of pneumonia

doi:10.3389/fnbot.2022.1059739

	Variational deep embedding-based active learning for the diagnosis of pneumonia
	Huang, Jian 5,6,7; Ding, Wen 7,8; Zhang, Jiarun 9; Li, Zhao 10; Shu, Ting 1; Kuosmanen, Pekka 2,6; Zhou, Guanqun 4; Zhou, Chuan 3; Yu, Gang 5,6,7,10
刊名	FRONTIERS IN NEUROROBOTICS
	2022-11-25
卷号	16 页码:7
关键词	pneumonia diagnosis active learning variational autoencoders brain-like computing human-centric computing
ISSN号	1662-5218
DOI	10.3389/fnbot.2022.1059739
英文摘要	Machine learning works similar to the way humans train their brains. In general, previous experiences prepared the brain by firing specific nerve cells in the brain and increasing the weight of the links between them. Machine learning also completes the classification task by constantly changing the weights in the model through training on the training set. It can conduct a much more significant amount of training and achieve higher recognition accuracy in specific fields than the human brain. In this paper, we proposed an active learning framework called variational deep embedding-based active learning (VaDEAL) as a human-centric computing method to improve the accuracy of diagnosing pneumonia. Because active learning (AL) realizes label-efficient learning by labeling the most valuable queries, we propose a new AL strategy that incorporates clustering to improve the sampling quality. Our framework consists of a VaDE module, a task learner, and a sampling calculator. First, the VaDE performs unsupervised reduction and clustering of dimension over the entire data set. The end-to-end task learner obtains the embedding representations of the VaDE-processed sample while training the target classifier of the model. The sampling calculator will calculate the representativeness of the samples by VaDE, the uncertainty of the samples through task learning, and ensure the overall diversity of the samples by calculating the similarity constraints between the current and previous samples. With our novel design, the combination of uncertainty, representativeness, and diversity scores allows us to select the most informative samples for labeling, thus improving overall performance. With extensive experiments and evaluations performed on a large dataset, we demonstrate that our proposed method is superior to the state-of-the-art methods and has the highest accuracy in the diagnosis of pneumonia.
资助项目	National Key R&D Program of China ; National Natural Science Foundation of China ; [2019YFE0126200] ; [62076218]
WOS研究方向	Computer Science ; Robotics ; Neurosciences & Neurology
语种	英语
出版者	FRONTIERS MEDIA SA
WOS记录号	WOS:000894294800001
内容类型	期刊论文
源URL	[http://ir.amss.ac.cn/handle/2S8OKBNM/60531]
专题	中国科学院数学与系统科学研究院
通讯作者	Shu, Ting; Yu, Gang
作者单位	1.Natl Hlth Commiss, Natl Inst Hosp Adm, Beijing, Peoples R China 2.Avaintec Oy, Helsinki, Finland 3.Chinese Acad Sci, Acad Math & Syst Sci, Beijing, Peoples R China 4.JancsiTech, Hangzhou, Peoples R China 5.Zhejiang Univ, Sch Med, Childrens Hosp, Dept Data & Informat, Hangzhou, Peoples R China 6.Sino Finland Joint AI Lab Child Hlth Zhejiang Prov, Hangzhou, Peoples R China 7.Natl Clin Res Ctr Child Hlth, Hangzhou, Peoples R China 8.Zhejiang Univ, Childrens Hosp, Sch Med, Dept Res & Educ, Hangzhou, Peoples R China 9.Univ Calif San Diego, Dept Comp Sci & Engn, San Diego, CA USA 10.Zhejiang Univ, Coll Comp Sci & Technol, Hangzhou, Peoples R China
推荐引用方式 GB/T 7714	Huang, Jian,Ding, Wen,Zhang, Jiarun,et al. Variational deep embedding-based active learning for the diagnosis of pneumonia[J]. FRONTIERS IN NEUROROBOTICS,2022,16:7.
APA	Huang, Jian.,Ding, Wen.,Zhang, Jiarun.,Li, Zhao.,Shu, Ting.,...&Yu, Gang.(2022).Variational deep embedding-based active learning for the diagnosis of pneumonia.FRONTIERS IN NEUROROBOTICS,16,7.
MLA	Huang, Jian,et al."Variational deep embedding-based active learning for the diagnosis of pneumonia".FRONTIERS IN NEUROROBOTICS 16(2022):7.