科研成果详情

题名Using deep learning in pathology image analysis: A novel active learning strategy based on latent representation
作者
发表日期2023
发表期刊ELECTRONIC RESEARCH ARCHIVE   影响因子和分区
语种英语
原始文献类型Article
关键词active learning pathology images classification latent representation samples selection ALHS strategy
摘要Most countries worldwide continue to encounter a pathologist shortage, significantly impeding the timely diagnosis and effective treatment of cancer patients. Deep learning techniques have performed remarkably well in pathology image analysis; however, they require expert pathologists to annotate substantial pathology image data. This study aims to minimize the need for data annotation to analyze pathology images. Active learning (AL) is an iterative approach to search for a few high-quality samples to train a model. We propose our active learning framework, which first learns latent representations of all pathology images by an auto-encoder to train a binary classification model, and then selects samples through a novel ALHS (Active Learning Hybrid Sampling) strategy. This strategy can effectively alleviate the sample redundancy problem and allows for more informative and diverse examples to be selected. We validate the effectiveness of our method by undertaking classification tasks on two cancer pathology image datasets. We achieve the target performance of 90% accuracy using 25% labeled samples in Kather's dataset and reach 88% accuracy using 65% labeled data in BreakHis dataset, which means our method can save 75% and 35% of the annotation budget in the two datasets, respectively.
资助项目Medico -Engineering Cooperation Funds from University of Electronic Science and Technology of China [ZYGX2021YGLH213, ZYGX2022YGRH016]; Zhejiang Provincial Natural Science Foundation of China [LGF22G010009]; Municipal Government of Quzhou [2022D018, 2022D029]
出版者AMER INST MATHEMATICAL SCIENCES-AIMS
ISSN2688-1594
EISSN2688-1594
卷号31期号:9页码:5340-5361
DOI10.3934/era.2023271
页数22
WOS类目Mathematics
WOS研究方向Mathematics
WOS记录号WOS:001041201200001
收录类别SCIE ; SCOPUS
URL查看原文
SCOPUSEID2-s2.0-85168829648
通讯作者地址[Wu, Lei]School of Mathematical Sciences,University of Electronic Science and Technology of China,Chengdu,611731,China
Scopus学科分类Mathematics (all)
引用统计
文献类型期刊论文
条目标识符https://kms.wmu.edu.cn/handle/3ETUA0LF/182306
专题其他_温州医科大学附属衢州医院
通讯作者Wu, Lei
作者单位
1.School of Mathematical Sciences,University of Electronic Science and Technology of China,Chengdu,611731,China;
2.Yangtze Delta Region Institute (Quzhou),University of Electronic Science and Technology of China,Quzhou,314099,China;
3.School of Computer and Software Engineering,Xihua University,Chengdu,611731,China;
4.The Quzhou Affiliated Hospital of Wenzhou Medical University,Quzhou People’s Hospital,Quzhou,324000,China
推荐引用方式
GB/T 7714
Sun, Yixin,Wu, Lei,Chen, Peng,et al. Using deep learning in pathology image analysis: A novel active learning strategy based on latent representation[J]. ELECTRONIC RESEARCH ARCHIVE,2023,31(9):5340-5361.
APA Sun, Yixin, Wu, Lei, Chen, Peng, Zhang, Feng, & Xu, Lifeng. (2023). Using deep learning in pathology image analysis: A novel active learning strategy based on latent representation. ELECTRONIC RESEARCH ARCHIVE, 31(9), 5340-5361.
MLA Sun, Yixin,et al."Using deep learning in pathology image analysis: A novel active learning strategy based on latent representation".ELECTRONIC RESEARCH ARCHIVE 31.9(2023):5340-5361.

条目包含的文件

条目无相关文件。
个性服务
查看访问统计
谷歌学术
谷歌学术中相似的文章
[Sun, Yixin]的文章
[Wu, Lei]的文章
[Chen, Peng]的文章
百度学术
百度学术中相似的文章
[Sun, Yixin]的文章
[Wu, Lei]的文章
[Chen, Peng]的文章
必应学术
必应学术中相似的文章
[Sun, Yixin]的文章
[Wu, Lei]的文章
[Chen, Peng]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。