Improving Semi-supervised Deep Learning by using Automatic Thresholding to Deal with Out of Distribution Data for COVID-19 Detection using Chest X-ray Images

Isaac Benavides-Mata, Saúl Calderón Ramírez
{"title":"Improving Semi-supervised Deep Learning by using Automatic Thresholding to Deal with Out of Distribution Data for COVID-19 Detection using Chest X-ray Images","authors":"Isaac Benavides-Mata, Saúl Calderón Ramírez","doi":"10.1109/BIP56202.2022.10032469","DOIUrl":null,"url":null,"abstract":"Semi-supervised learning (SSL) leverages both labeled and unlabeled data for training models when the labeled data is limited and the unlabeled data is vast. Frequently, the unlabeled data is more widely available than the labeled data, hence this data is used to improve the level of generalization of a model when the labeled data is scarce. However, in real-world settings unlabeled data might depict a different distribution than the labeled dataset distribution. This is known as distribution mismatch. Such problem generally occurs when the source of unlabeled data is different from the labeled data. For instance, in the medical imaging domain, when training a COVID-19 detector using chest X-ray images, different unlabeled datasets sampled from different hospitals might be used. In this work, we propose an automatic thresholding method to filter out-of-distribution data in the unlabeled dataset. We use the Mahalanobis distance between the labeled and unlabeled datasets using the feature space built by a pre-trained Image-net Feature Extractor (FE) to score each unlabeled observation. We test two simple automatic thresholding methods in the context of training a COVID-19 detector using chest X-ray images. The tested methods provide an automatic manner to define what unlabeled data to preserve when training a semi-supervised deep learning architecture.","PeriodicalId":161872,"journal":{"name":"2022 IEEE 4th International Conference on BioInspired Processing (BIP)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE 4th International Conference on BioInspired Processing (BIP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/BIP56202.2022.10032469","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Semi-supervised learning (SSL) leverages both labeled and unlabeled data for training models when the labeled data is limited and the unlabeled data is vast. Frequently, the unlabeled data is more widely available than the labeled data, hence this data is used to improve the level of generalization of a model when the labeled data is scarce. However, in real-world settings unlabeled data might depict a different distribution than the labeled dataset distribution. This is known as distribution mismatch. Such problem generally occurs when the source of unlabeled data is different from the labeled data. For instance, in the medical imaging domain, when training a COVID-19 detector using chest X-ray images, different unlabeled datasets sampled from different hospitals might be used. In this work, we propose an automatic thresholding method to filter out-of-distribution data in the unlabeled dataset. We use the Mahalanobis distance between the labeled and unlabeled datasets using the feature space built by a pre-trained Image-net Feature Extractor (FE) to score each unlabeled observation. We test two simple automatic thresholding methods in the context of training a COVID-19 detector using chest X-ray images. The tested methods provide an automatic manner to define what unlabeled data to preserve when training a semi-supervised deep learning architecture.
基于自动阈值法改进半监督深度学习的胸部x线图像COVID-19检测非分布数据处理
当标记数据有限而未标记数据巨大时,半监督学习(SSL)利用标记和未标记数据来训练模型。通常,未标记的数据比标记的数据更广泛可用,因此当标记的数据稀缺时,这些数据用于提高模型的泛化水平。然而,在现实环境中,未标记的数据可能描绘出与标记数据集分布不同的分布。这就是所谓的分布不匹配。当未标记数据的来源与标记数据不同时,通常会出现这种问题。例如,在医学成像领域,当使用胸部x射线图像训练COVID-19检测器时,可能会使用从不同医院采样的不同未标记数据集。在这项工作中,我们提出了一种自动阈值方法来过滤未标记数据集中的非分布数据。我们使用标记和未标记数据集之间的马氏距离,使用预训练的图像网络特征提取器(FE)构建的特征空间对每个未标记的观测值进行评分。在使用胸部x射线图像训练COVID-19检测器的背景下,我们测试了两种简单的自动阈值分割方法。测试的方法提供了一种自动方式来定义在训练半监督深度学习架构时要保留哪些未标记的数据。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信