Few-Shot Learning Geometric Ensemble for Multi-label Classification of Chest X-Rays.

Dana Moukheiber, Saurabh Mahindre, Lama Moukheiber, Mira Moukheiber, Song Wang, Chunwei Ma, George Shih, Yifan Peng, Mingchen Gao
{"title":"Few-Shot Learning Geometric Ensemble for Multi-label Classification of Chest X-Rays.","authors":"Dana Moukheiber,&nbsp;Saurabh Mahindre,&nbsp;Lama Moukheiber,&nbsp;Mira Moukheiber,&nbsp;Song Wang,&nbsp;Chunwei Ma,&nbsp;George Shih,&nbsp;Yifan Peng,&nbsp;Mingchen Gao","doi":"10.1007/978-3-031-17027-0_12","DOIUrl":null,"url":null,"abstract":"<p><p>This paper aims to identify uncommon cardiothoracic diseases and patterns on chest X-ray images. Training a machine learning model to classify rare diseases with multi-label indications is challenging without sufficient labeled training samples. Our model leverages the information from common diseases and adapts to perform on less common mentions. We propose to use multi-label few-shot learning (FSL) schemes including neighborhood component analysis loss, generating additional samples using distribution calibration and fine-tuning based on multi-label classification loss. We utilize the fact that the widely adopted nearest neighbor-based FSL schemes like ProtoNet are Voronoi diagrams in feature space. In our method, the Voronoi diagrams in the features space generated from multi-label schemes are combined into our geometric DeepVoro Multi-label ensemble. The improved performance in multi-label few-shot classification using the multi-label ensemble is demonstrated in our experiments (The code is publicly available at https://github.com/Saurabh7/Few-shot-learning-multilabel-cxray).</p>","PeriodicalId":93741,"journal":{"name":"Data augmentation, labelling, and imperfections : second MICCAI workshop, DALI 2022, held in conjunction with MICCAI 2022, Singapore, September 22, 2022, proceedings. DALI (Workshop) (2nd : 2022 : Singapore)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9652771/pdf/nihms-1846293.pdf","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Data augmentation, labelling, and imperfections : second MICCAI workshop, DALI 2022, held in conjunction with MICCAI 2022, Singapore, September 22, 2022, proceedings. DALI (Workshop) (2nd : 2022 : Singapore)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1007/978-3-031-17027-0_12","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2022/9/16 0:00:00","PubModel":"Epub","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3

Abstract

This paper aims to identify uncommon cardiothoracic diseases and patterns on chest X-ray images. Training a machine learning model to classify rare diseases with multi-label indications is challenging without sufficient labeled training samples. Our model leverages the information from common diseases and adapts to perform on less common mentions. We propose to use multi-label few-shot learning (FSL) schemes including neighborhood component analysis loss, generating additional samples using distribution calibration and fine-tuning based on multi-label classification loss. We utilize the fact that the widely adopted nearest neighbor-based FSL schemes like ProtoNet are Voronoi diagrams in feature space. In our method, the Voronoi diagrams in the features space generated from multi-label schemes are combined into our geometric DeepVoro Multi-label ensemble. The improved performance in multi-label few-shot classification using the multi-label ensemble is demonstrated in our experiments (The code is publicly available at https://github.com/Saurabh7/Few-shot-learning-multilabel-cxray).

胸片多标记分类的少射学习几何集成。
本文的目的是识别不常见的心胸疾病和胸片上的模式。在没有足够的标记训练样本的情况下,训练机器学习模型对具有多标签适应症的罕见病进行分类是具有挑战性的。我们的模型利用来自常见疾病的信息,并适应不太常见的提及。我们建议使用包含邻域成分分析损失的多标签少射学习(FSL)方案,使用分布校准和基于多标签分类损失的微调来生成额外的样本。我们利用了广泛采用的基于最近邻的FSL方案(如ProtoNet)是特征空间中的Voronoi图这一事实。在我们的方法中,由多标签方案生成的特征空间中的Voronoi图被组合到我们的几何DeepVoro多标签集成中。我们的实验证明了使用多标签集成在多标签少镜头分类中的改进性能(代码可在https://github.com/Saurabh7/Few-shot-learning-multilabel-cxray上公开获得)。
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