低辐射快速诊断新冠肺炎的高效稀疏视图医学图像分类

IF 3.2 4区 医学 Q2 ENGINEERING, BIOMEDICAL
Biomedical Engineering Letters Pub Date : 2025-05-22 eCollection Date: 2025-07-01 DOI:10.1007/s13534-025-00478-4
Seunghyun Gwak, Sooyoung Yang, Heawon Jeong, Junhu Park, Myungjoo Kang
{"title":"低辐射快速诊断新冠肺炎的高效稀疏视图医学图像分类","authors":"Seunghyun Gwak, Sooyoung Yang, Heawon Jeong, Junhu Park, Myungjoo Kang","doi":"10.1007/s13534-025-00478-4","DOIUrl":null,"url":null,"abstract":"<p><p>This study proposes a deep learning-based diagnostic model called the Projection-wise Masked Autoencoder (ProMAE) for rapid and accurate COVID-19 diagnosis using sparse-view CT images. ProMAE employs a column-wise masking strategy during pre-training to effectively learn critical diagnostic features from sinograms, even under extremely sparse conditions. The trained ProMAE can directly classify sparse-view sinograms without requiring CT image reconstruction. Experiments on sparse-view data with 50%, 75%, 85%, 95%, and 99% sparsity show that ProMAE achieves a diagnostic accuracy of over 95% at all sparsity levels and, in particular, outperforms ResNet, ConvNeXt, and conventional MAE models in COVID-19 diagnosis in environments with 85% or higher sparsity. This capability is especially advantageous for the development of portable and flexible imaging systems during large-scale outbreaks such as COVID-19, as it ensures accurate diagnosis while minimizing radiation exposure, making it a vital tool in resource-limited and high-demand settings.</p>","PeriodicalId":46898,"journal":{"name":"Biomedical Engineering Letters","volume":"15 4","pages":"785-795"},"PeriodicalIF":3.2000,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12229398/pdf/","citationCount":"0","resultStr":"{\"title\":\"Efficient sparse-view medical image classification for low radiation and rapid COVID-19 diagnosis.\",\"authors\":\"Seunghyun Gwak, Sooyoung Yang, Heawon Jeong, Junhu Park, Myungjoo Kang\",\"doi\":\"10.1007/s13534-025-00478-4\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>This study proposes a deep learning-based diagnostic model called the Projection-wise Masked Autoencoder (ProMAE) for rapid and accurate COVID-19 diagnosis using sparse-view CT images. ProMAE employs a column-wise masking strategy during pre-training to effectively learn critical diagnostic features from sinograms, even under extremely sparse conditions. The trained ProMAE can directly classify sparse-view sinograms without requiring CT image reconstruction. Experiments on sparse-view data with 50%, 75%, 85%, 95%, and 99% sparsity show that ProMAE achieves a diagnostic accuracy of over 95% at all sparsity levels and, in particular, outperforms ResNet, ConvNeXt, and conventional MAE models in COVID-19 diagnosis in environments with 85% or higher sparsity. This capability is especially advantageous for the development of portable and flexible imaging systems during large-scale outbreaks such as COVID-19, as it ensures accurate diagnosis while minimizing radiation exposure, making it a vital tool in resource-limited and high-demand settings.</p>\",\"PeriodicalId\":46898,\"journal\":{\"name\":\"Biomedical Engineering Letters\",\"volume\":\"15 4\",\"pages\":\"785-795\"},\"PeriodicalIF\":3.2000,\"publicationDate\":\"2025-05-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12229398/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Biomedical Engineering Letters\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1007/s13534-025-00478-4\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2025/7/1 0:00:00\",\"PubModel\":\"eCollection\",\"JCR\":\"Q2\",\"JCRName\":\"ENGINEERING, BIOMEDICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Biomedical Engineering Letters","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1007/s13534-025-00478-4","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/7/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"ENGINEERING, BIOMEDICAL","Score":null,"Total":0}
引用次数: 0

摘要

本研究提出了一种基于深度学习的诊断模型,称为投影智能掩码自动编码器(ProMAE),用于使用稀疏视图CT图像快速准确地诊断COVID-19。ProMAE在预训练期间采用列屏蔽策略,即使在极其稀疏的条件下,也能有效地从符号图中学习关键的诊断特征。训练后的ProMAE可以直接对稀疏视图图进行分类,而无需对CT图像进行重建。在稀疏度为50%、75%、85%、95%和99%的稀疏视图数据上进行的实验表明,ProMAE在所有稀疏度级别上的诊断准确率都超过95%,特别是在稀疏度为85%或更高的环境下,ProMAE在COVID-19诊断中的表现优于ResNet、ConvNeXt和传统MAE模型。这种能力对于在COVID-19等大规模疫情期间开发便携式和灵活的成像系统尤其有利,因为它可以确保准确诊断,同时最大限度地减少辐射暴露,使其成为资源有限和高需求环境中的重要工具。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Efficient sparse-view medical image classification for low radiation and rapid COVID-19 diagnosis.

This study proposes a deep learning-based diagnostic model called the Projection-wise Masked Autoencoder (ProMAE) for rapid and accurate COVID-19 diagnosis using sparse-view CT images. ProMAE employs a column-wise masking strategy during pre-training to effectively learn critical diagnostic features from sinograms, even under extremely sparse conditions. The trained ProMAE can directly classify sparse-view sinograms without requiring CT image reconstruction. Experiments on sparse-view data with 50%, 75%, 85%, 95%, and 99% sparsity show that ProMAE achieves a diagnostic accuracy of over 95% at all sparsity levels and, in particular, outperforms ResNet, ConvNeXt, and conventional MAE models in COVID-19 diagnosis in environments with 85% or higher sparsity. This capability is especially advantageous for the development of portable and flexible imaging systems during large-scale outbreaks such as COVID-19, as it ensures accurate diagnosis while minimizing radiation exposure, making it a vital tool in resource-limited and high-demand settings.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Biomedical Engineering Letters
Biomedical Engineering Letters ENGINEERING, BIOMEDICAL-
CiteScore
6.80
自引率
0.00%
发文量
34
期刊介绍: Biomedical Engineering Letters (BMEL) aims to present the innovative experimental science and technological development in the biomedical field as well as clinical application of new development. The article must contain original biomedical engineering content, defined as development, theoretical analysis, and evaluation/validation of a new technique. BMEL publishes the following types of papers: original articles, review articles, editorials, and letters to the editor. All the papers are reviewed in single-blind fashion.
×
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:604180095
Book学术官方微信