• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

基于神经网络的视频远程血氧估计。

Remote Blood Oxygen Estimation From Videos Using Neural Networks.

出版信息

IEEE J Biomed Health Inform. 2023 Aug;27(8):3710-3720. doi: 10.1109/JBHI.2023.3236631. Epub 2023 Aug 7.

DOI:10.1109/JBHI.2023.3236631
PMID:37018728
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC10472532/
Abstract

Peripheral blood oxygen saturation (SpO ) is an essential indicator of respiratory functionality and received increasing attention during the COVID-19 pandemic. Clinical findings show that COVID-19 patients can have significantly low SpO before any obvious symptoms. Measuring an individual's SpO without having to come into contact with the person can lower the risk of cross contamination and blood circulation problems. The prevalence of smartphones has motivated researchers to investigate methods for monitoring SpO using smartphone cameras. Most prior schemes involving smartphones are contact-based: They require using a fingertip to cover the phone's camera and the nearby light source to capture reemitted light from the illuminated tissue. In this paper, we propose the first convolutional neural network based noncontact SpO estimation scheme using smartphone cameras. The scheme analyzes the videos of an individual's hand for physiological sensing, which is convenient and comfortable for users and can protect their privacy and allow for keeping face masks on. We design explainable neural network architectures inspired by the optophysiological models for SpO measurement and demonstrate the explainability by visualizing the weights for channel combination. Our proposed models outperform the state-of-the-art model that is designed for contact-based SpO measurement, showing the potential of the proposed method to contribute to public health. We also analyze the impact of skin type and the side of a hand on SpO estimation performance.

摘要

外周血氧饱和度(SpO )是呼吸功能的重要指标,在 COVID-19 大流行期间受到越来越多的关注。临床研究表明,COVID-19 患者在出现明显症状之前,SpO 可能会显著降低。通过不与人体接触来测量个体的 SpO 可以降低交叉污染和血液循环问题的风险。智能手机的普及促使研究人员研究使用智能手机摄像头监测 SpO 的方法。大多数涉及智能手机的现有方案都是基于接触的:它们需要使用指尖覆盖手机的摄像头和附近的光源,以捕获来自被照亮组织的再发射光。在本文中,我们提出了第一个使用智能手机摄像头的基于卷积神经网络的非接触式 SpO 估计方案。该方案分析个体手部的视频进行生理感应,这对用户来说既方便又舒适,并且可以保护他们的隐私,允许他们戴口罩。我们设计了受 SpO 测量光学生理模型启发的可解释神经网络架构,并通过可视化通道组合的权重来证明其可解释性。我们提出的模型优于专为接触式 SpO 测量设计的最先进模型,表明该方法有可能为公共卫生做出贡献。我们还分析了皮肤类型和手部侧面对 SpO 估计性能的影响。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/31a6/10472532/03304b68f12f/nihms-1923209-f0012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/31a6/10472532/64c401287b2c/nihms-1923209-f0001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/31a6/10472532/9cab5011582c/nihms-1923209-f0002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/31a6/10472532/2e274a77e5b6/nihms-1923209-f0003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/31a6/10472532/35d732dbf663/nihms-1923209-f0004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/31a6/10472532/22cf9e5f3854/nihms-1923209-f0005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/31a6/10472532/966979042eb0/nihms-1923209-f0006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/31a6/10472532/0d3db755837a/nihms-1923209-f0007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/31a6/10472532/11b15abc2dda/nihms-1923209-f0008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/31a6/10472532/095fbc5ffb39/nihms-1923209-f0009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/31a6/10472532/ad1d2eaf8bca/nihms-1923209-f0010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/31a6/10472532/8234e37b2af8/nihms-1923209-f0011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/31a6/10472532/03304b68f12f/nihms-1923209-f0012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/31a6/10472532/64c401287b2c/nihms-1923209-f0001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/31a6/10472532/9cab5011582c/nihms-1923209-f0002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/31a6/10472532/2e274a77e5b6/nihms-1923209-f0003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/31a6/10472532/35d732dbf663/nihms-1923209-f0004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/31a6/10472532/22cf9e5f3854/nihms-1923209-f0005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/31a6/10472532/966979042eb0/nihms-1923209-f0006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/31a6/10472532/0d3db755837a/nihms-1923209-f0007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/31a6/10472532/11b15abc2dda/nihms-1923209-f0008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/31a6/10472532/095fbc5ffb39/nihms-1923209-f0009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/31a6/10472532/ad1d2eaf8bca/nihms-1923209-f0010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/31a6/10472532/8234e37b2af8/nihms-1923209-f0011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/31a6/10472532/03304b68f12f/nihms-1923209-f0012.jpg

相似文献

1
Remote Blood Oxygen Estimation From Videos Using Neural Networks.基于神经网络的视频远程血氧估计。
IEEE J Biomed Health Inform. 2023 Aug;27(8):3710-3720. doi: 10.1109/JBHI.2023.3236631. Epub 2023 Aug 7.
2
Signs and symptoms to determine if a patient presenting in primary care or hospital outpatient settings has COVID-19.在基层医疗机构或医院门诊环境中,如果患者出现以下症状和体征,可判断其是否患有 COVID-19。
Cochrane Database Syst Rev. 2022 May 20;5(5):CD013665. doi: 10.1002/14651858.CD013665.pub3.
3
Effects of targeting lower versus higher arterial oxygen saturations on death or disability in preterm infants.针对较低与较高动脉血氧饱和度对早产儿死亡或残疾的影响。
Cochrane Database Syst Rev. 2017 Apr 11;4(4):CD011190. doi: 10.1002/14651858.CD011190.pub2.
4
Short-Term Memory Impairment短期记忆障碍
5
Comparison of Two Modern Survival Prediction Tools, SORG-MLA and METSSS, in Patients With Symptomatic Long-bone Metastases Who Underwent Local Treatment With Surgery Followed by Radiotherapy and With Radiotherapy Alone.两种现代生存预测工具 SORG-MLA 和 METSSS 在接受手术联合放疗和单纯放疗治疗有症状长骨转移患者中的比较。
Clin Orthop Relat Res. 2024 Dec 1;482(12):2193-2208. doi: 10.1097/CORR.0000000000003185. Epub 2024 Jul 23.
6
Facial Emotion Recognition of 16 Distinct Emotions From Smartphone Videos: Comparative Study of Machine Learning and Human Performance.基于智能手机视频的16种不同情绪的面部表情识别:机器学习与人类表现的对比研究
J Med Internet Res. 2025 Jul 2;27:e68942. doi: 10.2196/68942.
7
Sexual Harassment and Prevention Training性骚扰与预防培训
8
Comparison of self-administered survey questionnaire responses collected using mobile apps versus other methods.使用移动应用程序与其他方法收集的自我管理调查问卷回复的比较。
Cochrane Database Syst Rev. 2015 Jul 27;2015(7):MR000042. doi: 10.1002/14651858.MR000042.pub2.
9
The Black Book of Psychotropic Dosing and Monitoring.《精神药物剂量与监测黑皮书》
Psychopharmacol Bull. 2024 Jul 8;54(3):8-59.
10
Computer and mobile technology interventions for self-management in chronic obstructive pulmonary disease.用于慢性阻塞性肺疾病自我管理的计算机和移动技术干预措施。
Cochrane Database Syst Rev. 2017 May 23;5(5):CD011425. doi: 10.1002/14651858.CD011425.pub2.

引用本文的文献

1
Estimation of Total Hemoglobin (SpHb) from Facial Videos Using 3D Convolutional Neural Network-Based Regression.使用基于3D卷积神经网络的回归方法从面部视频估计总血红蛋白(SpHb)
Biosensors (Basel). 2025 Jul 25;15(8):485. doi: 10.3390/bios15080485.
2
Exploring the Dynamics of Canine-Assisted Interactions: A Wearable Approach to Understanding Interspecies Well-Being.探索犬辅助互动的动态:一种通过可穿戴设备理解跨物种福祉的方法。
Animals (Basel). 2024 Dec 16;14(24):3628. doi: 10.3390/ani14243628.
3
Leveraging 3D convolutional neural network and 3D visible-near-infrared multimodal imaging for enhanced contactless oximetry.

本文引用的文献

1
Bayesian Analysis Reporting Guidelines.贝叶斯分析报告指南。
Nat Hum Behav. 2021 Oct;5(10):1282-1291. doi: 10.1038/s41562-021-01177-7. Epub 2021 Aug 16.
2
Robust non-contact peripheral oxygenation saturation measurement using smartphone-enabled imaging photoplethysmography.使用支持智能手机的成像光电容积脉搏波描记法进行稳健的非接触式外周血氧饱和度测量。
Biomed Opt Express. 2021 Mar 1;12(3):1746-1760. doi: 10.1364/BOE.419268.
3
Modulation Model of the Photoplethysmography Signal for Vital Sign Extraction.光电容积脉搏波信号的生命体征提取调制模型。
利用三维卷积神经网络和三维可见-近红外多模态成像技术增强非接触式血氧饱和度测量。
J Biomed Opt. 2024 Jun;29(Suppl 3):S33309. doi: 10.1117/1.JBO.29.S3.S33309. Epub 2024 Aug 21.
4
Innovative approaches in imaging photoplethysmography for remote blood oxygen monitoring.创新的成像光体积描记法在远程血氧监测中的应用。
Sci Rep. 2024 Aug 19;14(1):19144. doi: 10.1038/s41598-024-70192-1.
5
Contactless Blood Oxygen Saturation Estimation from Facial Videos Using Deep Learning.使用深度学习从面部视频中进行非接触式血氧饱和度估计。
Bioengineering (Basel). 2024 Mar 4;11(3):251. doi: 10.3390/bioengineering11030251.
6
CL-SPO2Net: Contrastive Learning Spatiotemporal Attention Network for Non-Contact Video-Based SpO2 Estimation.CL-SPO2Net:用于基于非接触式视频的血氧饱和度(SpO2)估计的对比学习时空注意力网络
Bioengineering (Basel). 2024 Jan 24;11(2):113. doi: 10.3390/bioengineering11020113.
7
Challenges and prospects of visual contactless physiological monitoring in clinical study.临床研究中视觉非接触式生理监测的挑战与前景
NPJ Digit Med. 2023 Dec 15;6(1):231. doi: 10.1038/s41746-023-00973-x.
8
Patent and Bibliometric Analysis of the Scientific Landscape of the Use of Pulse Oximeters and Their Prospects in the Field of Digital Medicine.脉搏血氧仪使用的科学态势的专利与文献计量分析及其在数字医学领域的前景
Healthcare (Basel). 2023 Nov 20;11(22):3003. doi: 10.3390/healthcare11223003.
9
Contactless SpO with an RGB camera: experimental proof of calibrated SpO.利用RGB摄像头进行非接触式血氧饱和度测量:校准后血氧饱和度的实验证明
Biomed Opt Express. 2022 Dec 1;13(12):6791-6802. doi: 10.1364/BOE.471332.
10
Contactless blood oxygen estimation from face videos: A multi-model fusion method based on deep learning.基于面部视频的非接触式血氧估计:一种基于深度学习的多模型融合方法。
Biomed Signal Process Control. 2023 Mar;81:104487. doi: 10.1016/j.bspc.2022.104487. Epub 2022 Dec 10.
IEEE J Biomed Health Inform. 2021 Apr;25(4):969-977. doi: 10.1109/JBHI.2020.3013811. Epub 2021 Apr 6.
4
Pulse oximetry in low-resource settings during the COVID-19 pandemic.新冠疫情期间资源匮乏地区的脉搏血氧饱和度测定
Lancet Glob Health. 2020 Sep;8(9):e1121-e1122. doi: 10.1016/S2214-109X(20)30287-4. Epub 2020 Jul 3.
5
The mystery of the pandemic's 'happy hypoxia'.疫情中“快乐低氧血症”之谜。
Science. 2020 May 1;368(6490):455-456. doi: 10.1126/science.368.6490.455.
6
RhythmNet: End-to-end Heart Rate Estimation from Face via Spatial-temporal Representation.RhythmNet:通过时空表征从面部进行端到端心率估计
IEEE Trans Image Process. 2019 Oct 22. doi: 10.1109/TIP.2019.2947204.
7
Measuring Oxygen Saturation With Smartphone Cameras Using Convolutional Neural Networks.利用卷积神经网络通过智能手机摄像头测量血氧饱和度。
IEEE J Biomed Health Inform. 2019 Nov;23(6):2603-2610. doi: 10.1109/JBHI.2018.2887209. Epub 2018 Dec 17.
8
Digital Twins in Health Care: Ethical Implications of an Emerging Engineering Paradigm.医疗保健中的数字孪生:一种新兴工程范式的伦理影响
Front Genet. 2018 Feb 13;9:31. doi: 10.3389/fgene.2018.00031. eCollection 2018.
9
Bayesian data analysis for newcomers.新手贝叶斯数据分析。
Psychon Bull Rev. 2018 Feb;25(1):155-177. doi: 10.3758/s13423-017-1272-1.
10
The Bayesian New Statistics: Hypothesis testing, estimation, meta-analysis, and power analysis from a Bayesian perspective.贝叶斯新统计:从贝叶斯视角看假设检验、估计、元分析和功效分析。
Psychon Bull Rev. 2018 Feb;25(1):178-206. doi: 10.3758/s13423-016-1221-4.