呼出肺部的秘密:使用 CNN-长短期记忆网络对正常和哮喘肺模型的呼出气流进行视频分类

Mohamed Talaat, X. Si, J. Xi
{"title":"呼出肺部的秘密:使用 CNN-长短期记忆网络对正常和哮喘肺模型的呼出气流进行视频分类","authors":"Mohamed Talaat, X. Si, J. Xi","doi":"10.3390/jor3040022","DOIUrl":null,"url":null,"abstract":"In this study, we present a novel approach to differentiate normal and diseased lungs based on exhaled flows from 3D-printed lung models simulating normal and asthmatic conditions. By leveraging the sequential learning capacity of the Long Short-Term Memory (LSTM) network and the automatic feature extraction of convolutional neural networks (CNN), we evaluated the feasibility of the automatic detection and staging of asthmatic airway constrictions. Two asthmatic lung models (D1, D2) with increasing levels of severity were generated by decreasing the bronchiolar calibers in the right upper lobe of a normal lung (D0). Expiratory flows were recorded in the mid-sagittal plane using a high-speed camera at 1500 fps. In addition to the baseline flow rate (20 L/min) with which the networks were trained and verified, two additional flow rates (15 L/min and 10 L/min) were considered to evaluate the network’s robustness to flow deviations. Distinct flow patterns and vortex dynamics were observed among the three disease states (D0, D1, D2) and across the three flow rates. The AlexNet-LSTM network proved to be robust, maintaining perfect performance in the three-class classification when the flow deviated from the recommendation by 25%, and still performed reasonably (72.8% accuracy) despite a 50% flow deviation. The GoogleNet-LSTM network also showed satisfactory performance (91.5% accuracy) at a 25% flow deviation but exhibited low performance (57.7% accuracy) when the deviation was 50%. Considering the sequential learning effects in this classification task, video classifications only slightly outperformed those using still images (i.e., 3–6%). The occlusion sensitivity analyses showed distinct heat maps specific to the disease state.","PeriodicalId":284235,"journal":{"name":"Journal of Respiration","volume":"1994 7","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2023-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Breathe out the Secret of the Lung: Video Classification of Exhaled Flows from Normal and Asthmatic Lung Models Using CNN-Long Short-Term Memory Networks\",\"authors\":\"Mohamed Talaat, X. Si, J. Xi\",\"doi\":\"10.3390/jor3040022\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this study, we present a novel approach to differentiate normal and diseased lungs based on exhaled flows from 3D-printed lung models simulating normal and asthmatic conditions. By leveraging the sequential learning capacity of the Long Short-Term Memory (LSTM) network and the automatic feature extraction of convolutional neural networks (CNN), we evaluated the feasibility of the automatic detection and staging of asthmatic airway constrictions. Two asthmatic lung models (D1, D2) with increasing levels of severity were generated by decreasing the bronchiolar calibers in the right upper lobe of a normal lung (D0). Expiratory flows were recorded in the mid-sagittal plane using a high-speed camera at 1500 fps. In addition to the baseline flow rate (20 L/min) with which the networks were trained and verified, two additional flow rates (15 L/min and 10 L/min) were considered to evaluate the network’s robustness to flow deviations. Distinct flow patterns and vortex dynamics were observed among the three disease states (D0, D1, D2) and across the three flow rates. The AlexNet-LSTM network proved to be robust, maintaining perfect performance in the three-class classification when the flow deviated from the recommendation by 25%, and still performed reasonably (72.8% accuracy) despite a 50% flow deviation. The GoogleNet-LSTM network also showed satisfactory performance (91.5% accuracy) at a 25% flow deviation but exhibited low performance (57.7% accuracy) when the deviation was 50%. Considering the sequential learning effects in this classification task, video classifications only slightly outperformed those using still images (i.e., 3–6%). The occlusion sensitivity analyses showed distinct heat maps specific to the disease state.\",\"PeriodicalId\":284235,\"journal\":{\"name\":\"Journal of Respiration\",\"volume\":\"1994 7\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-12-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Respiration\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3390/jor3040022\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Respiration","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3390/jor3040022","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

在这项研究中,我们提出了一种基于三维打印肺部模型(模拟正常和哮喘情况)呼出气流来区分正常肺部和病变肺部的新方法。通过利用长短期记忆(LSTM)网络的连续学习能力和卷积神经网络(CNN)的自动特征提取,我们评估了自动检测和分期哮喘气道收缩的可行性。通过减小正常肺(D0)右上叶的支气管口径,生成了两个严重程度依次递增的哮喘肺模型(D1、D2)。使用高速相机以 1500 fps 的速度记录中矢状面的呼气流量。除了训练和验证网络的基准流速(20 升/分钟)外,还考虑了另外两种流速(15 升/分钟和 10 升/分钟),以评估网络对流速偏差的鲁棒性。在三种疾病状态(D0、D1、D2)和三种流速之间观察到了不同的流动模式和涡流动态。事实证明,AlexNet-LSTM 网络具有很强的鲁棒性,当流量偏离推荐值 25% 时,它仍能在三类分类中保持完美的性能;当流量偏离推荐值 50% 时,它仍能保持合理的性能(72.8% 的准确率)。GoogleNet-LSTM 网络在流量偏差为 25% 时也表现出了令人满意的性能(91.5% 的准确率),但在流量偏差为 50% 时则表现出了较低的性能(57.7% 的准确率)。考虑到该分类任务中的连续学习效应,视频分类结果仅略微优于使用静态图像的分类结果(即 3-6%)。闭塞敏感性分析显示了疾病状态特有的热图。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Breathe out the Secret of the Lung: Video Classification of Exhaled Flows from Normal and Asthmatic Lung Models Using CNN-Long Short-Term Memory Networks
In this study, we present a novel approach to differentiate normal and diseased lungs based on exhaled flows from 3D-printed lung models simulating normal and asthmatic conditions. By leveraging the sequential learning capacity of the Long Short-Term Memory (LSTM) network and the automatic feature extraction of convolutional neural networks (CNN), we evaluated the feasibility of the automatic detection and staging of asthmatic airway constrictions. Two asthmatic lung models (D1, D2) with increasing levels of severity were generated by decreasing the bronchiolar calibers in the right upper lobe of a normal lung (D0). Expiratory flows were recorded in the mid-sagittal plane using a high-speed camera at 1500 fps. In addition to the baseline flow rate (20 L/min) with which the networks were trained and verified, two additional flow rates (15 L/min and 10 L/min) were considered to evaluate the network’s robustness to flow deviations. Distinct flow patterns and vortex dynamics were observed among the three disease states (D0, D1, D2) and across the three flow rates. The AlexNet-LSTM network proved to be robust, maintaining perfect performance in the three-class classification when the flow deviated from the recommendation by 25%, and still performed reasonably (72.8% accuracy) despite a 50% flow deviation. The GoogleNet-LSTM network also showed satisfactory performance (91.5% accuracy) at a 25% flow deviation but exhibited low performance (57.7% accuracy) when the deviation was 50%. Considering the sequential learning effects in this classification task, video classifications only slightly outperformed those using still images (i.e., 3–6%). The occlusion sensitivity analyses showed distinct heat maps specific to the disease state.
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
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