NerveGPS: A Novel Decision Support System for Ultrasound Nerve Block Guidance

C. Philippona, J. Morse, M. Wehbe, M. Giacalone, S. Cyr, R. Kazan, T. Hemmerling
{"title":"NerveGPS: A Novel Decision Support System for Ultrasound Nerve Block Guidance","authors":"C. Philippona, J. Morse, M. Wehbe, M. Giacalone, S. Cyr, R. Kazan, T. Hemmerling","doi":"10.1109/CBMS.2014.34","DOIUrl":null,"url":null,"abstract":"Peripheral regional nerve blockade (nerve block) is used in anesthesia to administer anesthesia to certain regions of the body. During nerve block the anesthetic is injected directly into or around the area surrounding the nerve. One of the most critical components of ultrasound-guided nerve blocks is the detection of the nerve within the ultrasound image. This study presents a software-based solution for the detection of nerves within the ultrasound feed. The software that was developed used image processing tools to detect the location of the sciatic nerve at the popliteal fossa within an ultrasound feed. For the study, 100 images were obtained from authors. Then, 2 anesthesiologists with experience in ultrasound-guided nerve blocks were asked to identify the contour of the nerve in the obtained images. The study used two criteria for evaluating the software: 1) the location of the software determined nerve center fell within the manually defined contour and 2) the percentage of overlap between the software and manually detected areas. A test was successful if the percentage of overlap between automatic and manual detection was a minimum of 95% for a circle of 0.4cm diameter centered at the software detected nerve center. For the 100 image sample, the nerve was detected within the manually detected area in 99% of the cases, with an overlap of 98% for a 0.4cm diameter circle. Time to detect the nerve ranged from 0.95s to 1.6s. These preliminary results show that the nerve detection software provides a reliable target for needle insertion. Future work will extend the software to different nerves of interest.","PeriodicalId":398710,"journal":{"name":"2014 IEEE 27th International Symposium on Computer-Based Medical Systems","volume":"28 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2014-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2014 IEEE 27th International Symposium on Computer-Based Medical Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CBMS.2014.34","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3

Abstract

Peripheral regional nerve blockade (nerve block) is used in anesthesia to administer anesthesia to certain regions of the body. During nerve block the anesthetic is injected directly into or around the area surrounding the nerve. One of the most critical components of ultrasound-guided nerve blocks is the detection of the nerve within the ultrasound image. This study presents a software-based solution for the detection of nerves within the ultrasound feed. The software that was developed used image processing tools to detect the location of the sciatic nerve at the popliteal fossa within an ultrasound feed. For the study, 100 images were obtained from authors. Then, 2 anesthesiologists with experience in ultrasound-guided nerve blocks were asked to identify the contour of the nerve in the obtained images. The study used two criteria for evaluating the software: 1) the location of the software determined nerve center fell within the manually defined contour and 2) the percentage of overlap between the software and manually detected areas. A test was successful if the percentage of overlap between automatic and manual detection was a minimum of 95% for a circle of 0.4cm diameter centered at the software detected nerve center. For the 100 image sample, the nerve was detected within the manually detected area in 99% of the cases, with an overlap of 98% for a 0.4cm diameter circle. Time to detect the nerve ranged from 0.95s to 1.6s. These preliminary results show that the nerve detection software provides a reliable target for needle insertion. Future work will extend the software to different nerves of interest.
NerveGPS:一种新的超声神经阻滞引导决策支持系统
周围区域神经阻滞(神经阻滞)在麻醉中用于给身体的某些区域麻醉。在神经阻滞期间,麻醉剂直接注射到神经周围或周围。超声引导神经阻滞最关键的组成部分之一是在超声图像中检测神经。本研究提出了一种基于软件的解决方案,用于超声馈送中的神经检测。开发的软件使用图像处理工具在超声信号中检测腘窝处坐骨神经的位置。在这项研究中,从作者那里获得了100张图片。然后,请2名具有超声引导神经阻滞经验的麻醉师在获得的图像中识别神经的轮廓。该研究使用两个标准来评估软件:1)软件确定的神经中枢的位置落在人工定义的轮廓内;2)软件与人工检测区域之间的重叠百分比。以软件检测到的神经中枢为中心的直径0.4cm的圆圈,如果自动检测和人工检测的重叠百分比至少为95%,则测试成功。对于100个图像样本,99%的病例在人工检测区域内检测到神经,对于直径0.4cm的圆,重叠率为98%。检测神经的时间从0.95秒到1.6秒不等。这些初步结果表明,神经检测软件为针的插入提供了一个可靠的目标。未来的工作将把软件扩展到不同的感兴趣的神经。
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:604180095
Book学术官方微信