使用深度学习的椎骨检测和标记

{"title":"使用深度学习的椎骨检测和标记","authors":"","doi":"10.35940/ijrte.a2419.059120","DOIUrl":null,"url":null,"abstract":"Inspection, Classification and localization of artificial vertebrae from random CT images is difficult. Normally vertebrates have a similar morphological appearance. Owing to anatomy and hence the subjective field of view of CT scans, the presence of any anchor vertebrae or parametric methods for defining the looks and form can hardly be believed. They suggest a robust and effective method for recognizing and localizing vertebrae that can automatically learn to use both the short range and long-range conceptual information in a controlled manner. Combine a fully convolutionary neural network with an instance memory that preserves information on already segmented vertebrae. This network analyzes image patches iteratively, using the instance memory to scan for and segment the not yet segmented primary vertebra. Every vertebra is measured as wholly or partly at an equal period. This study uses an over dimensional sample of 865 disc-levels from 1115 patients.","PeriodicalId":220909,"journal":{"name":"International Journal of Recent Technology and Engineering","volume":"14 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Detection and Labeling of Vertebrae using Deep Learning\",\"authors\":\"\",\"doi\":\"10.35940/ijrte.a2419.059120\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Inspection, Classification and localization of artificial vertebrae from random CT images is difficult. Normally vertebrates have a similar morphological appearance. Owing to anatomy and hence the subjective field of view of CT scans, the presence of any anchor vertebrae or parametric methods for defining the looks and form can hardly be believed. They suggest a robust and effective method for recognizing and localizing vertebrae that can automatically learn to use both the short range and long-range conceptual information in a controlled manner. Combine a fully convolutionary neural network with an instance memory that preserves information on already segmented vertebrae. This network analyzes image patches iteratively, using the instance memory to scan for and segment the not yet segmented primary vertebra. Every vertebra is measured as wholly or partly at an equal period. This study uses an over dimensional sample of 865 disc-levels from 1115 patients.\",\"PeriodicalId\":220909,\"journal\":{\"name\":\"International Journal of Recent Technology and Engineering\",\"volume\":\"14 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-05-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal of Recent Technology and Engineering\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.35940/ijrte.a2419.059120\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Recent Technology and Engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.35940/ijrte.a2419.059120","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

从随机CT图像中对人工椎体进行检测、分类和定位是困难的。通常脊椎动物有相似的形态外观。由于解剖学和CT扫描的主观视野,任何锚定椎体的存在或用于定义外观和形式的参数化方法都很难让人相信。他们提出了一种强大而有效的方法来识别和定位椎骨,这种方法可以在受控的方式下自动学习使用短程和远程概念信息。将全卷积神经网络与实例记忆相结合,保存已分段椎骨的信息。该网络迭代分析图像补丁,利用实例内存扫描和分割尚未分割的主椎体。每根脊椎骨全部或部分在同一时期测量。本研究使用了来自1115名患者的865个椎间盘水平的超量纲样本。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Detection and Labeling of Vertebrae using Deep Learning
Inspection, Classification and localization of artificial vertebrae from random CT images is difficult. Normally vertebrates have a similar morphological appearance. Owing to anatomy and hence the subjective field of view of CT scans, the presence of any anchor vertebrae or parametric methods for defining the looks and form can hardly be believed. They suggest a robust and effective method for recognizing and localizing vertebrae that can automatically learn to use both the short range and long-range conceptual information in a controlled manner. Combine a fully convolutionary neural network with an instance memory that preserves information on already segmented vertebrae. This network analyzes image patches iteratively, using the instance memory to scan for and segment the not yet segmented primary vertebra. Every vertebra is measured as wholly or partly at an equal period. This study uses an over dimensional sample of 865 disc-levels from 1115 patients.
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