A CNN-Based Novel Approach for Classification of Sacral Hiatus with GAN-Powered Tabular Data Set

IF 0.9 4区 工程技术 Q4 ENGINEERING, ELECTRICAL & ELECTRONIC
Ferhat Kilic, Murat Korkmaz, Orhan Er, Cemil Altin
{"title":"A CNN-Based Novel Approach for Classification of Sacral Hiatus with GAN-Powered Tabular Data Set","authors":"Ferhat Kilic, Murat Korkmaz, Orhan Er, Cemil Altin","doi":"10.5755/j02.eie.33852","DOIUrl":null,"url":null,"abstract":"Caudal epidural anaesthesia is usually the most well-known technique in obstetrics to deal with chronic back pain. Due to variations in the shape and size of the sacral hiatus (SH), its classification is a crucial and challenging task. Clinically, it is required in trauma, where surgeons must make fast and correct selections. Past studies have focused on morphometric and statistical analysis to classify it. Therefore, it is vital to automatically and accurately classify SH types through deep learning methods. To this end, we proposed the Multi-Task Process (MTP), a novel classification approach to classify the SH MTP that initially uses a small medical tabular data set obtained by manual feature extraction on computed tomography scans of the sacrums. Second, it augments the data set synthetically through a Generative Adversarial Network (GAN). In addition, it adapts a two-dimensional (2D) embedding algorithm to convert tabular features into images. Finally, it feeds images into Convolutional Neural Networks (CNNs). The application of MTP to six CNN models achieved remarkable classification success rates of approximately 90 % to 93 %. The proposed MTP approach eliminates the small medical tabular data problem that results in bone classification on deep models.","PeriodicalId":51031,"journal":{"name":"Elektronika Ir Elektrotechnika","volume":" ","pages":""},"PeriodicalIF":0.9000,"publicationDate":"2023-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Elektronika Ir Elektrotechnika","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.5755/j02.eie.33852","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0

Abstract

Caudal epidural anaesthesia is usually the most well-known technique in obstetrics to deal with chronic back pain. Due to variations in the shape and size of the sacral hiatus (SH), its classification is a crucial and challenging task. Clinically, it is required in trauma, where surgeons must make fast and correct selections. Past studies have focused on morphometric and statistical analysis to classify it. Therefore, it is vital to automatically and accurately classify SH types through deep learning methods. To this end, we proposed the Multi-Task Process (MTP), a novel classification approach to classify the SH MTP that initially uses a small medical tabular data set obtained by manual feature extraction on computed tomography scans of the sacrums. Second, it augments the data set synthetically through a Generative Adversarial Network (GAN). In addition, it adapts a two-dimensional (2D) embedding algorithm to convert tabular features into images. Finally, it feeds images into Convolutional Neural Networks (CNNs). The application of MTP to six CNN models achieved remarkable classification success rates of approximately 90 % to 93 %. The proposed MTP approach eliminates the small medical tabular data problem that results in bone classification on deep models.
基于cnn的gan表格数据集骶裂孔分类新方法
尾侧硬膜外麻醉通常是产科治疗慢性背痛最著名的技术。由于骶裂孔(SH)的形状和大小的变化,其分类是一项至关重要和具有挑战性的任务。在临床上,在创伤中,外科医生必须做出快速而正确的选择。过去的研究主要集中在形态计量学和统计分析上进行分类。因此,通过深度学习方法对SH类型进行自动准确的分类是至关重要的。为此,我们提出了多任务过程(MTP),这是一种新的分类方法,用于对SH MTP进行分类,该方法最初使用通过对骶骨计算机断层扫描进行手动特征提取获得的小型医学表格数据集。其次,通过生成对抗网络(GAN)对数据集进行综合增强。此外,它采用二维嵌入算法将表格特征转换为图像。最后,它将图像输入卷积神经网络(cnn)。将MTP应用于6个CNN模型,分类成功率约为90% ~ 93%。提出的MTP方法消除了导致深度模型骨分类的小医学表格数据问题。
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
Elektronika Ir Elektrotechnika
Elektronika Ir Elektrotechnika 工程技术-工程:电子与电气
CiteScore
2.40
自引率
7.70%
发文量
44
审稿时长
24 months
期刊介绍: The journal aims to attract original research papers on featuring practical developments in the field of electronics and electrical engineering. The journal seeks to publish research progress in the field of electronics and electrical engineering with an emphasis on the applied rather than the theoretical in as much detail as possible. The journal publishes regular papers dealing with the following areas, but not limited to: Electronics; Electronic Measurements; Signal Technology; Microelectronics; High Frequency Technology, Microwaves. Electrical Engineering; Renewable Energy; Automation, Robotics; Telecommunications Engineering.
×
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