All Attention U-NET for Semantic Segmentation of Intracranial Hemorrhages In Head CT Images

Chia Shuo Chang, Tian Sheuan Chang, Jiun-Lin Yan, L. Ko
{"title":"All Attention U-NET for Semantic Segmentation of Intracranial Hemorrhages In Head CT Images","authors":"Chia Shuo Chang, Tian Sheuan Chang, Jiun-Lin Yan, L. Ko","doi":"10.1109/BioCAS54905.2022.9948588","DOIUrl":null,"url":null,"abstract":"Intracranial hemorrhages in head CT scans serve as a first line tool to help specialists diagnose different types. However, their types have diverse shapes in the same type but similar confusing shape, size and location between types. To solve this problem, this paper proposes an all attention U-Net. It uses channel attentions in the U-Net encoder side to enhance class specific feature extraction, and space and channel attentions in the U-Net decoder side for more accurate shape extraction and type classification. The simulation results show up to a 31.8% improvement compared to baseline, ResNet50 + U-Net, and better performance than in cases with limited attention.","PeriodicalId":131230,"journal":{"name":"2022 IEEE Biomedical Circuits and Systems Conference (BioCAS)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE Biomedical Circuits and Systems Conference (BioCAS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/BioCAS54905.2022.9948588","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Intracranial hemorrhages in head CT scans serve as a first line tool to help specialists diagnose different types. However, their types have diverse shapes in the same type but similar confusing shape, size and location between types. To solve this problem, this paper proposes an all attention U-Net. It uses channel attentions in the U-Net encoder side to enhance class specific feature extraction, and space and channel attentions in the U-Net decoder side for more accurate shape extraction and type classification. The simulation results show up to a 31.8% improvement compared to baseline, ResNet50 + U-Net, and better performance than in cases with limited attention.
U-NET在颅内出血图像语义分割中的应用
颅内出血的CT扫描是帮助专家诊断不同类型的一线工具。然而,它们的类型在同一类型中具有不同的形状,但在类型之间具有相似的混淆形状,大小和位置。为了解决这一问题,本文提出了一个全关注的U-Net。它利用U-Net编码器侧的信道关注来增强类特定特征提取,利用U-Net解码器侧的空间和信道关注来实现更精确的形状提取和类型分类。仿真结果显示,与基线相比,ResNet50 + U-Net提高了31.8%,并且比注意力有限的情况下性能更好。
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
小红书