AC-IND: Sparse CT reconstruction based on attenuation coefficient estimation and implicit neural distribution

Wangduo Xie, Richard Schoonhoven, Tristan van Leeuwen, Matthew B. Blaschko
{"title":"AC-IND: Sparse CT reconstruction based on attenuation coefficient estimation and implicit neural distribution","authors":"Wangduo Xie, Richard Schoonhoven, Tristan van Leeuwen, Matthew B. Blaschko","doi":"arxiv-2409.07171","DOIUrl":null,"url":null,"abstract":"Computed tomography (CT) reconstruction plays a crucial role in industrial\nnondestructive testing and medical diagnosis. Sparse view CT reconstruction\naims to reconstruct high-quality CT images while only using a small number of\nprojections, which helps to improve the detection speed of industrial assembly\nlines and is also meaningful for reducing radiation in medical scenarios.\nSparse CT reconstruction methods based on implicit neural representations\n(INRs) have recently shown promising performance, but still produce artifacts\nbecause of the difficulty of obtaining useful prior information. In this work,\nwe incorporate a powerful prior: the total number of material categories of\nobjects. To utilize the prior, we design AC-IND, a self-supervised method based\non Attenuation Coefficient Estimation and Implicit Neural Distribution.\nSpecifically, our method first transforms the traditional INR from scalar\nmapping to probability distribution mapping. Then we design a compact\nattenuation coefficient estimator initialized with values from a rough\nreconstruction and fast segmentation. Finally, our algorithm finishes the CT\nreconstruction by jointly optimizing the estimator and the generated\ndistribution. Through experiments, we find that our method not only outperforms\nthe comparative methods in sparse CT reconstruction but also can automatically\ngenerate semantic segmentation maps.","PeriodicalId":501289,"journal":{"name":"arXiv - EE - Image and Video Processing","volume":"17 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - EE - Image and Video Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.07171","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

Computed tomography (CT) reconstruction plays a crucial role in industrial nondestructive testing and medical diagnosis. Sparse view CT reconstruction aims to reconstruct high-quality CT images while only using a small number of projections, which helps to improve the detection speed of industrial assembly lines and is also meaningful for reducing radiation in medical scenarios. Sparse CT reconstruction methods based on implicit neural representations (INRs) have recently shown promising performance, but still produce artifacts because of the difficulty of obtaining useful prior information. In this work, we incorporate a powerful prior: the total number of material categories of objects. To utilize the prior, we design AC-IND, a self-supervised method based on Attenuation Coefficient Estimation and Implicit Neural Distribution. Specifically, our method first transforms the traditional INR from scalar mapping to probability distribution mapping. Then we design a compact attenuation coefficient estimator initialized with values from a rough reconstruction and fast segmentation. Finally, our algorithm finishes the CT reconstruction by jointly optimizing the estimator and the generated distribution. Through experiments, we find that our method not only outperforms the comparative methods in sparse CT reconstruction but also can automatically generate semantic segmentation maps.
AC-IND:基于衰减系数估计和隐式神经分布的稀疏 CT 重构
计算机断层扫描(CT)重建在工业无损检测和医疗诊断中起着至关重要的作用。基于隐式神经表征(INRs)的稀疏 CT 重建方法最近表现出良好的性能,但由于难以获得有用的先验信息,仍然会产生伪影。在这项工作中,我们加入了一个强大的先验信息:物体的材料类别总数。为了利用该先验信息,我们设计了基于衰减系数估计和隐式神经分布的自监督方法 AC-IND。具体来说,我们的方法首先将传统的 INR 从标尺映射转换为概率分布映射。然后,我们设计了一个紧凑的衰减系数估计器,该估计器的初始值来自粗略重建和快速分割。最后,我们的算法通过联合优化估计器和生成的分布来完成 CT 重建。通过实验,我们发现我们的方法不仅在稀疏 CT 重建方面优于其他比较方法,而且还能自动生成语义分割图。
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:481959085
Book学术官方微信