将深度展开与直接扩散桥整合用于计算机断层扫描重建

Herman Verinaz-Jadan, Su Yan
{"title":"将深度展开与直接扩散桥整合用于计算机断层扫描重建","authors":"Herman Verinaz-Jadan, Su Yan","doi":"arxiv-2409.09477","DOIUrl":null,"url":null,"abstract":"Computed Tomography (CT) is widely used in healthcare for detailed imaging.\nHowever, Low-dose CT, despite reducing radiation exposure, often results in\nimages with compromised quality due to increased noise. Traditional methods,\nincluding preprocessing, post-processing, and model-based approaches that\nleverage physical principles, are employed to improve the quality of image\nreconstructions from noisy projections or sinograms. Recently, deep learning\nhas significantly advanced the field, with diffusion models outperforming both\ntraditional methods and other deep learning approaches. These models\neffectively merge deep learning with physics, serving as robust priors for the\ninverse problem in CT. However, they typically require prolonged computation\ntimes during sampling. This paper introduces the first approach to merge deep\nunfolding with Direct Diffusion Bridges (DDBs) for CT, integrating the physics\ninto the network architecture and facilitating the transition from degraded to\nclean images by bypassing excessively noisy intermediate stages commonly\nencountered in diffusion models. Moreover, this approach includes a tailored\ntraining procedure that eliminates errors typically accumulated during\nsampling. The proposed approach requires fewer sampling steps and demonstrates\nimproved fidelity metrics, outperforming many existing state-of-the-art\ntechniques.","PeriodicalId":501289,"journal":{"name":"arXiv - EE - Image and Video Processing","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Integrating Deep Unfolding with Direct Diffusion Bridges for Computed Tomography Reconstruction\",\"authors\":\"Herman Verinaz-Jadan, Su Yan\",\"doi\":\"arxiv-2409.09477\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Computed Tomography (CT) is widely used in healthcare for detailed imaging.\\nHowever, Low-dose CT, despite reducing radiation exposure, often results in\\nimages with compromised quality due to increased noise. Traditional methods,\\nincluding preprocessing, post-processing, and model-based approaches that\\nleverage physical principles, are employed to improve the quality of image\\nreconstructions from noisy projections or sinograms. Recently, deep learning\\nhas significantly advanced the field, with diffusion models outperforming both\\ntraditional methods and other deep learning approaches. These models\\neffectively merge deep learning with physics, serving as robust priors for the\\ninverse problem in CT. However, they typically require prolonged computation\\ntimes during sampling. This paper introduces the first approach to merge deep\\nunfolding with Direct Diffusion Bridges (DDBs) for CT, integrating the physics\\ninto the network architecture and facilitating the transition from degraded to\\nclean images by bypassing excessively noisy intermediate stages commonly\\nencountered in diffusion models. Moreover, this approach includes a tailored\\ntraining procedure that eliminates errors typically accumulated during\\nsampling. The proposed approach requires fewer sampling steps and demonstrates\\nimproved fidelity metrics, outperforming many existing state-of-the-art\\ntechniques.\",\"PeriodicalId\":501289,\"journal\":{\"name\":\"arXiv - EE - Image and Video Processing\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-14\",\"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-2409.09477\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - EE - Image and Video Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.09477","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

计算机断层扫描(CT)被广泛应用于医疗保健领域的详细成像。然而,低剂量 CT 虽然减少了辐射暴露,但由于噪声增加,往往会导致图像质量下降。传统的方法,包括预处理、后处理和基于模型的方法(利用物理原理),都被用来提高从噪声投影或正弦曲线中重建图像的质量。最近,深度学习大大推动了这一领域的发展,扩散模型的表现优于传统方法和其他深度学习方法。这些模型有效地融合了深度学习和物理学,可作为 CT 逆问题的稳健先验。然而,它们在采样过程中通常需要较长的计算时间。本文介绍了第一种将深度折叠与直接扩散桥(DDBs)合并用于 CT 的方法,将物理学整合到网络架构中,通过绕过扩散模型中常见的噪声过大的中间阶段,促进从退化图像到清洁图像的过渡。此外,这种方法还包括一个量身定制的训练程序,可以消除通常在采样过程中积累的误差。所提出的方法需要的采样步骤更少,保真度指标也得到了改善,优于许多现有的先进技术。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Integrating Deep Unfolding with Direct Diffusion Bridges for Computed Tomography Reconstruction
Computed Tomography (CT) is widely used in healthcare for detailed imaging. However, Low-dose CT, despite reducing radiation exposure, often results in images with compromised quality due to increased noise. Traditional methods, including preprocessing, post-processing, and model-based approaches that leverage physical principles, are employed to improve the quality of image reconstructions from noisy projections or sinograms. Recently, deep learning has significantly advanced the field, with diffusion models outperforming both traditional methods and other deep learning approaches. These models effectively merge deep learning with physics, serving as robust priors for the inverse problem in CT. However, they typically require prolonged computation times during sampling. This paper introduces the first approach to merge deep unfolding with Direct Diffusion Bridges (DDBs) for CT, integrating the physics into the network architecture and facilitating the transition from degraded to clean images by bypassing excessively noisy intermediate stages commonly encountered in diffusion models. Moreover, this approach includes a tailored training procedure that eliminates errors typically accumulated during sampling. The proposed approach requires fewer sampling steps and demonstrates improved fidelity metrics, outperforming many existing state-of-the-art techniques.
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
期刊最新文献
multiPI-TransBTS: A Multi-Path Learning Framework for Brain Tumor Image Segmentation Based on Multi-Physical Information Autopet III challenge: Incorporating anatomical knowledge into nnUNet for lesion segmentation in PET/CT Denoising diffusion models for high-resolution microscopy image restoration Tumor aware recurrent inter-patient deformable image registration of computed tomography scans with lung cancer Cross-Organ and Cross-Scanner Adenocarcinoma Segmentation using Rein to Fine-tune Vision Foundation Models
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1