ProxNF: Neural Field Proximal Training for High-Resolution 4D Dynamic Image Reconstruction

IF 4.2 2区 计算机科学 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC IEEE Transactions on Computational Imaging Pub Date : 2024-09-10 DOI:10.1109/TCI.2024.3458397
Luke Lozenski;Refik Mert Cam;Mark D. Pagel;Mark A. Anastasio;Umberto Villa
{"title":"ProxNF: Neural Field Proximal Training for High-Resolution 4D Dynamic Image Reconstruction","authors":"Luke Lozenski;Refik Mert Cam;Mark D. Pagel;Mark A. Anastasio;Umberto Villa","doi":"10.1109/TCI.2024.3458397","DOIUrl":null,"url":null,"abstract":"Accurate spatiotemporal image reconstruction methods are needed for a wide range of biomedical research areas but face challenges due to data incompleteness and computational burden. Data incompleteness arises from the undersampling often required to increase frame rates, while computational burden emerges due to the memory footprint of high-resolution images with three spatial dimensions and extended time horizons. Neural fields (NFs), an emerging class of neural networks that act as continuous representations of spatiotemporal objects, have previously been introduced to solve these dynamic imaging problems by reframing image reconstruction as a problem of estimating network parameters. Neural fields can address the twin challenges of data incompleteness and computational burden by exploiting underlying redundancies in these spatiotemporal objects. This work proposes ProxNF, a novel neural field training approach for spatiotemporal image reconstruction leveraging proximal splitting methods to separate computations involving the imaging operator from updates of the network parameters. Specifically, ProxNF evaluates the (subsampled) gradient of the data-fidelity term in the image domain and uses a fully supervised learning approach to update the neural field parameters. This method is demonstrated in two numerical phantom studies and an in-vivo application to tumor perfusion imaging in small animal models using dynamic contrast-enhanced photoacoustic computed tomography (DCE PACT).","PeriodicalId":56022,"journal":{"name":"IEEE Transactions on Computational Imaging","volume":"10 ","pages":"1368-1383"},"PeriodicalIF":4.2000,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Computational Imaging","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10675448/","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0

Abstract

Accurate spatiotemporal image reconstruction methods are needed for a wide range of biomedical research areas but face challenges due to data incompleteness and computational burden. Data incompleteness arises from the undersampling often required to increase frame rates, while computational burden emerges due to the memory footprint of high-resolution images with three spatial dimensions and extended time horizons. Neural fields (NFs), an emerging class of neural networks that act as continuous representations of spatiotemporal objects, have previously been introduced to solve these dynamic imaging problems by reframing image reconstruction as a problem of estimating network parameters. Neural fields can address the twin challenges of data incompleteness and computational burden by exploiting underlying redundancies in these spatiotemporal objects. This work proposes ProxNF, a novel neural field training approach for spatiotemporal image reconstruction leveraging proximal splitting methods to separate computations involving the imaging operator from updates of the network parameters. Specifically, ProxNF evaluates the (subsampled) gradient of the data-fidelity term in the image domain and uses a fully supervised learning approach to update the neural field parameters. This method is demonstrated in two numerical phantom studies and an in-vivo application to tumor perfusion imaging in small animal models using dynamic contrast-enhanced photoacoustic computed tomography (DCE PACT).
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
ProxNF:用于高分辨率 4D 动态图像重建的神经场近端训练
许多生物医学研究领域都需要精确的时空图像重建方法,但由于数据不完整和计算负担,这些方法面临着挑战。数据不完整的原因是为了提高帧频通常需要采样不足,而计算负担则是由于具有三个空间维度和更长时间跨度的高分辨率图像的内存占用造成的。神经场(NFs)是一类新兴的神经网络,可作为时空对象的连续表征,以前曾被引入解决这些动态成像问题,方法是将图像重建重构为估计网络参数的问题。神经场可以通过利用这些时空对象中的潜在冗余来解决数据不完整和计算负担的双重挑战。本研究提出的 ProxNF 是一种用于时空图像重建的新型神经场训练方法,它利用近端分割方法将涉及成像算子的计算与网络参数的更新分离开来。具体来说,ProxNF 评估图像域中数据保真度项的(子采样)梯度,并使用完全监督学习方法更新神经场参数。该方法在两项数值模型研究中得到了验证,并通过动态对比增强光声计算机断层扫描(DCE PACT)应用于小动物模型的体内肿瘤灌注成像。
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 去求助
来源期刊
IEEE Transactions on Computational Imaging
IEEE Transactions on Computational Imaging Mathematics-Computational Mathematics
CiteScore
8.20
自引率
7.40%
发文量
59
期刊介绍: The IEEE Transactions on Computational Imaging will publish articles where computation plays an integral role in the image formation process. Papers will cover all areas of computational imaging ranging from fundamental theoretical methods to the latest innovative computational imaging system designs. Topics of interest will include advanced algorithms and mathematical techniques, model-based data inversion, methods for image and signal recovery from sparse and incomplete data, techniques for non-traditional sensing of image data, methods for dynamic information acquisition and extraction from imaging sensors, software and hardware for efficient computation in imaging systems, and highly novel imaging system design.
期刊最新文献
IEEE Signal Processing Society Information List of Reviewers Ice-Tide: Implicit Cryo-ET Imaging and Deformation Estimation Joint Edge Optimization Deep Unfolding Network for Accelerated MRI Reconstruction FgC2F-UDiff: Frequency-Guided and Coarse-to-Fine Unified Diffusion Model for Multi-Modality Missing MRI Synthesis
×
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