arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.12141math.NAcs.NA
收藏

基于深度学习的有限角度层析成像快速重建

Fast deep learning based reconstruction for limited angle tomography

Knut Salomonsson, Eric Oldgren, Emanuel Ström, Ozan Öktem

AI总结:

针对有限角度层析成像数据不完整的重建难题,本研究提出FNO-BP网络,将傅里叶神经算子融入滤波反投影方法并结合矩条件进行正弦图外推,在保持与经典FBP相当的运行速度下有效减轻伪影。

摘要:

计算机断层扫描面临的一大挑战是从不完整数据中重建物体。将深度学习模型融入重建算法是解决此类问题日益流行的方案。本研究提出一种新方法,将傅里叶神经算子(FNO)集成到滤波反投影(FBP)重建方法中,构建出FNO反投影(FNO-BP)网络。我们利用矩条件进行正弦图外推,以辅助模型减轻有限数据带来的伪影。值得注意的是,该深度学习架构的运行时间与经典滤波反投影(FBP)重建相当,确保了在推理和训练阶段的快速性能。我们在Helsinki Tomography Challenge 2022背景下评估了该重建方法,并将其与常规FBP方法进行了对比。

英文摘要:

A major challenge in computed tomography is reconstructing objects from incomplete data. An increasingly popular solution for these problems is to incorporate deep learning models into reconstruction algorithms. This study introduces a novel approach by integrating a Fourier neural operator (FNO) into the Filtered Backprojection (FBP) reconstruction method, yielding the FNO back projection (FNO-BP) network. We employ moment conditions for sinogram extrapolation to assist the model in mitigating artefacts from limited data. Notably, our deep learning architecture maintains a runtime comparable to classical filtered back projection (FBP) reconstructions, ensuring swift performance during both inference and training. We assess our reconstruction method in the context of the Helsinki Tomography Challenge 2022 and also compare it against regular FBP methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑