ReconU-Net：一种使用具有反投影诱导跳跃连接的 U-Net 架构的直接 PET 图像重建
ReconU-Net: a direct PET image reconstruction using U-Net architecture with back projection-induced skip connection
AI总结：
本研究提出一种将反投影物理模型嵌入跳跃连接的 ReconU-Net 架构，用于直接 PET 图像重建，有效传递空间信息，在有限模拟数据训练下成功重建真实脑体模，显著提升了图像保真度。
摘要：
[目的] 本研究旨在引入一种新颖的由反投影诱导的 U-Net 形状架构，称为 ReconU-Net，用于基于深度学习的直接正电子发射断层扫描（PET）图像重建。此外，我们的目标是通过将提出的 ReconU-Net 架构与其他没有跳跃连接的编码器-解码器架构进行比较，分析直接 PET 图像重建的行为并获得更深入的见解。[方法] 提出的 ReconU-Net 架构独特地将反投影操作的物理模型整合到跳跃连接中。这一显著特征通过嵌入的物理模型，促进了从输入正弦图到重建图像的内在空间信息的有效传递。提出的 ReconU-Net 使用来自 Brainweb 体模的蒙特卡罗模拟数据进行训练，并在模拟和真实的 Hoffman 脑体模数据上进行了测试。[主要结果] 与其他基于深度学习的直接重建方法相比，提出的 ReconU-Net 方法生成了结构更准确的重建图像。进一步分析表明，提出的 ReconU-Net 架构能够通过跳跃连接传递多种分辨率的特征，特别是非抽象的高分辨率信息。尽管对模拟数据的训练有限，提出的 ReconU-Net 仍成功重建了真实的 Hoffman 脑体模，而其他基于深度学习的直接重建方法则未能生成重建图像。[意义] 通过利用数据驱动建模与成像过程物理模型之间的协同关系，提出的 ReconU-Net 能够提高直接 PET 图像重建的保真度，即使在处理小型训练数据集时也是如此。
英文摘要：
[Objective] This study aims to introduce a novel back projection-induced U-Net-shaped architecture, called ReconU-Net, for deep learning-based direct positron emission tomography (PET) image reconstruction. Additionally, our objective is to analyze the behavior of direct PET image reconstruction and gain deeper insights by comparing the proposed ReconU-Net architecture with other encoder-decoder architectures without skip connections. [Approach] The proposed ReconU-Net architecture uniquely integrates the physical model of the back projection operation into the skip connection. This distinctive feature facilitates the effective transfer of intrinsic spatial information from the input sinogram to the reconstructed image via an embedded physical model. The proposed ReconU-Net was trained using Monte Carlo simulation data from the Brainweb phantom and tested on both simulated and real Hoffman brain phantom data. [Main results] The proposed ReconU-Net method generated a reconstructed image with a more accurate structure compared to other deep learning-based direct reconstruction methods. Further analysis showed that the proposed ReconU-Net architecture has the ability to transfer features of multiple resolutions, especially non-abstract high-resolution information, through skip connections. Despite limited training on simulated data, the proposed ReconU-Net successfully reconstructed the real Hoffman brain phantom, unlike other deep learning-based direct reconstruction methods, which failed to produce a reconstructed image. [Significance] The proposed ReconU-Net can improve the fidelity of direct PET image reconstruction, even when dealing with small training datasets, by leveraging the synergistic relationship between data-driven modeling and the physics model of the imaging process.
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。
