Deep learning tomographic reconstruction through hierarchical decomposition of domain transforms.
Deep learning tomographic reconstruction through hierarchical decomposition of domain transforms.
复制标题
DOI：
10.1186/s42492-022-00127-y
复制
发表时间：
2022-12-09
影响因子：
--
通讯作者：
中科院分区：
文献类型：
--
作者：
深度学习 (DL) 在许多图像分析和图像增强任务中表现出了前所未有的性能。然而，解决断层扫描重建等大规模逆问题对于深度学习来说仍然具有挑战性。这些问题涉及输入域和输出域之间的非局部和空变积分变换，目前还没有有效的神经网络模型可用。之前使用监督学习解决断层扫描重建问题的尝试依赖于强力全连接网络，并且仅允许使用 1284 系统矩阵大小进行重建。这实际上无法扩展到现实的数据大小，例如三维数据集的 5124 和 5126。在这里，我们提出了一个新颖的框架，通过将原始问题转换为输入域和输出域之间的中间表示的连续体，来使用深度学习解决此类问题。原始问题被分解为一系列更简单的转换，这些转换可以很好地映射到高效的分层网络架构上，其参数比完全连接的网络所需的参数少得多。我们将该方法应用于 5124 系统矩阵大小的计算机断层扫描 (CT) 图像重建。这项工作引入了一种新型数据驱动的深度学习求解器，用于全尺寸 CT 重建，而不依赖于直接（分析）或迭代（数值）反演技术的结构。这项工作展示了全面学习重建的可行性，但需要更多的发展来证明相对于传统重建方法的优越性。所提出的方法还可以扩展到其他成像问题，例如发射和磁共振重建。更广泛地说，分层深度学习为解决一般逆问题的新型求解器打开了大门，这可能会提高各个领域的信噪比、空间分辨率和计算效率。
Deep learning (DL) has shown unprecedented performance for many image analysis and image enhancement tasks. Yet, solving large-scale inverse problems like tomographic reconstruction remains challenging for DL. These problems involve non-local and space-variant integral transforms between the input and output domains, for which no efficient neural network models are readily available. A prior attempt to solve tomographic reconstruction problems with supervised learning relied on a brute-force fully connected network and only allowed reconstruction with a 1284 system matrix size. This cannot practically scale to realistic data sizes such as 5124 and 5126 for three-dimensional datasets. Here we present a novel framework to solve such problems with DL by casting the original problem as a continuum of intermediate representations between the input and output domains. The original problem is broken down into a sequence of simpler transformations that can be well mapped onto an efficient hierarchical network architecture, with exponentially fewer parameters than a fully connected network would need. We applied the approach to computed tomography (CT) image reconstruction for a 5124 system matrix size. This work introduces a new kind of data-driven DL solver for full-size CT reconstruction without relying on the structure of direct (analytical) or iterative (numerical) inversion techniques. This work presents a feasibility demonstration of full-scale learnt reconstruction, whereas more developments will be needed to demonstrate superiority relative to traditional reconstruction approaches. The proposed approach is also extendable to other imaging problems such as emission and magnetic resonance reconstruction. More broadly, hierarchical DL opens the door to a new class of solvers for general inverse problems, which could potentially lead to improved signal-to-noise ratio, spatial resolution and computational efficiency in various areas.
登录
查看更多内容
影响因子：
3.3
作者：
Hammernik K;Klatzer T;Kobler E;Recht MP;Sodickson DK;Pock T;Knoll F
通讯作者：
Knoll F
影响因子：
10.6
作者：
HEBERT, T;LEAHY, R
通讯作者：
LEAHY, R
影响因子：
10.6
作者：
Jin, Kyong Hwan;McCann, Michael T.;Unser, Michael
通讯作者：
Unser, Michael
影响因子：
3.8
作者：
De Man, Quinten;Haneda, Eri;Wang, Ge
通讯作者：
Wang, Ge
影响因子：
4
作者：
Hua KL;Hsu CH;Hidayati SC;Cheng WH;Chen YJ
通讯作者：
Chen YJ