Technical Note: PYRO-NN: Python reconstruction operators in neural networks
Technical Note: PYRO-NN: Python reconstruction operators in neural networks
复制标题
DOI：
10.1002/mp.13753
复制
发表时间：
2019-08-27
期刊：
影响因子：
3.8
通讯作者：
Maier, Andreas K.
中科院分区：
文献类型：
--
作者：
Syben, Christopher;Michen, Markus;Maier, Andreas K.
最近，人们尝试将深度学习转移到医学图像重建中。越来越多的出版物遵循将计算机断层扫描（CT）重建作为已知算子嵌入到神经网络中的概念。然而，提出的大多数方法缺乏完全集成到深度学习环境中的有效CT重建框架。因此，许多方法使用解决方法来解决数学上明确可解的问题。MethodsPYRO-NN是一个通用框架，将已知运算符嵌入到流行的深度学习框架Tensorflow中。目前的状态包括最先进的平行、扇形和锥束投影仪，以及使用CUDA作为Tensorflow层加速的背投仪。在顶部，该框架提供了一个高层次的Python API进行FBP和迭代重建实验与数据从真实的CT systems.ResultsThe框架提供了所有必要的算法和工具来设计端到端的神经网络管道集成CT重建算法。高级Python API允许简单使用Tensorflow中已知的层。所有算法和工具都参考了科学出版物，并与现有的非深度学习重建框架进行了比较。为了演示这些层的功能，框架附带了基线实验，这些实验在补充材料中进行了描述。该框架在Apache 2.0许可下作为开源软件提供。结论PYRO-NN配备了流行的深度学习框架Tensorflow，并允许在医学图像重建背景下设置端到端的可训练神经网络。我们相信，该框架将是可重复的研究的一步，并为医学物理界提供一个工具包，以提高医学图像重建与新的深度学习technology.Purpose最近，进行了几次尝试，将深度学习转移到医学图像重建。越来越多的出版物遵循将计算机断层扫描（CT）重建作为已知算子嵌入到神经网络中的概念。然而，提出的大多数方法缺乏完全集成到深度学习环境中的有效CT重建框架。因此，许多方法使用解决方法来解决数学上明确可解的问题。PYRO-NN是一个通用的框架，将已知的操作符嵌入到流行的深度学习框架Tensorflow中。目前的状态包括最先进的平行、扇形和锥束投影仪，以及使用CUDA作为Tensorflow层加速的背投仪。最重要的是，该框架提供了一个高级Python API，用于使用来自真实的CT系统的数据进行FBP和迭代重建实验。结果该框架提供了所有必要的算法和工具，设计端到端的神经网络管道与集成CT重建算法。高级Python API允许简单使用Tensorflow中已知的层。所有算法和工具都参考了科学出版物，并与现有的非深度学习重建框架进行了比较。为了演示这些层的功能，框架附带了基线实验，这些实验在补充材料中进行了描述。该框架可以在Apache 2.0许可证下作为开源软件提供。PYRO-NN配备了流行的深度学习框架Tensorflow，并允许在医学图像重建背景下设置端到端的可训练神经网络。我们相信，该框架将是迈向可重复研究的一步，并为医学物理界提供了一个工具包，可以通过新的深度学习技术提升医学图像重建。
PurposeRecently, several attempts were conducted to transfer deep learning to medical image reconstruction. An increasingly number of publications follow the concept of embedding the computed tomography (CT) reconstruction as a known operator into a neural network. However, most of the approaches presented lack an efficient CT reconstruction framework fully integrated into deep learning environments. As a result, many approaches use workarounds for mathematically unambiguously solvable problems.MethodsPYRO-NN is a generalized framework to embed known operators into the prevalent deep learning framework Tensorflow. The current status includes state-of-the-art parallel-, fan-, and cone-beam projectors, and back-projectors accelerated with CUDA provided as Tensorflow layers. On top, the framework provides a high-level Python API to conduct FBP and iterative reconstruction experiments with data from real CT systems.ResultsThe framework provides all necessary algorithms and tools to design end-to-end neural network pipelines with integrated CT reconstruction algorithms. The high-level Python API allows a simple use of the layers as known from Tensorflow. All algorithms and tools are referenced to a scientific publication and are compared to existing non-deep learning reconstruction frameworks. To demonstrate the capabilities of the layers, the framework comes with baseline experiments, which are described in the supplementary material. The framework is available as open-source software under the Apache 2.0 licence at .ConclusionsPYRO-NN comes with the prevalent deep learning framework Tensorflow and allows to setup end-to-end trainable neural networks in the medical image reconstruction context. We believe that the framework will be a step toward reproducible research and give the medical physics community a toolkit to elevate medical image reconstruction with new deep learning techniques.Purpose Recently, several attempts were conducted to transfer deep learning to medical image reconstruction. An increasingly number of publications follow the concept of embedding the computed tomography (CT) reconstruction as a known operator into a neural network. However, most of the approaches presented lack an efficient CT reconstruction framework fully integrated into deep learning environments. As a result, many approaches use workarounds for mathematically unambiguously solvable problems. Methods PYRO-NN is a generalized framework to embed known operators into the prevalent deep learning framework Tensorflow. The current status includes state-of-the-art parallel-, fan-, and cone-beam projectors, and back-projectors accelerated with CUDA provided as Tensorflow layers. On top, the framework provides a high-level Python API to conduct FBP and iterative reconstruction experiments with data from real CT systems. Results The framework provides all necessary algorithms and tools to design end-to-end neural network pipelines with integrated CT reconstruction algorithms. The high-level Python API allows a simple use of the layers as known from Tensorflow. All algorithms and tools are referenced to a scientific publication and are compared to existing non-deep learning reconstruction frameworks. To demonstrate the capabilities of the layers, the framework comes with baseline experiments, which are described in the supplementary material. The framework is available as open-source software under the Apache 2.0 licence at . Conclusions PYRO-NN comes with the prevalent deep learning framework Tensorflow and allows to setup end-to-end trainable neural networks in the medical image reconstruction context. We believe that the framework will be a step toward reproducible research and give the medical physics community a toolkit to elevate medical image reconstruction with new deep learning techniques.