Technical Note: PYRO-NN: Python reconstruction operators in neural networks.

Medical physics Pub Date : 2019-11-01 Epub Date: 2019-08-27 DOI:10.1002/mp.13753
Christopher Syben, Markus Michen, Bernhard Stimpel, Stephan Seitz, Stefan Ploner, Andreas K Maier
{"title":"Technical Note: PYRO-NN: Python reconstruction operators in neural networks.","authors":"Christopher Syben,&nbsp;Markus Michen,&nbsp;Bernhard Stimpel,&nbsp;Stephan Seitz,&nbsp;Stefan Ploner,&nbsp;Andreas K Maier","doi":"10.1002/mp.13753","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>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.</p><p><strong>Methods: </strong>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.</p><p><strong>Results: </strong>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 https://github.com/csyben/PYRO-NN.</p><p><strong>Conclusions: </strong>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.</p>","PeriodicalId":94136,"journal":{"name":"Medical physics","volume":"46 11","pages":"5110-5115"},"PeriodicalIF":0.0000,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1002/mp.13753","citationCount":"41","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Medical physics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1002/mp.13753","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2019/8/27 0:00:00","PubModel":"Epub","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 41

Abstract

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 https://github.com/csyben/PYRO-NN.

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.

Abstract Image

技术说明:PYRO-NN:神经网络中的Python重构运算符。
目的:最近,人们进行了几次尝试,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神经网络的概念。然而,所提出的大多数方法都缺乏一个有效的CT重建框架,该框架完全集成到深度学习环境中。因此,许多方法对数学上明确可解的问题使用变通方法。方法:PYRO-NN是一个将已知算子嵌入到流行的深度学习框架Tensorflow中的广义框架。目前的状态包括最先进的平行光束、扇形光束和锥形光束投影仪,以及使用作为Tensorflow层提供的CUDA加速的背面投影仪。最重要的是,该框架提供了高级Python API,用于使用真实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来设计具有集成CT重建算法的端到端神经网络管道。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一份科学出版物,并与现有的非深度学习重建框架进行了比较。为了证明这些层的能力,该框架附带了补充材料中描述的基线实验。该框架可作为Apache 2.0许可证下的开源软件在https://github.com/csyben/PYRO-NN.Conclusions:PYRO-NN带有流行的深度学习框架Tensorflow,允许在医学图像重建环境中建立端到端可训练的神经网络。我们相信,该框架将是向可重复研究迈出的一步,并为医学物理界提供一个工具包,用新的深度学习技术提升医学图像重建。
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 求助全文
来源期刊
自引率
0.00%
发文量
0
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信