Deformable image registration using convolutional neural networks

机译：使用卷积神经网络可变形图像配准

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

Deformable image registration can be time-consuming and often needs extensive parameterization to perform well on a specific application. We present a step towards a registration framework based on a three-dimensional convolutional neural network. The network directly learns transformations between pairs of three-dimensional images. The outputs of the network are three maps for the x, y, and z components of a thin plate spline transformation grid. The network is trained on synthetic random transformations, which are applied to a small set of representative images for the desired application. Training therefore does not require manually annotated ground truth deformation information. The methodology is demonstrated on public data sets of inspiration-expiration lung CT image pairs, which come with annotated corresponding landmarks for evaluation of the registration accuracy. Advantages of this methodology are its fast registration times and its minimal parameterization.

机译：可变形的图像配准可以耗时，并且通常需要广泛的参数化在特定应用程序上执行良好。我们展示了基于三维卷积神经网络的登记框架的一步。网络直接学习三维图像对之间的转换。网络的输出是薄板样条转换网格的X，Y和Z组件的三个地图。该网络接受了合成随机变换的培训，其应用于所需应用的一小组代表性图像。因此，培训不需要手动注释的地面真相变形信息。在启动到期肺CT图像对的公共数据组上证明了方法，该对应的相应地标具有用于评估登记精度的注释相应的地标。该方法的优点是其快速注册时间及其最小参数化。

著录项

来源
《SPIE Medical Imaging Conference》|2018年|v. p.|共6页
会议地点
作者
Koen A.J. Eppenhof; Maxime W. Lafarge; Pim Moeskops; Mitko Veta; Josien P.W. Pluim;
展开▼
作者单位

展开▼
会议组织
原文格式 PDF
正文语种
中图分类计算技术、计算机技术;
关键词
deformable image registration; machine learning; convolutional networks; thoracic CT;

机译：可变形图像配准;机器学习;卷积网络;胸段CT;

相似文献

外文文献
中文文献
专利

1. A multi-scale framework with unsupervised joint training of convolutional neural networks for pulmonary deformable image registration [J] . Jiang Zhuoran, Yin Fang-Fang, Ge Yun, Physics in medicine and biology. . 2020,第1期

机译：一种多尺度框架，具有无监督的联合培训对扭曲可变形图像配准的卷积神经网络
2. A fast and scalable method for quality assurance of deformable image registration on lung CT scans using convolutional neural networks [J] . Medical Physics . 2020,第1期

机译：使用卷积神经网络对肺CT扫描的可变形图像配准的快速和可扩展方法
3. Progressively Trained Convolutional Neural Networks for Deformable Image Registration [J] . Eppenhof Koen A. J., Lafarge Maxime W., Veta Mitko, IEEE Transactions on Medical Imaging . 2020,第5期

机译：用于可变形图像配准的逐步训练的卷积神经网络
4. A Convolutional Neural Network-based Deformable Image Registration Method for Cardiac Motion Estimation from Cine Cardiac MR Images [C] . Roshan Reddy Upendra, Brian Jamison Wentz, Suzanne M Shontz, Computing in Cardiology . 2020

机译：一种基于卷积神经网络的可变形图像配准法，用于来自Cine心脏MR图像的心动估计
5. Combining Convolutional Neural Networks and Graph Neural Networks for Image Classification [D] . Trivedy, Vivek. 2021

机译：结合卷积神经网络和图形神经网络的图像分类
6. Error estimation of deformable image registration of pulmonary CT scans using convolutional neural networks [O] . Koen A. J. Eppenhof, Josien P. W. Pluim 2018

机译：利用卷积神经网络估计肺部CT扫描的可变形图像配准的误差
7. End-to-End Unsupervised Deformable Image Registration with a Convolutional Neural Network [O] . de Vos, Bob D., Berendsen, Floris F., Viergever, Max A., 2017

机译：端到端无监督可变形图像配准卷积神经网络

Deformable image registration using convolutional neural networks

摘要

著录项

相似文献

相关主题

期刊订阅