Unsupervised End-to-end Learning for Deformable Medical Image Registration
Unsupervised End-to-end Learning for Deformable Medical Image Registration
复制标题
DOI：
--
复制
发表时间：
2017-11
期刊：
影响因子：
--
通讯作者：
Siyuan Shan;Xiaoqing Guo;Wen Yan;E. Chang;Yubo Fan;Yan Xu
中科院分区：
文献类型：
--
作者：
Siyuan Shan;Xiaoqing Guo;Wen Yan;E. Chang;Yubo Fan;Yan Xu
本文提出了一种基于卷积神经网络的二维CT/MRI医学图像的端到端无监督配准算法。该算法的贡献有三个方面：(1)我们将传统的图像配准算法移植到端到端卷积神经网络框架中，同时保持了图像配准问题的无监督性质。图像到图像集成框架可以同时学习图像特征和变换矩阵进行配准。(2)使用不带任何标签的附加数据进行训练可以进一步提高注册性能约10%。(3)配准速度比传统方法快100倍。该网络实现简单，训练效率高。实验表明，我们的系统在二维脑配准上取得了最先进的结果，在二维肝脏配准上也取得了相当的结果。它可以扩展到肝和脑以外的其他器官，如肾、肺和心脏。
We propose a registration algorithm for 2D CT/MRI medical images with a new unsupervised end-to-end strategy using convolutional neural networks. The contributions of our algorithm are threefold: (1) We transplant traditional image registration algorithms to an end-to-end convolutional neural network framework, while maintaining the unsupervised nature of image registration problems. The image-to-image integrated framework can simultaneously learn both image features and transformation matrix for registration. (2) Training with additional data without any label can further improve the registration performance by approximately 10 %. (3) The registration speed is 100x faster than traditional methods. The proposed network is easy to implement and can be trained efficiently. Experiments demonstrate that our system achieves state-of-the-art results on 2D brain registration and achieves comparable results on 2D liver registration. It can be extended to register other organs beyond liver and brain such as kidney, lung, and heart.