Difficulty-aware hierarchical convolutional neural networks for deformable registration of brain MR images.
Difficulty-aware hierarchical convolutional neural networks for deformable registration of brain MR images.
复制标题
DOI：
10.1016/j.media.2020.101817
复制
发表时间：
2021-01
影响因子：
10.9
通讯作者：
Yap PT
中科院分区：
文献类型：
--
作者：
Huang Y;Ahmad S;Fan J;Shen D;Yap PT
可变形脑图像配准的目的是对齐解剖结构，这可能会随着大而复杂的变形而变化。解剖结构的大小和形状各不相同，需要配准算法来估计各种复杂程度的变形场。在这里，我们提出了一个基于注意力机制的困难感知模型，以自动识别难以注册的区域，从而更好地估计大的复杂变形。难度感知模型被纳入一个级联的神经网络组成的三个子网络，充分利用全局和局部上下文信息进行有效的注册。第一个子网络在图像级进行训练，以预测粗尺度变形场，然后将其用于初始化后续子网络。接下来的两个子网络在不同分辨率的面片级别上逐步优化，以预测精细尺度的变形场。将难度感知学习嵌入到分层神经网络中，可以在更深的子网络中以更高的分辨率识别更硬的补丁，以细化变形场。在四个公共数据集上进行的实验验证了我们的方法与最先进的配准方法相比，具有更好的拓扑保持性，达到了很好的配准精度。
The aim of deformable brain image registration is to align anatomical structures, which can potentially vary with large and complex deformations. Anatomical structures vary in size and shape, requiring the registration algorithm to estimate deformation fields at various degrees of complexity. Here, we present a difficulty-aware model based on an attention mechanism to automatically identify hard-to-register regions, allowing better estimation of large complex deformations. The difficulty-aware model is incorporated into a cascaded neural network consisting of three sub-networks to fully leverage both global and local contextual information for effective registration. The first sub-network is trained at the image level to predict a coarse-scale deformation field, which is then used for initializing the subsequent sub-network. The next two sub-networks progressively optimize at the patch level with different resolutions to predict a fine-scale deformation field. Embedding difficulty-aware learning into the hierarchical neural network allows harder patches to be identified in the deeper sub-networks at higher resolutions for refining the deformation field. Experiments conducted on four public datasets validate that our method achieves promising registration accuracy with better preservation of topology, compared with state-of-the-art registration methods.
登录
查看更多内容
影响因子：
10.9
作者：
Maintz, J B;Viergever, M A
通讯作者：
Viergever, M A
影响因子：
10.9
作者：
de Vos, Bob D.;Berendsen, Floris F.;Isgum, Ivana
通讯作者：
Isgum, Ivana
使用提示感知深度回归网络的可变形图像配准
DOI：
10.1109/tbme.2018.2822826
发表时间：
2018-09
期刊：
IEEE transactions on bio-medical engineering
影响因子：
--
作者：
Cao X;Yang J;Zhang J;Wang Q;Yap PT;Shen D
通讯作者：
Shen D
影响因子：
10.9
作者：
Fan, Jingfan;Cao, Xiaohuan;Shen, Dinggang
通讯作者：
Shen, Dinggang
影响因子：
10.9
作者：
Avants, B. B.;Epstein, C. L.;Gee, J. C.
通讯作者：
Gee, J. C.