Semantically Guided 3D Abdominal Image Registration with Deep Pyramid Feature Learning
Semantically Guided 3D Abdominal Image Registration with Deep Pyramid Feature Learning
复制标题
通过深度金字塔特征学习进行语义引导的 3D 腹部图像配准
DOI：
10.1007/978-3-658-33198-6_6
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Mattias P. Heinrich
中科院分区：
文献类型：
--
作者：
Mona Schumacher;Daniela Frey;In Young Ha;Ragnar Bade;Andreas Genz;Mattias P. Heinrich
大变形图像的可变形图像配准仍然是一项具有挑战性的任务。目前可用的深度学习方法超过了经典的非基于学习的方法，主要是在较低的计算时间方面。然而，这些卷积网络在应用于具有大变形的扫描时面临困难。我们提出了一个语义引导的配准网络与深金字塔特征学习，使大的变形，从图像的特征被注册到注册网络。两个网络部分都有U-Net架构。该网络是端到端训练的，并使用两个数据集进行评估，这两个数据集都包含对比增强的肝脏CT图像和地面实况肝脏分割。我们将我们的方法与一种经典方法和两种深度学习方法进行了比较。我们的实验验证表明，与其他深度学习方法相比，我们提出的方法可以实现大变形，并实现最高的Dice分数和最小的肝脏表面距离。
Deformable image registration of images with large deformations is still a challenging task. Currently available deep learning methods exceed classical non-learning-based methods primarily in terms of lower computational time. However, these convolutional networks face difficulties when applied to scans with large deformations. We present a semantically guided registration network with deep pyramid feature learning that enables large deformations by transferring features from the images to be registered to the registration networks. Both network parts have U-Net architectures. The networks are trained end-to-end and evaluated with two datasets, both containing contrast enhanced liver CT images and ground truth liver segmentations. We compared our method against one classical and two deep learning methods. Our experimental validation shows that our proposed method enables large deformation and achieves the highest Dice score and the smallest surface distance of the liver in contrast to other deep learning methods.