前进 (2022-07-28 11:54):
#paper doi: 10.1109/TMI.2019.2953788 Transactions on Medical Imaging 2019 Progressively trained convolutional neural networks for deformable image registration 现有的基于深度学习的配准算法对存在大尺度变形的配准任务经常表现不佳。为了解决这种大尺度变形的问题,现有的方法主要分为两种:1、在配准前先采用传统的方法对图像进行预配准(affine,rigid)2、采用多个网络级联的方式,逐步变形,最终生成大尺度变形配准场。这两种方式都存在一定的弊端:1、传统方法耗时过长,削弱了利用深度学习进行后续配准的优势。2、级联网络在配准图像时,会对浮动图像进行多次插值,插值误差积累将会影响最后的变形场质量。因此论文作者提出只采用一个单独的网络联合渐进式训练方式来进行大尺度变形配准。渐进式训练方式首先是被用来提高GAN生成图像的分辨率,现被作者迁移用来解决配准问题。渐进式训练方式简单解释就是当网络的一层训练收敛以后,添加新层,再进行训练,直到生成最后的变形场。该论文有3点创新: 1、 提出了一个渐进式学习模型,能在同一个卷积网络内学习图像不同尺度的变形。 2、 证明了用神经网络配准两张图之前无需预配准。 3、 证明了神经网络可以采用合成的变形场进行监督训练,最后能够泛化解决实际配准问题。
Progressively Trained Convolutional Neural Networks for Deformable Image Registration
翻译
Abstract:
Deep learning-based methods for deformable image registration are attractive alternatives to conventional registration methods because of their short registration times. However, these methods often fail to estimate larger displacements in complex deformation fields, for which a multi-resolution strategy is required. In this article, we propose to train neural networks progressively to address this problem. Instead of training a large convolutional neural network on the registration task all at once, we initially train smaller versions of the network on lower resolution versions of the images and deformation fields. During training, we progressively expand the network with additional layers that are trained on higher resolution data. We show that this way of training allows a network to learn larger displacements without sacrificing registration accuracy and that the resulting network is less sensitive to large misregistrations compared to training the full network all at once. We generate a large number of ground truth example data by applying random synthetic transformations to a training set of images, and test the network on the problem of intrapatient lung CT registration. We analyze the learned representations in the progressively growing network to assess how the progressive learning strategy influences training. Finally, we show that a progressive training procedure leads to improved registration accuracy when learning large and complex deformations.
翻译
回到顶部