Leveraging unsupervised image registration for discovery of landmark shape descriptor.
Leveraging unsupervised image registration for discovery of landmark shape descriptor.
复制标题
DOI：
10.1016/j.media.2021.102157
复制
发表时间：
2021-10
影响因子：
10.9
通讯作者：
Whitaker R
中科院分区：
文献类型：
--
作者：
Bhalodia R;Elhabian S;Kavan L;Whitaker R
在当前的生物和医学研究中，统计形状建模（SSM）为解剖/形态学表征提供了一个重要的框架。这种分析通常是由在整个群体的样本中发现的相对少量的几何一致特征的识别所驱动的。这些特征随后可以提供关于种群形状变化的信息。密集对应模型可以简化计算，并在进行降维后产生可解释的低维形状描述符。然而，获得这种对应关系的自动方法通常需要对图像进行分割，然后进行大量的预处理，这在计算和人力资源方面都是繁重的。在许多情况下，分割和后续处理需要人工指导和解剖特定领域的专业知识。本文提出了一种自监督深度学习方法，用于从图像中发现地标，这些地标可以直接用作后续分析的形状描述符。我们使用地标驱动的图像配准作为主要任务，迫使神经网络发现能够很好地配准图像的地标。我们还提出了一个正则化项，允许神经网络的鲁棒优化，并确保地标均匀地跨越图像域。该方法绕过分割和预处理，直接使用二维或三维图像生成可用的形状描述符。此外，我们还提出了训练损失函数的两种变体，允许将先验形状信息集成到模型中。我们将该框架应用于若干二维和三维数据集，以获得它们的形状描述符。我们分析了这些形状描述符捕获形状信息的有效性，通过执行不同的形状驱动应用程序，这取决于从形状聚类到严重性预测到结果诊断的数据。
In current biological and medical research, statistical shape modeling (SSM) provides an essential framework for the characterization of anatomy/morphology. Such analysis is often driven by the identification of a relatively small number of geometrically consistent features found across the samples of a population. These features can subsequently provide information about the population shape variation. Dense correspondence models can provide ease of computation and yield an interpretable low-dimensional shape descriptor when followed by dimensionality reduction. However, automatic methods for obtaining such correspondences usually require image segmentation followed by significant preprocessing, which is taxing in terms of both computation as well as human resources. In many cases, the segmentation and subsequent processing require manual guidance and anatomy specific domain expertise. This paper proposes a self-supervised deep learning approach for discovering landmarks from images that can directly be used as a shape descriptor for subsequent analysis. We use landmark-driven image registration as the primary task to force the neural network to discover landmarks that register the images well. We also propose a regularization term that allows for robust optimization of the neural network and ensures that the landmarks uniformly span the image domain. The proposed method circumvents segmentation and preprocessing and directly produces a usable shape descriptor using just 2D or 3D images. In addition, we also propose two variants on the training loss function that allows for prior shape information to be integrated into the model. We apply this framework on several 2D and 3D datasets to obtain their shape descriptors. We analyze these shape descriptors in their efficacy of capturing shape information by performing different shape-driven applications depending on the data ranging from shape clustering to severity prediction to outcome diagnosis.
登录
查看更多内容
DOI：
10.1023/b:visi.0000043755.93987.aa
发表时间：
2005-02-01
影响因子：
19.5
作者：
Beg, MF;Miller, MI;Younes, L
通讯作者：
Younes, L
影响因子：
3.8
作者：
Harris, Michael D.;Reese, Shawn P.;Anderson, Andrew E.
通讯作者：
Anderson, Andrew E.
DOI：
10.1002/jor.23468
发表时间：
2017-08
期刊：
Journal of orthopaedic research : official publication of the Orthopaedic Research Society
影响因子：
--
作者：
Atkins PR;Elhabian SY;Agrawal P;Harris MD;Whitaker RT;Weiss JA;Peters CL;Anderson AE
通讯作者：
Anderson AE
影响因子：
10.6
作者：
Davies, RH;Twining, CJ;Taylor, CJ
通讯作者：
Taylor, CJ
影响因子：
5.2
作者：
Johnson, David;Wilkie, Andrew O. M.
通讯作者：
Wilkie, Andrew O. M.