A coupled global registration and segmentation framework with application to magnetic resonance prostate imagery.
A coupled global registration and segmentation framework with application to magnetic resonance prostate imagery.
复制标题
DOI：
10.1109/tmi.2010.2052065
复制
发表时间：
2010-10
影响因子：
10.6
通讯作者：
Tannenbaum AR
中科院分区：
文献类型：
--
作者：
Gao Y;Sandhu R;Fichtinger G;Tannenbaum AR
从磁共振（MR）图像中提取前列腺是医学图像分析和手术规划的一项具有挑战性和重要性的任务。在这项工作中，我们提出了一个统一的基于形状的框架，以提取前列腺MR前列腺图像。在许多情况下，基于形状的分割是一个由两部分组成的问题。首先，必须正确地对齐一组训练形状，使得形状中的任何变化都不是由于姿势引起的。然后可以在学习形状的约束下执行分割。然而，前列腺形状的一般配准任务由于训练集中的姿态和形状的大变化而变得越来越困难，并且不容易通过现有技术来处理。因此，本文的贡献是双重的。我们首先明确地解决注册问题，通过将训练集的形状表示为点云。在这样做的时候，我们能够通过某种基于粒子滤波的方案来利用更全局的配准方面。此外，一旦形状已被注册，成本函数被设计为将本地图像统计以及学习的形状先验两者结合。我们提供的实验结果，其中包括几个具有挑战性的临床数据集，突出算法的鲁棒处理仰卧/俯卧前列腺登记和整体分割任务的能力。
Extracting the prostate from magnetic resonance (MR) imagery is a challenging and important task for medical image analysis and surgical planning. We present in this work a unified shape-based framework to extract the prostate from MR prostate imagery. In many cases, shape-based segmentation is a two-part problem. First, one must properly align a set of training shapes such that any variation in shape is not due to pose. Then segmentation can be performed under the constraint of the learnt shape. However, the general registration task of prostate shapes becomes increasingly difficult due to the large variations in pose and shape in the training sets, and is not readily handled through existing techniques. Thus, the contributions of this paper are twofold. We first explicitly address the registration problem by representing the shapes of a training set as point clouds. In doing so, we are able to exploit the more global aspects of registration via a certain particle filtering based scheme. In addition, once the shapes have been registered, a cost functional is designed to incorporate both the local image statistics as well as the learnt shape prior. We provide experimental results, which include several challenging clinical data sets, to highlight the algorithm’s capability of robustly handling supine/prone prostate registration and the overall segmentation task.