Shape-aware label fusion for multi-atlas frameworks
Shape-aware label fusion for multi-atlas frameworks
复制标题
DOI：
10.1016/j.patrec.2018.07.008
复制
发表时间：
2019-06-01
影响因子：
5.1
通讯作者：
Enqvist, Olof
中科院分区：
文献类型：
--
作者：
Alven, Jennifer;Kahl, Fredrik;Enqvist, Olof
尽管没有明确的形状模型，多图谱的图像分割方法已被证明是一个顶级的表演几个不同的数据集和成像模式。在本文中，我们展示了如何直接将形状正则化纳入多图集框架。与传统的多图谱方法不同，我们提出的方法不依赖于体素级别上的标签融合。相反，每个配准的图谱被视为形状模型的位置的估计。我们在两个公共基准上评估和比较我们的方法：（i）全身CT图像多器官分割的VISCERAL Grand Challenge和（ii）分割海马和杏仁核的MR图像的Hammers脑图谱。对于这一广泛的容易和困难的分割任务，我们的实验定量结果与最先进的水平相当或更好。更重要的是，我们获得了定性更好的分割边界，例如，保持拓扑结构和精细结构。(C)2018爱思唯尔B.V.保留所有权利。
Despite of having no explicit shape model, multi-atlas approaches to image segmentation have proved to be a top-performer for several diverse datasets and imaging modalities. In this paper, we show how one can directly incorporate shape regularization into the multi-atlas framework. Unlike traditional multi-atlas methods, our proposed approach does not rely on label fusion on the voxel level. Instead, each registered atlas is viewed as an estimate of the position of a shape model. We evaluate and compare our method on two public benchmarks: (i) the VISCERAL Grand Challenge on multi-organ segmentation of whole-body CT images and (ii) the Hammers brain atlas of MR images for segmenting the hippocampus and the amygdala. For this wide spectrum of both easy and hard segmentation tasks, our experimental quantitative results are on par or better than state-of-the-art. More importantly, we obtain qualitatively better segmentation boundaries, for instance, preserving topology and fine structures. (C) 2018 Elsevier B.V. All rights reserved.