Characterizing spatially varying performance to improve multi-atlas multi-label segmentation.

Characterizing spatially varying performance to improve multi-atlas multi-label segmentation.
复制标题

DOI:
10.1007/978-3-642-22092-0_8
复制
发表时间:
2011
期刊:
LECTURE NOTES IN ARTIFICIAL INTELLIGENCE
影响因子:
--
通讯作者:
Landman, Bennett A.
Landman, Bennett A.
中科院分区:
其他
文献类型:
--
作者:
Asman, Andrew J.;Landman, Bennett A.

文献摘要

参考文献

被引文献

相似文献

医学图像的分割已经成为了解生物结构-功能关系的关键。Atlas登记和标签转移提供了一种完全自动化的方法,用于根据atlas训练数据得出分词。当使用多个地图集时,统计标签融合技术已被证明能够显著提高分割精度。然而,这些技术在处理与目标数据有不同相似性的复杂结构和地图集方面取得的成功有限。以前的方法通过单个混淆矩阵对评分者进行参数化,从而忽略了单个评分者的空间变化性能。在本文中,我们重新定义了统计融合模型,通过区域混淆矩阵来描述评分者,使得共同注册的地图集标签可以以最优的、空间变化的方式进行融合,从而改进了对异质地图集的标签融合估计。这种方法的优势体现在模拟和经验性的全脑标记任务中。
Segmentation of medical images has become critical to building understanding of biological structure-functional relationships. Atlas registration and label transfer provide a fully-automated approach for deriving segmentations given atlas training data. When multiple atlases are used, statistical label fusion techniques have been shown to dramatically improve segmentation accuracy. However, these techniques have had limited success with complex structures and atlases with varying similarity to the target data. Previous approaches have parameterized raters by a single confusion matrix, so that spatially varying performance for a single rater is neglected. Herein, we reformulate the statistical fusion model to describe raters by regional confusion matrices so that co-registered atlas labels can be fused in an optimal, spatially varying manner, which leads to an improved label fusion estimation with heterogeneous atlases. The advantages of this approach are characterized in a simulation and an empirical whole-brain labeling task.
DOI: 10.1109/tmi.2004.828354
发表时间: 2004-07-01
影响因子: 10.6
作者:
Warfield, SK;Zou, KH;Wells, WM
通讯作者: Wells, WM
DOI: 10.1109/tmi.2003.819299
发表时间: 2003-11-01
影响因子: 10.6
作者:
Rohde, GK;Aldroubi, A;Dawant, BM
通讯作者: Dawant, BM
DOI: 10.2307/1932409
发表时间: 1945-01-01
期刊: ECOLOGY
影响因子: 4.8
作者:
DICE, LR
通讯作者: DICE, LR
DOI: 10.1109/tmi.2008.2011480
发表时间: 2009-07-01
影响因子: 10.6
作者:
Isgum, Ivana;Staring, Marius;van Ginneken, Brain
通讯作者: van Ginneken, Brain
DOI: 10.1002/jmri.1880020603
发表时间: 1992-11-01
期刊: JMRI-JOURNAL OF MAGNETIC RESONANCE IMAGING
影响因子: --
作者:
KIKINIS, R;SHENTON, ME;JOLESZ, FA
通讯作者: JOLESZ, FA