Online resource for validation of brain segmentation methods.

Online resource for validation of brain segmentation methods.
复制标题

DOI:
10.1016/j.neuroimage.2008.10.066
复制
发表时间:
2009-04-01
期刊:
影响因子:
5.7
通讯作者:
Toga AW
Toga AW
中科院分区:
医学1区
文献类型:
--
作者:
Shattuck DW;Prasad G;Mirza M;Narr KL;Toga AW

文献摘要

参考文献

被引文献

相似文献

在图像分割算法的开发过程中必须解决的一个关键问题是它们产生的结果的准确性。算法开发人员需要这样做,以便他们可以了解哪些方法需要改进,并了解新开发与现有开发相比如何。算法的用户在选择算法并将其应用于神经影像分析应用时还需要了解算法的特征。人们提出了许多指标来描述分割中的错误率和成功率,并且也公开了一些数据集以供评估。尽管如此,分析和报告这些结果所使用的方法因研究而异,因此即使研究使用相同的指标,其数值结果也不一定具有直接可比性。为了解决这个问题,我们开发了一个基于网络的资源,用于评估 T1 加权 MRI 中颅骨剥离的性能。该资源提供了要分割的数据以及对数据执行验证研究的在线应用程序。用户可以下载测试数据集,使用他们希望评估的任何方法对其进行分割,并将分割结果上传到服务器。服务器计算一系列指标,显示验证结果的详细报告,并将这些结果存档以供将来浏览和分析。我们将该框架应用于几种不同程序设置下的 3 种流行的头骨剥离算法的评估——大脑提取工具、混合分水岭算法和大脑表面提取器。我们的结果表明,通过正确的参数选择,所有 3 种算法都可以在测试数据上实现令人满意的头骨剥离。
One key issue that must be addressed during the development of image segmentation algorithms is the accuracy of the results they produce. Algorithm developers require this so they can see where methods need to be improved and see how new developments compare with existing ones. Users of algorithms also need to understand the characteristics of algorithms when they select and apply them to their neuroimaging analysis applications. Many metrics have been proposed to characterize error and success rates in segmentation, and several datasets have also been made public for evaluation. Still, the methodologies used in analyzing and reporting these results vary from study to study, so even when studies use the same metrics their numerical results may not necessarily be directly comparable. To address this problem, we developed a web-based resource for evaluating the performance of skull-stripping in T1-weighted MRI. The resource provides both the data to be segmented and an online application that performs a validation study on the data. Users may download the test dataset, segment it using whichever method they wish to assess, and upload their segmentation results to the server. The server computes a series of metrics, displays a detailed report of the validation results, and archives these for future browsing and analysis. We applied this framework to the evaluation of 3 popular skull-stripping algorithms – the Brain Extraction Tool, the Hybrid Watershed Algorithm, and the Brain Surface Extractor under several different program settings. Our results show that with proper parameter selection, all 3 algorithms can achieve satisfactory skull-stripping on the test data.
DOI: 10.1016/j.neuroimage.2007.09.031
发表时间: 2008-02-01
期刊: NEUROIMAGE
影响因子: 5.7
作者:
Shattuck, David W.;Mirza, Mubeena;Toga, Arthur W.
通讯作者: Toga, Arthur W.
DOI: 10.1109/42.668698
发表时间: 1998-02-01
影响因子: 10.6
作者:
Sled, JG;Zijdenbos, AP;Evans, AC
通讯作者: Evans, AC
DOI: 10.1109/tmi.2007.895453
发表时间: 2007-05-01
影响因子: 10.6
作者:
Tohka, Jussi;Krestyannikov, Evgeny;Toga, Arthur W.
通讯作者: Toga, Arthur W.
DOI: 10.1109/tmi.2007.893283
发表时间: 2007-04-01
影响因子: 10.6
作者:
Bazin, Pierre-Louis;Pham, Dzung L.
通讯作者: Pham, Dzung L.
DOI: 10.1109/42.811270
发表时间: 1999-10-01
影响因子: 10.6
作者:
Van Leemput, K;Maes, F;Suetens, P
通讯作者: Suetens, P