首页> 外文会议>Multimodal Brain Image Analysis >Simultaneous Brain Structures Segmentation Combining Shape and Pose Forces
【24h】

Simultaneous Brain Structures Segmentation Combining Shape and Pose Forces

机译:结合形状和姿势力的同时脑结构分割

获取原文
获取原文并翻译 | 示例

摘要

This paper presents a new supervised learning based method for brain structure segmentation. We learn moment-based signatures of structures of interest and formulate the segmentation as a maximum a-posteriori estimation problem employing nonparametric multivariate kernel densities. For this problem, we propose a gradient flow solution. We have compared our method with state-of-the-art methods such as FSL-FIRST and Free-Surfer using volumetric 3T from IBSR. In addition, we have evaluated our algorithm on 7T MR data. We report comparative results of accuracy and significantly improved time-efficiency.
机译:本文提出了一种新的基于监督学习的脑结构分割方法。我们学习感兴趣结构的基于矩的签名,并将分段公式化为采用非参数多元核密度的最大后验估计问题。针对此问题,我们提出了一种梯度流解决方案。我们已经将我们的方法与最先进的方法(例如,使用IBSR的体积3T进行的FSL-FIRST和Free-Surfer)进行了比较。此外,我们已经根据7T MR数据评估了我们的算法。我们报告了准确性的比较结果,并显着提高了时间效率。

著录项

  • 来源
    《Multimodal Brain Image Analysis》|2011年|p.143-151|共9页
  • 会议地点 Toronto(CA);Toronto(CA);Toronto(CA);Toronto(CA)
  • 作者单位

    Philips Research, Eindhoven, 5656AE, The Netherlands;

    Division of Image Processing, Department of Radiology, Leiden University Medical Center, The Netherlands;

    CJ Gorter center for High Field MRI, Department of Radiology, Leiden University Medical Center, The Netherlands;

    Department of Radiology, Leiden University Medical Center, The Netherlands;

    Division of Image Processing, Department of Radiology, Leiden University Medical Center, The Netherlands;

    Philips Research, Eindhoven, 5656AE, The Netherlands;

  • 会议组织
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类 医用物理学;脑部疾病;
  • 关键词

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号