首页> 外文会议>Multimodal Brain Image Analysis >Joint Tl and Brain Fiber Diffeomorphic Registration Using the Demons
【24h】

Joint Tl and Brain Fiber Diffeomorphic Registration Using the Demons

机译:联合Tl和使用恶魔的脑纤维异形配准

获取原文
获取原文并翻译 | 示例

摘要

Non-linear image registration is one of the most challenging task in medical image analysis. In this work, we propose an extension of the well-established diffeomorphic Demons registration algorithm to take into account geometric constraints. Combining the deformation field induced by the image and the geometry, we define a mathematically sound framework to jointly register images and geometric descriptors such as fibers or sulcal lines. We demonstrate this framework by registering simultaneously T_1 images and 50 fiber bundles consistently extracted in 12 subjects. Results show the improvement of fibers alignment while maintaining, and sometimes improving image registration. Further comparisons with non-linear T_1 and tensor registration demonstrate the superiority of the Geometric Demons over their purely iconic counterparts.
机译:非线性图像配准是医学图像分析中最具挑战性的任务之一。在这项工作中,我们提出了一种完善的微分形恶魔注册算法,以考虑到几何约束。结合图像和几何形状引起的变形场,我们定义了一个数学上合理的框架,以共同注册图像和诸如纤维或沟渠线的几何描述符。我们通过同时注册在12个主题中一致提取的T_1图像和50根光纤束来演示此框架。结果表明,在保持纤维排列的同时改善了排列,有时还改善了图像配准。与非线性T_1和张量配准的进一步比较表明,几何恶魔比它们的纯标志性同类具有优越性。

著录项

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