首页> 外文会议>2016 IEEE First Conference on Connected Health: Applications, Systems and Engineering Technologies >Large Scale Cloud-Based Deformable Registration for Image Guided Therapy
【24h】

Large Scale Cloud-Based Deformable Registration for Image Guided Therapy

机译:基于大规模基于云的可变形配准,用于图像引导治疗

获取原文
获取原文并翻译 | 示例

摘要

We present a feasibility study using cloud resources for computing the deformable registration or non-rigid registration (NRR) of brain MR images for Image Guided Neurosurgery (IGNS). We consider the use of cloud resources in two scenarios. First, we describe a workflow implementation to enable speculative computation of registration to improve confidence in the result and assist in retrospective evaluation of the method. We evaluate the use of computing and storage capabilities of the cloud to handle more than 6 TB of images. Second, we evaluate the feasibility of large scale running NRR on the cloud to provide timely execution of the most time-consuming components of the registration in short duration of a brain surgery. Our preliminary results indicate that the cloud provides practical and cost-effective means to support IGNS. In addition, cloud resources could be used to improve the accuracy of NRR up to 57%.
机译:我们提出了使用云资源来计算图像引导神经外科手术(IGNS)的大脑MR图像的可变形配准或非刚性配准(NRR)的可行性研究。我们考虑在两种情况下使用云资源。首先,我们描述一种工作流实现,以实现注册的推测性计算,以提高结果的置信度并协助对该方法进行回顾性评估。我们评估了使用云计算和存储功能来处理6 TB以上的图像。其次,我们评估了在云上大规模运行NRR的可行性,以在脑外科手术的短时间内及时执行最耗时的注册过程。我们的初步结果表明,云提供了实用且具有成本效益的方式来支持IGNS。此外,云资源可用于将NRR的准确性提高多达57%。

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