...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Medical image analysis >Analysis of nonstandardized stress echocardiography sequences using multiview dimensionality reduction
【24h】

Analysis of nonstandardized stress echocardiography sequences using multiview dimensionality reduction

机译：利用多视图维度减少的非标准应激超声心动图序列分析

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Alternative stress echocardiography protocols such as handgrip exercise are potentially more favorable towards large-scale screening scenarios than those currently adopted in clinical practice. However, these are still underexplored because the maximal exercise levels are not easily quantified and regulated, requiring the analysis of the complete data sequences (thousands of images), which represents a challenging task for the clinician. We propose a framework for the analysis of these complex datasets, and illustrate it on a handgrip exercise dataset including complete acquisitions of 10 healthy controls and 5 ANT1 mutation patients (1377 cardiac cycles). The framework is based on an unsupervised formulation of multiple kernel learning, which is used to integrate information coming from myocardial velocity traces and heart rate to obtain a lower-dimensional representation of the data. Such simplified representation is then explored to discriminate groups of response and understand the underlying pathophysiological mechanisms. The analysis pipeline involves the reconstruction of population-specific signatures using multiscale kernel regression, and the clustering of subjects based on the trajectories defined by their projected sequences. The results confirm that the proposed framework is able to detect distinctive clusters of response and to provide insight regarding the underlying pathophysiology. (C) 2019 Elsevier B.V. All rights reserved.
机译：替代的应力超声心动图（如手柄锻炼）可能比目前临床实践所采用的大规模筛查情景更有利。然而，这些仍然是曝光率的，因为最大运动水平不容易被量化和调节，需要分析完整的数据序列（数千种图像），这代表了临床医生的具有挑战性的任务。我们提出了一种分析这些复杂数据集的框架，并在手柄锻炼数据集中说明，包括完全采集的10个健康对照和5名Ant1突变患者（1377个心脏循环）。该框架基于多个内核学习的无监督制剂，其用于集成来自心肌速度迹线和心率的信息，以获得数据的较低尺寸表示。然后探讨这种简化的表示来区分响应组并理解潜在的病理生理机制。分析管道涉及使用多尺度内核回归重建人口特定签名，以及基于由预计序列定义的轨迹的受试者的聚类。结果证实，所提出的框架能够检测到具有涉及潜在病理生理学的独特响应集群。 （c）2019年Elsevier B.V.保留所有权利。

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