Medisys, Philips Research Paris, France; PhySense, ETIC, Universitat Pompeu Fabra, Barcelona, Spain.
Medisys, Philips Research Paris, France.
Med Image Anal. 2020 Feb;60:101594. doi: 10.1016/j.media.2019.101594. Epub 2019 Nov 6.
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.
替代压力超声心动图方案，如握力运动，相比于目前在临床实践中采用的方案，可能更有利于大规模筛查。然而，这些方案仍未得到充分探索，因为最大运动水平不易量化和调节，需要分析完整的数据序列（数千张图像），这对临床医生来说是一项具有挑战性的任务。我们提出了一种分析这些复杂数据集的框架，并在手握运动数据集上进行了说明，该数据集包括 10 名健康对照者和 5 名 ANT1 突变患者的完整采集（1377 个心动周期）。该框架基于多核学习的无监督公式，用于整合来自心肌速度轨迹和心率的信息，以获得数据的低维表示。然后，这种简化的表示形式被探索用于区分反应组并理解潜在的病理生理机制。分析流程涉及使用多尺度核回归重建群体特异性特征，并根据其投影序列定义的轨迹对受试者进行聚类。结果证实，所提出的框架能够检测到有区别的反应簇，并提供有关潜在病理生理学的见解。
