Bayesian tracking of intracranial pressure signal morphology.
Bayesian tracking of intracranial pressure signal morphology.
复制标题
DOI：
10.1016/j.artmed.2011.08.007
复制
发表时间：
2012-02
影响因子：
7.5
通讯作者：
Hu, Xiao
中科院分区：
文献类型：
--
作者：
Scalzo, Fabien;Asgari, Shadnaz;Kim, Sunghan;Bergsneider, Marvin;Hu, Xiao
关键词：
颅内压（ICP）脉冲的波形形态包含了颅内和脑血管病理生理变化的重要信息。大多数当前ICP脉冲分析框架独立地处理每个脉冲，因此不利用连续脉冲之间存在的时间依赖性。我们提出了一个概率框架，利用这种时间依赖性来跟踪ICP波形形态的三个峰值。共记录了128例因各种颅内压相关疾病接受治疗的患者的ICP和心电图（ECG）信号。跟踪被视为图形模型中的推理，该模型将随机变量与每个峰的位置相关联。一个关键的贡献是利用非参数贝叶斯推理算法，提供鲁棒性和真实的时间性能。一个简单而有效的学习过程使用从手动注释的脉冲收集的证据以非参数方式估计峰值之间的统计非线性依赖关系。实验证明了该跟踪框架对真实的ICP脉冲的有效性及其对遮挡和丢失峰值的鲁棒性。在人工畸变的ICP序列上，与MOCAIP检测器相比，潜伏期的平均误差分别为：第一峰11.88- 8.09ms，第二峰11.80- 6.90ms，第三峰11.76- 7.46ms。所提出的跟踪算法成功地提高了检测ICP脉冲形态变化的时间分辨率，从分钟级到搏动级。
The waveform morphology of intracranial pressure (ICP) pulses holds essential informations about intracranial and cerebrovascular pathophysiological variations. Most of current ICP pulse analysis frameworks process each pulse independently and therefore do not exploit the temporal dependency existing between successive pulses. We propose a probabilistic framework that exploits this temporal dependency to track ICP waveform morphology in terms of its three peaks. ICP and electrocardiogram (ECG) signals were recorded from a total of 128 patients treated for various intracranial pressure related conditions. The tracking is posed as inference in a graphical model that associates a random variable to the position of each peak. A key contribution is to exploit a nonparametric Bayesian inference algorithm that offers robustness and real time performance. A simple, yet effective learning procedure estimates the statistical, nonlinear, dependencies between the peaks in a nonparametric way using evidence collected from manually annotated pulses. Experiments demonstrate the effectiveness of the tracking framework on real ICP pulses and its robustness to occlusion and missing peaks. On artificialy distorted ICP sequences, the average error in latency in comparision with MOCAIP detector was reduced as follows: 11.88–8.09 ms, 11.80–6.90 ms, and 11.76–7.46 ms for the first, second, and third peak, respectively. The proposed tracking algorithm sucessfuly increases the temporal resolution of detecting ICP pulse morphological changes from the minute-level to the beat-level.
登录
查看更多内容
DOI：
10.1109/tbme.2008.2008636
发表时间：
2009-03
期刊：
IEEE transactions on bio-medical engineering
影响因子：
--
作者：
Hu X;Xu P;Scalzo F;Vespa P;Bergsneider M
通讯作者：
Bergsneider M
影响因子：
3.2
作者：
Scalzo, Fabien;Xu, Peng;Asgari, Shadnaz;Bergsneider, Marvin;Hu, Xiao
通讯作者：
Hu, Xiao
影响因子：
3
作者：
CONTANT, CF;ROBERTSON, CS;GROSSMAN, RG
通讯作者：
GROSSMAN, RG
影响因子：
4.8
作者：
PORTNOY, HD;CHOPP, M
通讯作者：
CHOPP, M
影响因子：
4.6
作者：
Afonso, VX;Tompkins, WJ;Luo, S
通讯作者：
Luo, S