A New Approach for Investigating Intracranial Pressure Signal: Filtering and Morphological Features Extraction from Continuous Recording
A New Approach for Investigating Intracranial Pressure Signal: Filtering and Morphological Features Extraction from Continuous Recording
复制标题
DOI：
10.1109/tbme.2012.2191550
复制
发表时间：
2013-03-01
影响因子：
4.6
通讯作者：
Azzerboni, Bruno
中科院分区：
文献类型：
--
作者：
Calisto, Andrea;Galeano, Massimiliano;Azzerboni, Bruno
颅内压（ICP）监测已成为创伤性和慢性神经病变最常用的检查方法。ICP信号通常是三相的，也就是说，在单个波形中，可以识别三个子峰。这项工作概述了一种新的算法，以确定从ICP记录的次峰，并提取一些有意义的20个参数的趋势。通过与神经外科医生人工标记的亚峰进行比较，验证了该方法的有效性。自动标记系统已经识别了63.74%（平均值）脉搏波的子峰，提供了每个识别的子峰的位置和幅度，公差为+/-7个样本。这个自动系统提供了一个特征集，供分类软件使用，以便在所有涉及脑损伤或疾病的情况下获得更精确和更容易的诊断。
Nowadays, the Intracranial Pressure (ICP) monitoring has become the most common method of investigation for both traumatic and chronic neural pathologies. ICP signals are typically triphasic, that is, in a single waveform, three subpeaks can be identified. This work outlines a new algorithm to identify subpeaks from the ICP recordings and to extract a number of 20 meaningful parameter trends. The validity of the implemented method has been proved through a comparison between the automatic subpeaks identification by the algorithm and the manually marked subpeaks by a neurosurgeon. The automatic marking system has identified subpeaks for the 63.74% (mean value) of pulse waves, providing the position and amplitude of each identified subpeak within a tolerance of +/-7 samples. This automatic system provides a feature set to be used by classification software to obtain more precise and easier diagnosis in all those cases that involve brain damages or diseases.