COMPUTERIZED EEG PATTERN-CLASSIFICATION BY ADAPTIVE SEGMENTATION AND PROBABILITY DENSITY-FUNCTION CLASSIFICATION - CLINICAL-EVALUATION
COMPUTERIZED EEG PATTERN-CLASSIFICATION BY ADAPTIVE SEGMENTATION AND PROBABILITY DENSITY-FUNCTION CLASSIFICATION - CLINICAL-EVALUATION
复制标题
DOI：
10.1016/0013-4694(85)91012-0
复制
发表时间：
1985-01-01
期刊：
影响因子：
--
通讯作者：
BARLOW, JS
中科院分区：
文献类型：
--
作者：
CREUTZFELDT, OD;BODENSTEIN, G;BARLOW, JS
通过计算机分析了一系列显示各种正常和异常模式的 63 个临床脑电图，特别参考同一脑电图内的不同类型模式。不同模式之间的边界是通过自适应分段建立的，因此所得片段的持续时间由特定脑电图本身决定（因此称为“自适应”）。分析每个脑电图的四个通道，同时对配对（左和右）通道进行分段和交互分析。然后通过估计具有平均频率和平均功率维度的二维特征空间中的概率密度函数，在没有监督的情况下对相似的片段进行聚类。单个簇出现为表面明确的峰、单个片段或持续时间不足以构成单独簇的小组，被识别为奇异事件（例如，罕见的锐波、伪影）。自相关函数用于表征脑电图的分割和随后对所得片段的聚类。基于脑电图自相关函数的自适应分割非常令人满意。通过估计特征空间中的概率密度函数进行的无监督聚类在大多数记录 (65%) 中给出了正确的聚类数量 (通常 < 5)，但在其余少数情况 (35%) 中，发生了过度聚类或聚类不足。奇异事件有时会部分包含在正式的集群中。将无监督概率密度函数估计的脑电图聚类结果与有监督层次聚类获得的早期结果进行比较表明，脑电图学家在脑电图模式分类中可能使用了微妙的线索，而迄今为止本工作中使用的计算机算法尚未充分近似这些线索。因此，至少在目前，聚类过程中至少某种程度的监督可能是必要的。该方法建议自身用于说明性脑电图摘要的表示，与简短的书面报告相结合，将为临床神经科医生提供真实脑电图的充分图片，而在大多数情况下，无需检查原始记录。
A series of 63 clinical EEG showing a variety of normal and abnormal patterns was analyzed by computer with particular reference to the different types of pattern within the same EEG. Boundaries between different patterns were establishedd by means of adaptive segmentation, so that the duration of the resulting segments was determined by the particular EEG itself (thus the term adaptive). Four channels from each EEG were analyzed, paired (left and right) channels were simultaneosly segmented and analyzed interactively. Similar segments were then clustered without supervision by estimating a probability density function in a 2-dimensional feature space having dimension of mean frequency and mean power. Individual clusters emerges as well-defined peaks of the surface, individual segments or small groups of duration insufficient to constitute a separate cluster, being identified as singular events (e.g, rare sharp waves, artifiacts). The autocorrelation function was used to characterize the EEG both for the segmentation and for the subsequent clustering of the resulting segments. Adaptive segmentation based on the autocorrelation function of the EEG was quite satisfactory. Unsupervised clustering by estimation of the probability density function in feature space gave the correct number of clusters (usually < 5) in a majority of the records (65%), but in the remaining minority of cases (35%), either overclustering or underclustering occurred. The singular events were occasionally partly included in a formal cluster. Comparison of these results of EEG clustering by unsupervised probability density function estimation with earlier results obtained by supervised hierarchical clustering suggests that there may be subtle cues used by the electroencephalographer in the classification of EEG patterns which have not been adequately approximated by the computer algorithms thus far used in this work. Hence at least some minimal degree of supervision in the clustering process may be necessary, at least for the present. The method recommends itself for the representation of illustrative EEG summaries which, in conjunction with a short written report, would provide the clinical neurologist with a sufficient picture of the real EEG without, in most cases, the need to inspect the original record.