Abstract WMP60: Automatic Embolic Signal Detection Using Adaptive Wavelet Packet Transform and Adaptive Neuro-Fuzzy Inference System

Abstract

Introduction: Transcranial Doppler(TCD) can be used to detect emboli in cerebral circulation. To classify the measured TCD as an embolic signal (ES) or artifact is usually done by a well-trained physician. However, inter-rater reliability among those physicians is variable. Also,in countries where skilled physicians are scarce, an automatic ES detection system can be useful as a medical support system. Method: We propose a two-step algorithm based on adaptive Wavelet Packet Transform (WPT) and Adaptive Neuro-Fuzzy Inference System (ANFIS) described as follows. First, the TCD signal is windowed using a 256-sample Gaussian window with 80% overlap. A 3-level WPT is used to transform each windowed TCD signal. The best basis algorithm is applied to find the best binary tree from which the entropy and normalized energy are calculated. The entropy and normalized energy are used as features to classify each windowed TCD signal as normal or abnormal. Second, the abnormal TCD windows are classified further as ES or artifact. Specifically, standard deviation of level 3 WPT coefficients from frequency index 1 to 6 are calculated and used as inputs of ANFIS where each standard deviation can be combined with others resulting in 64 rules. After training the ANFIS, ES and artifact can be differentiated. Results: Six hundred and sixty abnormal signals in vivo are used to evaluate the algorithm, i.e., 176 ESs collected during emboli monitoring from patients undergoing carotid angioplasty with stenting and from patients with patent foramen ovale, 106 artifacts from normal subjects, and 378 artifacts from stroke patients with carotid stenosis. The signals are divided into training and validation sets. The training set is used to train the algorithm and the validation set is used to evaluate the validity of the algorithm. Experimental results show that the algorithm can differentiate abnormal from normal signals efficiently with 100% accuracy. A sensitivity of 96.6% and specificity of 96.5% can be achieved from the validation set. Conclusions: The automatic embolic signal detection algorithm has been developed. The experimental results suggested that the algorithm could detect emboli and differentiate artifacts efficiently and could be used as a medical support system.