A computer-aided detection of EEG seizures in infants: A singular-spectrum approach and performance comparison

被引:107
作者
Celka, P
Colditz, P
机构
[1] Queensland Univ Technol, Signal Proc Res Ctr, Brisbane, Qld 4001, Australia
[2] Univ Queensland, Royal Hosp Women, Perinatal Res Ctr, Brisbane, Qld 4029, Australia
基金
澳大利亚研究理事会;
关键词
detection; EEG seizure; infant; MDL; newborn; singular spectrum analysis;
D O I
10.1109/10.995684
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
This paper presents a scalp electroencephalogram (EEG) seizure detection scheme based on singular spectrum analysis (SSA) and Rissanen minimum description length (MDL) model-order selection (SSA-MDL). Preprocessing of the signals allows for the drastic reduction of the number of false alarms. Statistical performance comparison with seizure detection schemes of Gotman et al. and Liu et al. is performed on both synthetic data and real EEG seizures. Monte Carlo simulations based on synthetic infant EEG seizure data reveals some detection drawbacks on a large variety of seizure waveforms. Detection using both Monte Carlo and four real infant scalp EEG signals shows the superiority of the SSA-MDL method with an average good detection rate of > 93 % and false detection rate < 4 %.
引用
收藏
页码:455 / 462
页数:8
相关论文
共 35 条
[1]  
[Anonymous], ELECTROENCEPHALOGR C
[2]  
BERGEY GK, 2001, ELECTROENCEPHALOGR C, V112, P241
[3]   EXTRACTING QUALITATIVE DYNAMICS FROM EXPERIMENTAL-DATA [J].
BROOMHEAD, DS ;
KING, GP .
PHYSICA D, 1986, 20 (2-3) :217-236
[4]   Time-varying statistical dimension analysis with application to newborn scalp EEG seizure signals [J].
Celka, P ;
Colditz, P .
MEDICAL ENGINEERING & PHYSICS, 2002, 24 (01) :1-8
[5]   Preprocessing and time-frequency analysis of newborn EEG seizures [J].
Celka, P ;
Boashash, B ;
Colditz, P .
IEEE ENGINEERING IN MEDICINE AND BIOLOGY MAGAZINE, 2001, 20 (05) :30-39
[6]  
CELKA P, 2001, EMBS2001 IST TURK
[7]  
CELKA P, IN PRESS IEEE T BIOM
[8]  
DASILVA FHL, 1974, KYBERNETIK, V15, P27, DOI DOI 10.1007/BF00270757
[9]  
ELLINGSON RJ, 1990, CLIN NEUROPHYSIOL, V4, P79
[10]   Time-frequency analysis using the matching pursuit algorithm applied to seizures originating from the mesial temporal lobe [J].
Franaszczuk, PJ ;
Bergey, GK ;
Durka, PJ ;
Eisenberg, HM .
ELECTROENCEPHALOGRAPHY AND CLINICAL NEUROPHYSIOLOGY, 1998, 106 (06) :513-521