Dynamic Dictionary for Combined EEG Compression and Seizure Detection

A novel technique for real-time electroencephalogram (EEG) compression is proposed in this paper. This technique makes use of the redundancy between the different frequency subbands present in EEG segments of one channel. It uses discrete wavelet transform (DWT) and dynamic reference lists to compute and send the decorrelated subband coefficients. Set partitioning in hierarchical trees (SPIHT) is also used as source coder. Experimental results showed that the proposed method can not only compress EEG channels in one dimension (1-D), but also detect seizure-like activity. A diagnostics-oriented performance assessment was performed to evaluate the performance of both the compression and detection capabilities of the proposed method. In this paper, we show that the algorithm can positively detect seizure sections in the recordings at bitrates down to 2 bits per sample.

[1]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

[2]  K. Srinivasan,et al.  Efficient preprocessing technique for real-time lossless EEG compression , 2010 .

[3]  J. Gotman.  Automatic recognition of epileptic seizures in the EEG. , 1982, Electroencephalography and clinical neurophysiology.

[4]  Marie-Françoise Lucas,et al.  Optimal wavelets for biomedical signal compression , 2006, Medical and Biological Engineering and Computing.

[5]  K. Srinivasan.  Selection of Optimal wavelet for lossless EEG compression for real-time applications , 2009 .

[6]  B. Siddik Yarman,et al.  EEG signal compression based on Classified Signature and Envelope Vector Sets , 2007, 2007 18th European Conference on Circuit Theory and Design.

[7]  Pamela C. Cosman,et al.  Evaluating quality of compressed medical images: SNR, subjective rating, and diagnostic accuracy , 1994, Proc. IEEE.

[8]  J. Gotman,et al.  Wavelet based automatic seizure detection in intracerebral electroencephalogram , 2003, Clinical Neurophysiology.

[9]  J. Gotman,et al.  Long-term EEG compression for intensive-care settings. , 2001, IEEE engineering in medicine and biology magazine : the quarterly magazine of the Engineering in Medicine & Biology Society.

[10]  E. Jones,et al.  Lossy compression of EEG signals using SPIHT , 2011 .

[11]  A.J. Casson,et al.  Data reduction techniques to facilitate wireless and long term AEEG epilepsy monitoring , 2007, 2007 3rd International IEEE/EMBS Conference on Neural Engineering.

[12]  C. Eswaran,et al.  Context Based Error Modeling for Lossless Compression of EEG Signals Using Neural Networks , 2006, Journal of Medical Systems.

[13]  Fabrice Labeau,et al.  Performance analysis of a 2-D EEG compression algorithm using an automatic seizure detection system , 2012, 2012 Conference Record of the Forty Sixth Asilomar Conference on Signals, Systems and Computers (ASILOMAR).

[14]  C. Eswaran,et al.  An Adaptive Error Modeling Scheme for the Lossless Compression of EEG Signals , 2008, IEEE Transactions on Information Technology in Biomedicine.

[15]  William A. Pearlman,et al.  Wavelet compression of ECG signals by the set partitioning in hierarchical trees algorithm , 2000, IEEE Transactions on Biomedical Engineering.

[16]  Ali H. Shoeb,et al.  Application of Machine Learning To Epileptic Seizure Detection , 2010, ICML.

[17]  Fabrice Labeau,et al.  Pre-Processing of multi-channel EEG for improved compression performance using SPIHT , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[18]  Julián Cárdenas-Barrera,et al.  A wavelet-packets based algorithm for EEG signal compression , 2004, Medical informatics and the Internet in medicine.

[19]  Fabrice Labeau,et al.  A Channel Differential EZW Coding Scheme for EEG Data Compression , 2011, IEEE Transactions on Information Technology in Biomedicine.

[20]  J. Gotman,et al.  A system to detect the onset of epileptic seizures in scalp EEG , 2005, Clinical Neurophysiology.

[21]  S. Mitra,et al.  Iterative function system and genetic algorithm-based EEG compression. , 1997, Medical engineering & physics.

[22]  N Pradhan,et al.  Data compression by linear prediction for storage and transmission of EEG signals. , 1994, International journal of bio-medical computing.

[23]  Ali H. Shoeb,et al.  Application of machine learning to epileptic seizure onset detection and treatment , 2009 .