Medically relevant criteria used in EEG compression for improved post-compression seizure detection

@article{Daou2014MedicallyRC,
  title={Medically relevant criteria used in EEG compression for improved post-compression seizure detection},
  author={Hoda Daou and Fabrice Labeau},
  journal={2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society},
  year={2014},
  pages={697-701}
}
  • H. DaouF. Labeau
  • Published 30 April 2014
  • Computer Science
  • 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Biomedical signals aid in the diagnosis of different disorders and abnormalities. When targeting lossy compression of such signals, the medically relevant information that lies within the data should maintain its accuracy and thus its reliability. In fact, signal models that are inspired by the biophysical properties of the signals at hand allow for a compression that preserves more naturally the clinically significant features of these signals. In this paper, we illustrate this through the… 

Figures and Tables from this paper

Lossy compression techniques for EEG signals

A survey of existing lossy compression algorithms reported in the last two decades to provide a qualitative comparison among them and to select a suitable lossy EEG compression technique.

References

SHOWING 1-10 OF 14 REFERENCES

Performance analysis of a 2-D EEG compression algorithm using an automatic seizure detection system

  • H. DaouF. Labeau
  • Computer Science
    2012 Conference Record of the Forty Sixth Asilomar Conference on Signals, Systems and Computers (ASILOMAR)
  • 2012
A framework to evaluate the performance of EEG compression mechanisms in terms of post-compression seizure detection capability is proposed and it is shown that the above-mentioned 2-D algorithm can maintain diagnostic features down to bitrates of 2 bits per sample.

Dynamic Dictionary for Combined EEG Compression and Seizure Detection

  • H. DaouF. Labeau
  • Computer Science
    IEEE Journal of Biomedical and Health Informatics
  • 2014
The algorithm can positively detect seizure sections in the recordings at bitrates down to 2 bits per sample, and can not only compress EEG channels in one dimension (1-D), but also detect seizure-like activity.

Pre-Processing of multi-channel EEG for improved compression performance using SPIHT

  • H. DaouF. Labeau
  • Computer Science
    2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society
  • 2012
Experimental results show that this technique is able to provide low distortion values for high compression ratios (CRs) and performance results of this method do not vary a lot between different patients which proves the stability of the method when used with recordings of different characteristics.

EEG Compression of Scalp Recordings Based on Dipole Fitting

  • H. DaouF. Labeau
  • Computer Science
    IEEE Journal of Biomedical and Health Informatics
  • 2015
A novel technique for electroencephalogram (EEG) compression is proposed, based on methods borrowed from dipole fitting that is usually used in order to find a solution to the classic problems in EEG analysis: inverse and forward problems.

Long-term EEG compression for intensive-care settings.

  • R. AgarwalJ. Gotman
  • Computer Science
    IEEE engineering in medicine and biology magazine : the quarterly magazine of the Engineering in Medicine & Biology Society
  • 2001
The proposed method presents samples of original EEG that represent the long-term EEG along with their temporal distribution to the user and is intended to provide a summary of the EEG and should be used to supplement the EEG.

Wavelet compression of ECG signals by the set partitioning in hierarchical trees algorithm

A wavelet electrocardiogram (ECG) data codec based on the set partitioning in hierarchical trees (SPIHT) compression algorithm is proposed and is significantly more efficient in compression and in computation than previously proposed ECG compression schemes.

Automatic recognition of epileptic seizures in the EEG.

  • J. Gotman
  • Medicine
    Electroencephalography and clinical neurophysiology
  • 1982

Wavelet Compression of ECG Signals by the Set Partitioning in Hierarchical Trees ( SPIHT ) Algorithm

A wavelet ECG data codec based on the Set Partitioning In Hierarchical Trees (SPIHT) compression algorithm is proposed and revealed that the proposed codec is significantly more efficient in compression and in computation than previously proposed ECG compression schemes.

Review of methods for solving the EEG inverse problem

This paper reviews the class of instantaneous, 3D, discrete, linear solutions for the EEG inverse problem. Five different inverse methods are analyzed and compared: minimum norm, weighted minimum

Independent component analysis for EEG source localization

A spatiotemporal method for source localization, taking advantage of the entire EEG time series to reduce the configuration space the authors must evaluate and substantially reduce the search complexity and increase the likelihood of efficiently converging on the correct solution.