Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Medically Relevant Criteria used in EEG Compression for Improved Post-Compression Seizure Detection

Hoda Daou, Fabrice Labeau

TL;DR

This paper analyzes three specific lossy EEG compression schemes based on signal models that have different degrees of reliance on signal production and physiological characteristics of EEG; the resilience of these schemes is illustrated through the performance of seizure detection post compression.

Abstract

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 bio-physical 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 example of EEG signals; more specifically, we analyze three specific lossy EEG compression schemes. These schemes are based on signal models that have different degrees of reliance on signal production and physiological characteristics of EEG. The resilience of these schemes is illustrated through the performance of seizure detection post compression.

Medically Relevant Criteria used in EEG Compression for Improved Post-Compression Seizure Detection

TL;DR

This paper analyzes three specific lossy EEG compression schemes based on signal models that have different degrees of reliance on signal production and physiological characteristics of EEG; the resilience of these schemes is illustrated through the performance of seizure detection post compression.

Abstract

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 bio-physical 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 example of EEG signals; more specifically, we analyze three specific lossy EEG compression schemes. These schemes are based on signal models that have different degrees of reliance on signal production and physiological characteristics of EEG. The resilience of these schemes is illustrated through the performance of seizure detection post compression.

Paper Structure

This paper contains 11 sections, 3 figures, 1 table.

Table of Contents

  1. INTRODUCTION
  2. Compression Methods
  3. Pre-Processing of Multi-Channel EEG for Improved Compression Performance using SPIHT
  4. Dynamic Dictionary for Combined EEG Compression and Seizure Detection
  5. EEG Compression of Scalp Recordings based on Dipole Fitting
  6. Results and Discussions
  7. Dataset
  8. Statistical Measures used in Detection Analysis
  9. Results
  10. Discussion
  11. CONCLUSION

Figures (3)

  • Figure 1: Bar plots showing the mean, maximum and minimum values of the detection results with Stellate Harmonie tested at $16$ bps as Ground Truth and bit rate equal to $2$bps.
  • Figure 2: Bar plots showing the mean, maximum and minimum values of the detection results with Stellate Harmonie tested at $16$ bps as Ground Truth and bit rate equal to $4$bps.
  • Figure 3: Scatter plot showing $TP$ with the Stellate Harmonie detections of the original files as Ground Truth with respect to the mean PRD values of all $12$ patients of MIT DB.