Outline

  • Abstract
  • Keywords
  • 1. Introduction
  • 1.1. Methods for Detection of Epilepsy
  • 1.2. Eeg Analysis for Epilepsy Detection
  • 2. Methods
  • 2.1. Eeg Analysis Methods
  • 2.1.1. Time Domain Methods
  • 2.1.2. Frequency Domain Methods
  • 2.1.3. Time–frequency Domain Methods
  • 2.1.4. Nonlinear Method of Analysis
  • 2.2. Surrogate Data Analysis
  • 2.3. Necessity of Nonlinear Methods for Eeg Analysis
  • 3. Epilepsy Activity Classification
  • 3.1. Studies That Presented Techniques for Two-Class (normal, Ictal) Epilepsy Activity Classification
  • 3.2. Studies That Presented Techniques for Three-Class (normal, Interictal, Ictal Stages) Epilepsy Activity Classification
  • 4. Conclusions
  • References

رئوس مطالب

  • چکیده
  • کلیدواژه ها
  • 1.مقدمه
  • 1.1.روش‌های تشخیص صرع
  • 1.2. تحلیل الکتروانسفالوگرام جهت تشخیص صرع
  • 2.روش‌ها
  • 2.1. روش‌های تحلیل الکتروانسفالوگرام
  • 2.1.1. روش‌های دامنه زمان
  • 2.1.2. روش‌های دامنه فرکانس
  • 2.1.3. روش‌های دامنه زمان- فرکانس
  • 2.1.4. روش تحلیل غیرخطی
  • 2.2. تحلیل داده‌های جایگزین
  • 2.3. ضرورت روش‌های غیرخطی در تحلیل الکتروانسفالوگرام
  • 3. دسته‌بندی فعالیت صرع
  • 3.1. تحقیقات ارائه‌دهنده تکنیک‌های دسته‌بندی دو گونه (عادی، ایکتال) فعالیت صرع
  • 3.2. تحقیقات ارائه‌دهنده تکنیک‌های دسته‌بندی سه گونه (مراحل عادی، اینترایکتال، ایکتال) فعالیت صرع
  • 4. نتیجه‌گیری

Abstract

Epilepsy is an electrophysiological disorder of the brain, characterized by recurrent seizures. Electroencephalogram (EEG) is a test that measures and records the electrical activity of the brain, and is widely used in the detection and analysis of epileptic seizures. However, it is often difficult to identify subtle but critical changes in the EEG waveform by visual inspection, thus opening up a vast research area for biomedical engineers to develop and implement several intelligent algorithms for the identification of such subtle changes. Moreover, the EEG signals are nonlinear and non-stationary in nature, which contribute to further complexities related to their manual interpretation and detection of normal and abnormal (interictal and ictal) activities. Hence, it is necessary to develop a Computer Aided Diagnostic (CAD) system to automatically identify the normal and abnormal activities using minimum number of highly discriminating features in classifiers. It has been found that nonlinear features are able to capture the complex physiological phenomena such as abrupt transitions and chaotic behavior in the EEG signals. In this review, we discuss various feature extraction methods and the results of different automated epilepsy stage detection techniques in detail. We also briefly present the various open ended challenges that need to be addressed before a CAD based epilepsy detection system can be set-up in a clinical setting.

Keywords: - - - - - - - -

Conclusions

EEG signals can be used effectively to study the mental states and ailments related to the brain. The inherent issues with the EEG signal are that it is highly nonlinear in nature and its visual interpretations are tedious and subjective prone to inter-observer variations. To help researchers better analyze EEG signals, we have presented various signal analysis techniques such as linear, frequency domain, time–frequency, and nonlinear methods in this review. Our key focus in this review was on epilepsy detection. Epilepsy is a neurological disorder that can cause serious discomfort to the patients due to its abrupt and uncertain nature of presentation. A good side of it is that it is treatable with antiepileptics. An automated system to detect the nature of the seizures at early stage (interictal) and to classify normal, interictal, and ictal states can help improving the quality of life by preventing its occurrence. In this regard, we have summarized the findings of many automated epilepsy activity classification techniques that use EEG as the base signal. It is evident from the summary that a combination of the features extracted using the reviewed techniques or sometimes even the features extracted from a single technique can successfully distinguish the three classes. It appears that the use of nonlinear features extracted from EEG segments in classifiers results in high classification accuracies of more than 99%. Even though the highest possible classification accuracy has been achieved for epilepsy activity detection, there are several challenges that have to be faced before such a technique can be clinically used. We have briefly highlighted these challenges and open ended problems that need to be addressed for a fully automated CAD based epilepsy detection and seizure monitoring system to be deployed in a clinical setting.

دانلود ترجمه تخصصی این مقاله دانلود رایگان فایل pdf انگلیسی