|
Research Staff
|
Dr Edward Peter Riddington
|
Project
|
Automated Interpretation of the Background EEG using Fuzzy Logic
|
Director of Studies
|
Professor Emmanuel C. Ifeachor
|
Ph.D Project and Thesis
Automated Interpretation of the Background EEG using Fuzzy Logic
Edward Peter Riddington |
Abstract:
A new framework is described for managing uncertainty and for dealing
withartefact corruption to introduce objectivity in the interpretation of the
electroencephalogram(EEG).
Conventionally, EEG interpretation is time consuming and subjective, and is
known to showsignificant inter- and intra-personnel variation. A need thus
exists to automate the interpretationof the EEG to provide a more consistent
and efficient assessment. However, automated analysis ofEEGs by computer is
complicated by two major factors. the difficulty of adequate capturing
inmachine form, the skills and subjective expertise of the experienced
electroencephalographer, andthe lack of a reliable means of dealing with the
range of EEG artefacts (signal contamination). Inthis thesis, a new framework
is described which introduces objectivity in to important outcomes of clinical
evaluation of the EEG, namely, the clinical factual report and the clinical
'conclusion',by capturing the subjective expertise of the and dealing with the
problems of artefact corruption.
The framework is separated into two stages to assist piecewise optimization and
to cater fordifferent requirements. the first stage, 'quantitative analysis',
relies on novel digital signal processing algorithm and cluster analysis
techniques to reduce data and identify and describebackground activities in the
EEG. To deal with artefact corruption, an artefact removal strategy,based on a
new reliable techniques for artefact identification is used to ensure that
artefact-freeactivities only are used in the analysis. The outcome is a
quantitative analysis, which efficientlydescribe background activity in the
record, and can support future clinical investigations inneurophysiology. In
clinical practice, many of the EEG features are described by clinicians
innatural language terms, such as very high, extremely irregular, somewhat
abnormal, etc. The secondstage of the framework, 'qualitative analysis',
captures the subjectivity and linguistic uncertainty expressed by the clinical
experts, using novel, intelligent models, based on fuzzy logic, to provide an
analysisclosely comparable to the clinical interpretation made in practice. The
outcome of this stage is anEEG report with qualitative descriptions to
complement the quantitative analysis.
The system was evaluated using EEG records from 1 patient with Alzheimer's
disease and 2-age-matched normalcontrols for the factual report, and 3 patients
with Alzheimer's disease and 7 age-matched normalcontrols for the 'conclusion'.
Good agreement was found between factual reports produced by thesystem and
factual reports produced by the qualified clinicians. Further, the 'conclusion'
producedby the system achieved 100\% discrimination between the two subject
groups. After a thorough evaluation, the system should significantly aid the
process of EEG interpretation and diagnosis. |
Publications
|
|
Automated Interpretation of the Background EEG using Fuzzy
Logic
Edward Peter Riddington (Ph.D thesis, University of Plymouth)
|
|
Intelligent enhancement and interpretation of EEG signals
Riddington, E.P. Wu, J. Ifeachor, E.C. Allen, E.M. Hudson, N.R.
IEE Colloquium on Artificial Intelligence Methods for Biomedical Data
Processing, April 1996
|
|
Knowledge-based enhancement and interpretation of EEG signals
Riddington, E.P., Ifeachor, E.C., Allen, E.M., Hudson, N.R. and Mapps,
D.J.
Proceedings of the 2nd International Conference on Neural Networks and
Expert Systems in Medicine and Healthcare (NESMED96), University of
Plymouth, Plymouth, UK. pp. 246-255, 1996.
|
|
Investigation Into Different Methods of fuzzy Inference Using ROC
Analysis
E. P. Riddington, E. C. Ifeachor, E. M. Allen, and D. P. Mapps
Proceedings of the 2nd International Conference on Neural Networks and Expert
Systems in Medicine and Healthcare (NNESMED'96), Plymouth, UK pp. 104-111, 1996
|
|
|