Authors:
Suzani Mohamad Samuri
1
;
George Panoutsos
1
;
Mahdi Mahfouf
1
;
G. H. Mills
2
;
M. Denaï
3
and
B. H. Brown
4
Affiliations:
1
University of Sheffield, United Kingdom
;
2
Northern General Hospital, United Kingdom
;
3
School of Science and Eng. and Teesside University, United Kingdom
;
4
Royal Hallamshire Hospital, United Kingdom
Keyword(s):
Electrical Impedance Tomography (EIT), ANFIS, Data-driven modelling, Lung imaging, Non-invasive monitoring.
Related
Ontology
Subjects/Areas/Topics:
Applications and Services
;
Artificial Intelligence
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Computational Intelligence
;
Computer Vision, Visualization and Computer Graphics
;
Fuzzy Systems and Signals
;
Health Engineering and Technology Applications
;
Human-Computer Interaction
;
Medical Image Detection, Acquisition, Analysis and Processing
;
Methodologies and Methods
;
Neural Networks
;
Neurocomputing
;
Neurotechnology, Electronics and Informatics
;
Pattern Recognition
;
Physiological Computing Systems
;
Sensor Networks
;
Signal Processing
;
Soft Computing
;
Theory and Methods
Abstract:
Electrical Impedance Tomography (EIT) has been the subject of intensive research since its development in the early 1980s by Barber and Brown at the Department of Medical Physics and Clinical Engineering, Hallamshire Hospital in Sheffield (UK). In particular, pulmonary measurement has been the focus of most EIT related research. One of the relatively recent advances in EIT is the development of an absolute EIT system (aEIT) which can estimate absolute values of lung resistivity and lung volumes. However, there is still active research in the area of validating and improving the accuracy and consistency of the aEIT estimation of lung volumes towards characterising the system as suitable for clinical use. In this paper we present a new approach based on Computational Intelligence (CI) modelling to model the ‘Resistivity - Lung Volume’ relationship that will allow more accurate lung volume predictions. Eight (8) healthy volunteers were measured simultaneously by the Sheffield aEIT syste
m and a Spirometer and the recorded results were used to develop subject-specific Neural-Fuzzy models able to predict absolute values of lung volume based only on absolute lung resistivity data. The developed models show improved accuracy in the prediction of lung volumes, as compared with the original Sheffield aEIT system. However the inter-individual differences observed in the subject-specific modelling behaviour of the ‘Resistivity-Lung Volume’ curves suggest that a model extension is needed, whereby the modelling structure auto-calibrates to account for subject (or patient-specific) inter-parameter variability.
(More)