Authors:
A. Zifan
;
P. Liatsis
;
P. Kantartzis
and
R. Vargas-Canas
Affiliation:
City University, United Kingdom
Keyword(s):
Electrical impedance tomography, Mesh, Probabilistic modeling and segmentation.
Related
Ontology
Subjects/Areas/Topics:
Applications and Services
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Computer Vision, Visualization and Computer Graphics
;
Medical Image Detection, Acquisition, Analysis and Processing
Abstract:
In this paper, we propose a novel method for the automatic segmentation of Electrical Impedance Tomography (EIT) lung images. EIT is a non-invasive technique, which produces low-spatial and high-temporal resolution images of the internal resistivity of the region of the body probed by currents. EIT is the only technology that reliably quantifies regional lung volumes non-invasively. The problem is non-linear and ill-conditioned and can be solved using 2D or 3D finite element methods (FEMs) subject to using appropriate regularisation strategies. The usual method of segmenting EIT lung images is to manually select a region of interest and derive statistical measures. This procedure is not suitable for FEM-based models as it works on rectangular pixels, as well as making the task tedious and time consuming. We propose an alternative segmentation framework, which operates directly on the resulting FEM meshes, prior to rasterisation in order to prevent the propagation of errors in the rec
onstructed resistivity regions, due to mapping onto a rectangular grid. We use a spatio-temporal probabilistic method to segment conductivity changes in the EIT thorax images. Application of the proposed method offers a much needed alternative to interactive segmentation currently favoured by EIT researchers and clinicians.
(More)