- Poster presentation
- Open Access
Detection of pathological areas and estimation of viability parameters in late-enhancement cardiac MRI
© Elagouni et al; licensee BioMed Central Ltd. 2010
- Published: 21 January 2010
- Standard Deviation
- Membership Degree
- Abnormal Tissue
- Volumetric Fraction
- Region Competition
Viability assessment is essential for therapy planning following a myocardial infarction. In particular, the proportion of viable myocardium is a major factor in determining whether a patient may benefit from revascularization . By means of late-enhancement cardiac MR imaging (LECMR), it is now possible to visualize normal and non-viable areas with high spatial resolution.
We propose a novel fully automatic method to detect and quantify pathological areas in late-enhancement cardiac MR images.
The first step consists to analyse myocardium intensity with a specifically tailored Expectation-Maximization algorithm . Estimated distributions of both normal and abnormal tissues are then exploited to generate a fuzzy map indicating, for every pixel, the membership degree to the abnormal tissue class. As false positives remain, we design a fast version of the region competition  algorithm to rapidly obtain well-defined regions corresponding to pathological areas and the membership values of all their pixels. To quantify these areas, we calculate the percentage of abnormal tissue and use normalized representations independent of myocardium shape and size to automatically compute the thickness of pathological regions.
We presented a fast and robust method for detecting and quantifying abnormal regions in short-axis LECMR images.
This article is published under license to BioMed Central Ltd.