Picture of person typing on laptop with programming code visible on the laptop screen

World class computing and information science research at Strathclyde...

The Strathprints institutional repository is a digital archive of University of Strathclyde's Open Access research outputs. Strathprints provides access to thousands of Open Access research papers by University of Strathclyde researchers, including by researchers from the Department of Computer & Information Sciences involved in mathematically structured programming, similarity and metric search, computer security, software systems, combinatronics and digital health.

The Department also includes the iSchool Research Group, which performs leading research into socio-technical phenomena and topics such as information retrieval and information seeking behaviour.

Explore

Variational level set method with shape constraint and application to edema cardiac magnetic resonance image

Kadir, K. and Gao, Hao and Payne, A. and Soraghan, J. and Berry, C. (2011) Variational level set method with shape constraint and application to edema cardiac magnetic resonance image. In: Proceedings of the 17th International Conference on Digital Signal Processing (DSP), 2011. IEEE. ISBN 978-1-4577-0273-0

Full text not available in this repository. Request a copy from the Strathclyde author

Abstract

Quantification of oedema area after acute myocardial infarction (MI) is very important in clinical prognosis for differentiating the viable and death myocardial tissues. In order to quantify oedema region, the first step is to segment the myocardial wall accurately. This paper applies variational level set method with shape constraint to oedema cardiac magnetic resonance (CMR) images. Shape information of the myocardial wall is introduced into the variational level set formulation, and the performance of the automatic method is tested on T2 weighted CMR images from 8 patients, and compared with manual analysis from two clinical experts. Results show that the proposed automatic segmentation framework can segment left ventricle (LV) boundary with no significant difference compared to manual segmentation.