Abstract
Automated segmentation of different tissues on medical images is a crucial concept for medical image analysis. In this study, unsupervised image segmentation problem is generalized as a Mumford-Shah energy minimization problem, and several solution proposals for the problem are investigated. Ambrosio-Tortorelli approximation method is implemented, and the performance of the algorithm on magnetic resonance (MR) images of brain is evaluated. First image used in the experiments is chosen among the ones which contain an edema formation due to a brain tumor, and the second one belongs to a healthy subject on which gray matter/white matter segmentation is aimed. Acquired results are presented in visual, tabular and numerical forms. Results and performance are discussed and quantitatively evaluated.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
Keywords
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Cevik, A., Eyuboglu, B.M. (2014). Mumford-Shah Based Unsupervised Segmentation of Brain Tissue on MR Images. In: Roa Romero, L. (eds) XIII Mediterranean Conference on Medical and Biological Engineering and Computing 2013. IFMBE Proceedings, vol 41. Springer, Cham. https://doi.org/10.1007/978-3-319-00846-2_66
Download citation
DOI: https://doi.org/10.1007/978-3-319-00846-2_66
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-00845-5
Online ISBN: 978-3-319-00846-2
eBook Packages: EngineeringEngineering (R0)