Direkt zum Inhalt
Bannergrafik (AG-Freisleben)
Sie sind hier:» Universität » Mathematik und Informatik » Arbeitsgruppen » Verteilte Systeme » Research » Past Projects » Brain Imaging (UKGM)
  • Print this page
  • create PDF file

Volumetric Analysis of Cerebral Pathologies

Keywords: Volumetric Analysis, Glioblastoma Multiforme, Pituitary Adenomas, Cerebral Aneurysms

Manual segmentation of various intracranial processes is an important but time-consuming process that can be overcome by a new semi-automatic segmentation algorithm proposed in this project. This segmentation algorithm has been applied to three intracranial pathologies: glioblastoma multiforme (GBM), pituitary macro-adenomas and cerebral aneurysms. Although different in biology, corresponding disease and therapy, they all have a need for a rigidly registered volume follow-up. They have in common a relatively well circumscribable outline and round morphology, especially pituitary adenomas and the aneurysms.

In this research project, a medical software system for volumetric analysis of different cerebral pathologies in magnetic resonance imaging (MRI) data has been developed. The software system is based on a semi-automatic segmentation algorithm and helps to overcome the time-consuming process of volume determination during monitoring of a patient. After imaging, the parameter settings – including a seed point – are set up in the system and an automatic segmentation is performed by a novel graph-based approach. Manually reviewing the result leads to reseeding, adding seed points or an automatic surface mesh generation. The mesh is saved for monitoring the patient and for comparisons with follow-up scans. Based on the mesh, the system performs a voxelization and volume calculation, which leads to diagnosis and therefore further treatment decisions. The overall system has been tested with different cerebral pathologies – glioblastoma multiforme, pituitary adenomas and cerebral aneurysms – and evaluated against manual expert segmentations using the Dice Similarity Coefficient (DSC). Additionally, intra-physician segmentations have been performed to provide a quality measure for the presented system.


GBM  pituitary adenoma

cerebral aneurysm 



Contact: Dr. Jan Egger, Prof. Dr. Christopher Nimsky

Selected Publications:

  • J. Egger, R. R. Colen, B. Freisleben, Ch. Nimsky, A Manual Refinement System for Graph-Based Segmentation Results in the Medical Domain, Journal of Medical Systems, Springer Press, Aug. 2011.
  • J. Egger, C. Kappus, B. Freisleben, Ch. Nimsky, A Medical Software System for Volumetric Analysis of Cerebral Pathologies in Magnetic Resonance Imaging (MRI) Data, Journal of Medical Systems, Springer Press, Mar. 2011.
  • J. Egger, M. H. A. Bauer, D. Kuhnt, B. Carl, C. Kappus, B. Freisleben, Ch. Nimsky, Nugget-Cut: A Segmentation Scheme for Spherically- and Elliptically-Shaped 3D Objects, 32nd Annual Symposium of the German Association for Pattern Recognition (DAGM), LNCS 6376, pp. 383–392, Springer Press, Darmstadt, Germany, Sep. 2010.


Zuletzt aktualisiert: 16.08.2011 · schmid2v

Fb. 12 - Mathematik und Informatik

Verteilte Systeme (AG Freisleben), Hans-Meerwein-Straße 6, D-35032 Marburg
Tel. +49 6421/28-21567, Fax +49 6421/28-21573, E-Mail: freisleb@informatik.uni-marburg.de

URL dieser Seite: https://www.uni-marburg.de/fb12/arbeitsgruppen/verteilte_systeme/forschung/pastproj/mri

Impressum | Datenschutz