Title | ||
---|---|---|
A hybrid approach to MR imaging segmentation using unsupervised clustering and approximate reducts |
Abstract | ||
---|---|---|
We introduce a hybrid approach to magnetic resonance image segmentation using unsupervised clustering and the rules derived from approximate decision reducts. We utilize the MRI phantoms from the Simulated Brain Database. We run experiments on randomly selected slices from a volumetric set of multi-modal MR images (T1, T2, PD). Segmentation accuracy reaches 96% for the highest resolution images and 89% for the noisiest image volume. We also tested the resultant classifier on real clinical data, which yielded an accuracy of approximately 84%. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1007/11548706_39 | RSFDGrC (2) |
Keywords | Field | DocType |
mri phantom,segmentation accuracy,highest resolution image,approximate decision reducts,magnetic resonance image segmentation,hybrid approach,simulated brain database,mr imaging segmentation,real clinical data,multi-modal mr image,noisiest image volume,unsupervised clustering,approximate reducts,self organizing maps,magnetic resonance image,rough set,rough sets | Computer vision,Scale-space segmentation,Pattern recognition,Segmentation,Computer science,Image processing,Self-organizing map,Image segmentation,Unsupervised learning,Artificial intelligence,Cluster analysis,Image resolution | Conference |
Volume | ISSN | ISBN |
3642 | 0302-9743 | 3-540-28660-8 |
Citations | PageRank | References |
6 | 0.55 | 14 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sebastian Widz | 1 | 67 | 6.50 |
Kenneth Revett | 2 | 313 | 27.15 |
Dominik Ślęzak | 3 | 553 | 50.04 |