DocumentCode :
3108371
Title :
Automatic White Matter Fiber Clustering Using Dominant Sets
Author :
Dodero, Luca ; Vascon, S. ; Giancardo, L. ; Gozzi, A. ; Sona, Diego ; Murino, Vittorio
Author_Institution :
Pattern Anal. & Comput. Vision, Ist. Italiano di Tecnol. Genoa, Genoa, Italy
fYear :
2013
fDate :
22-24 June 2013
Firstpage :
216
Lastpage :
219
Abstract :
We present an unsupervised approach based on the Dominant Sets framework to automatically segment the white matter fibers into bundles. This framework, rooted in the Game Theory, allows for the automatic determination of the number of clusters from the data itself, without any prior assumption. The clustered bundles are a key information for the generation of unbiased structural connectivity atlases. We have thoroughly validated our algorithm both quantitatively and qualitatively. Indeed, we used biologically plausible synthetic datasets to numerically validate the performance in terms of Precision, Recall and other measures employed in the literature. We also evaluated the algorithm on a real Diffusion Tensor Imaging tractography of a whole mouse brain obtaining promising results. In fact, some of the most prominent brain structures determined by the algorithm correspond to white matter expected anatomy.
Keywords :
biodiffusion; biomedical MRI; brain; fibres; game theory; medical computing; neurophysiology; numerical analysis; pattern clustering; set theory; anatomy; automatic cluster number determination; automatic white matter fiber clustering; automatic white matter fiber segmentation; biologically plausible synthetic datasets; clustered bundles; dominant set framework; game theory; mouse brain structures; numerical analysis; precision factor; qualitative analysis; quantitative analysis; real-diffusion tensor imaging tractography; recall factor; unbiased structural connectivity atlases; unsupervised approach; Clustering algorithms; Diffusion tensor imaging; Image segmentation; Indexes; Mice; Clustering; DTI; Diffusion Magnetic Resonance Imaging; Dominant Sets; Fibers; Segmentation; Tractography; White Matter;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Pattern Recognition in Neuroimaging (PRNI), 2013 International Workshop on
Conference_Location :
Philadelphia, PA
Type :
conf
DOI :
10.1109/PRNI.2013.62
Filename :
6603594
Link To Document :
بازگشت