Title :
Automatic subcortical tissue segmentation of MR images using optimum-path forest clustering
Author :
Cappabianco, Fábio ; Ide, Jaime S. ; Falcão, Alexandre ; Li, Chiang-shan R.
Author_Institution :
Dept. Cienc. e Tecnol., Univ. Fed. de Sao Paulo, Sao Jose dos Campos, Brazil
Abstract :
Automatic MR-image segmentation of brain tissues is an important issue in neuroimaging. For instance, it is a key methodological component of a popular technique denominated voxel-based morphometry (VBM), which quantifies gray-matter (GM) volumes from MR images. However, segmentation accuracy in some subcortical regions on the basis of extant methods is not satisfactory, compromising VBM results. We combine a probabilistic atlas and a fast clustering approach based on optimum connectivity between voxels in their feature space. The algorithm exploits local image properties and global information from the atlas as features to group GM and white-matter (WM) voxels in distinct clusters, and uses the total probability values inside the clusters to label them as GM or WM. This new method is validated in the region of the thalamus and outperformed two widely used methods packaged in SPM and FSL.
Keywords :
biological tissues; biomedical MRI; feature extraction; image segmentation; medical image processing; pattern clustering; probability; FSL; SPM; automatic MR-image segmentation; automatic subcortical tissue segmentation; brain tissue; gray-matter volume; neuroimaging; optimum connectivity; optimum-path forest clustering; probabilistic atlas; subcortical region; voxel-based morphometry; white-matter voxel; Brain; Clustering algorithms; Conferences; Educational institutions; Image segmentation; Probabilistic logic; Prototypes; atlas-based segmentation; clustering; graph-search algorithms for image processing; medical image analysis; mri;
Conference_Titel :
Image Processing (ICIP), 2011 18th IEEE International Conference on
Conference_Location :
Brussels
Print_ISBN :
978-1-4577-1304-0
Electronic_ISBN :
1522-4880
DOI :
10.1109/ICIP.2011.6116212