Skip to main content

Table 2 Automatic CaudateCut Segmentation Algorithm

From: A fully-automatic caudate nucleus segmentation of brain MRI: Application in volumetric analysis of pediatric attention-deficit/hyperactivity disorder

1.

Initial segmentation using AB method.

2.

Set background and caudate seeds by erosion and dilatation of AB mask.

3.

Initialize unsupervised unary potentials UU p ("cau") and UU p ("back") based on local graylevel intensities.

4.

Initialize supervised unary potentials SU p ("cau") and SU p ("back") based on SVM correlogram classifier.

5.

Initialize unary term based on combined unary potentials.

6.

Initialize boundary term B(L) based on first and second derivatives of intensities and multi-scale edge map.

7.

Estimate caudate segmentation using GC.