Multiple Atlases-Based Joint Labeling of Human Cortical Sulcal Curves

We present a spectral-based sulcal curve labeling method by considering geometrical information of neighboring curves in a multiple atlases-based framework. Compared to the conventional method, we propose to use neighboring curves for avoiding ambiguity in curve-by-curve labeling and to integrate the labeling results obtained from multiple atlases for consistent labeling. In particular, we compute a histogram of points on the neighboring curves as a new feature descriptor for each point on a sulcal curve under consideration. To better resolve ambiguity in the curve labeling, we also employ the neighboring curves that are parallel to major sulcal curves. Moreover, we further integrate all the results from multiple atlases into a linear system, by solving which our method ultimately gives accurate labels to the major curves in the subjects. Experimental results on evaluation of 12 major sulcal curves of 12 human cortical surfaces indicate that our method achieves higher labeling accuracy 7.87% compared to the conventional method, while reducing 4.41% of false positive labeling errors on average.