The Impact of Atlas Formation Methods on Atlas-Guided Brain Segmentation

L. Zollei, M. E. Shenton, W. Wells, K. Pohl
miccai
Volume 4791, Pages 39-46
October, 2007

Download full paper

Abstract

We analyze the impact of atlas construction within the context of an atlas-guided segmenter applied to a morphometry study in neuroanatomy. Automatic segmenters often rely on anatomical information encoded via probabilistic atlases. These atlases are frequently constructed by registering collections of training data. In this paper, we study the impact of registration methods as well as the training data on automatic segmentation results. With respect to registration, we focus our comparison on pairwise vs. group-wise methods and fixed vs. online coordinate systems. For the training data, we consider collections of population specific and general population data. To study the impact of these factors, we revisit a previously published statistical group comparison that was based on manual segmentations. For each atlas type, we record the group differences based on automatic segmentations and compare these findings to the original ones. Furthermore, we measure the Dice overlap between manual and automatic segmentations. Our results indicate some advantages for coordinate systems that are developed in an online fashion.


Reference

Zollei L, Shenton ME, Wells W, Pohl K. The impact of atlas formation methods on atlas-guided brain segmentation. In miccai, volume 4791 of Lecture Notes in Computer Science. Heidelberg, Germany: Springer, 2007;39-46.

Research area

segmentation
© 2013 Psychiatry Neuroimaging Laboratory | Last updated 04.15.2013