Skip to main page content
Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2009 Jun;19(6):549-57.
doi: 10.1002/hipo.20615.

Automated Segmentation of Hippocampal Subfields From Ultra-High Resolution in Vivo MRI

Affiliations
Free PMC article

Automated Segmentation of Hippocampal Subfields From Ultra-High Resolution in Vivo MRI

Koen Van Leemput et al. Hippocampus. .
Free PMC article

Abstract

Recent developments in MRI data acquisition technology are starting to yield images that show anatomical features of the hippocampal formation at an unprecedented level of detail, providing the basis for hippocampal subfield measurement. However, a fundamental bottleneck in MRI studies of the hippocampus at the subfield level is that they currently depend on manual segmentation, a laborious process that severely limits the amount of data that can be analyzed. In this article, we present a computational method for segmenting the hippocampal subfields in ultra-high resolution MRI data in a fully automated fashion. Using Bayesian inference, we use a statistical model of image formation around the hippocampal area to obtain automated segmentations. We validate the proposed technique by comparing its segmentations to corresponding manual delineations in ultra-high resolution MRI scans of 10 individuals, and show that automated volume measurements of the larger subfields correlate well with manual volume estimates. Unlike manual segmentations, our automated technique is fully reproducible, and fast enough to enable routine analysis of the hippocampal subfields in large imaging studies.

Figures

FIGURE 1
FIGURE 1
From left to right: cross-sectional slices of an ultra-high resolution MRI scan, manual delineation of the hippocampal subfields and corresponding automated segmentation.
FIGURE 2
FIGURE 2
Mesh-based probabilistic atlas derived from manual delineations in nine subjects, warped onto the 10th subject which is shown in Figure 1. The structure-wise probabilities have been color-coded for visualization purposes; only 7 structures of interest are shown.
FIGURE 3
FIGURE 3
Dice overlap measures (top left), average boundary distances (bottom left), and relative volume differences (top right) between automated and manual segmentations in 10 subjects. Also shown (bottom right) are the human intrarater Dice overlap measures (empty bars) along with automated vs. manual Dice overlaps (filled bars), calculated on two slices in the midbody of the hippocampus in five subjects. The colors are as in Figure 1. Error bars represent standard errors on the mean.

Similar articles

See all similar articles

Cited by 155 articles

See all "Cited by" articles

Publication types

Feedback