Fully automatic segmentation of the hippocampus and the amygdala from MRI using hybrid prior knowledge.

Department of Clinical and Experimental Epilepsy, IoN, UCL, London, UK.
Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention 02/2007; 10(Pt 1):875-82. DOI: 10.1007/978-3-540-75757-3_106
Source: PubMed


The segmentation of macroscopically ill-defined and highly variable structures, such as the hippocampus Hc and the amygdala Am, from MRI requires specific constraints. Here, we describe and evaluate a hybrid segmentation method that uses knowledge derived from a probabilistic atlas and from anatomical landmarks based on stable anatomical characteristics of the structures. Combined in a previously published semi-automatic segmentation method, they lead to a fast, robust and accurate fully automatic segmentation of Hc and Am. The probabilistic atlas was built from 16 young controls and registered with the "unified segmentation" of SPM5. The algorithm was quantitatively evaluated with respect to manual segmentation on two MRI datasets: the 16 young controls, with a leave-one-out strategy, and a mixed cohort of 8 controls and 15 subjects with epilepsy with variable hippocampal sclerosis. The segmentation driven by hybrid knowledge leads to greatly improved results compared to that obtained by registration of the thresholded atlas alone: mean overlap for Hc on the 16 young controls increased from 78% to 87% (p < 0.001) and on the mixed cohort from 73% to 82% (p < 0.001) while the error on volumes decreased from 10% to 7% (p < 0.005) and from 18% to 8% (p < 0.001), respectively. Automatic results were better than the semi-automatic results: for the 16 young controls, average overlap increased from 84% to 87% (p < 0.001) for Hc and from 81% to 84% (p < 0.002) for Am, with equivalent improvements in volume error.

Download full-text


Available from: Louis Lemieux, Jan 15, 2014
  • Source
    • "A number of automated and semiautomated computational techniques have been used to detect hippocampal volume changes in mTLE (Hogan et al., 2000, 2004; Keller et al., 2002; Bonilha et al., 2004; Chupin et al., 2007; Hammers et al., 2007; McDonald et al., 2008; Pell et al., 2008; Bonilha et al., 2009); however, few of these studies explicitly compared automated volume estimates with the corresponding manual estimate in the same subject (Chupin et al., 2007; Hammers et al., 2007). In the studies in which a direct comparison of manual and automated techniques was made (Chupin et al., 2007; Hammers et al., 2007), an automated segmentation technique was used that was different from the two publicly available methods presented in this article. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Quantitative measurement of hippocampal volume using structural magnetic resonance imaging (MRI) is a valuable tool for detection and lateralization of mesial temporal lobe epilepsy with hippocampal sclerosis (mTLE). We compare two automated hippocampal volume methodologies and manual hippocampal volumetry to determine which technique is most sensitive for the detection of hippocampal atrophy in mTLE. We acquired a three-dimensional (3D) volumetric sequence in 10 patients with left-lateralized mTLE and 10 age-matched controls. Hippocampal volumes were measured manually, and using the software packages Freesurfer and FSL-FIRST. The sensitivities of the techniques were compared by determining the effect size for average volume reduction in patients with mTLE compared to controls. The volumes and spatial overlap of the automated and manual segmentations were also compared. Significant volume reduction in affected hippocampi in mTLE compared to controls was detected by manual hippocampal volume measurement (p < 0.01, effect size 33.2%), Freesurfer (p < 0.01, effect size 20.8%), and FSL-FIRST (p < 0.01, effect size 13.6%) after correction for brain volume. Freesurfer correlated reasonably (r = 0.74, p < 0.01) with this manual segmentation and FSL-FIRST relatively poorly (r = 0.47, p < 0.01). The spatial overlap between manual and automated segmentation was reduced in affected hippocampi, suggesting the accuracy of automated segmentation is reduced in pathologic brains. Expert manual hippocampal volumetry is more sensitive than both automated methods for the detection of hippocampal atrophy associated with mTLE. In our study Freesurfer was the most sensitive to hippocampal atrophy in mTLE and could be used if expert manual segmentation is not available.
    Epilepsia 09/2009; 50(12):2586-92. DOI:10.1111/j.1528-1167.2009.02243.x · 4.57 Impact Factor
  • Source
    • "While manual delineation of the hippocampus is still considered to be the gold standard, semi-automated and automated methods for delineation have been developed. In semi-automated methods, prior knowledge is introduced by a human operator who identifies landmarks, seedpoints, or bounding boxes (Chupin et al., 2007; Ghanei et al., 1998; Perez de Alejo et al., 2003; Shen et al., 2002). Fully automated methods might be based on statistical shape-models, on affine or non-linear registration to an atlas (Barnes et al., 2007; Carmichael et al., 2005; Svarer et al., 2005; Vemuri et al., 2003) or to multiple atlases (Heckemann et al., 2006). "
    [Show abstract] [Hide abstract]
    ABSTRACT: Due to its crucial role for memory processes and its relevance in neurological and psychiatric disorders, the hippocampus has been the focus of neuroimaging research for several decades. In vivo measurement of human hippocampal volume and shape with magnetic resonance imaging has become an important element of neuroimaging research. Nevertheless, volumetric findings are still inconsistent and controversial for many psychiatric conditions including affective disorders. Here we review the wealth of anatomical protocols for the delineation of the hippocampus in MR images, taking into consideration 71 different published protocols from the neuroimaging literature, with an emphasis on studies of affective disorders. We identified large variations between protocols in five major areas. 1) The inclusion/exclusion of hippocampal white matter (alveus and fimbria), 2) the definition of the anterior hippocampal-amygdala border, 3) the definition of the posterior border and the extent to which the hippocampal tail is included, 4) the definition of the inferior medial border of the hippocampus, and 5) the use of varying arbitrary lines. These are major sources of variance between different protocols. In contrast, the definitions of the lateral, superior, and inferior borders are less disputed. Directing resources to replication studies that incorporate characteristics of the segmentation protocols presented herein may help resolve seemingly contradictory volumetric results between prior neuroimaging studies and facilitate the appropriate selection of protocols for manual or automated delineation of the hippocampus for future research purposes.
    NeuroImage 06/2009; 47(4):1185-95. DOI:10.1016/j.neuroimage.2009.05.019 · 6.36 Impact Factor
  • Source
    • "The results show that the accuracy achieved by similarity selection is significantly higher than that achieved by the fusion of random sets of atlases. The results obtained from a large number of leave-one-out cross-validation experiments (Table 1) compare very well with the state-of-the-art (see for example Fischl et al. (2002), Klein and Hirsch (2005) or Chupin et al. (2007)) and are comparable with some previous manual segmentation Fig. 13. Exemplar Subject 1 (age 12, left) and the top 10 atlases selected using image similarity (see also Table 3). "
    [Show abstract] [Hide abstract]
    ABSTRACT: Quantitative research in neuroimaging often relies on anatomical segmentation of human brain MR images. Recent multi-atlas based approaches provide highly accurate structural segmentations of the brain by propagating manual delineations from multiple atlases in a database to a query subject and combining them. The atlas databases which can be used for these purposes are growing steadily. We present a framework to address the consequent problems of scale in multi-atlas segmentation. We show that selecting a custom subset of atlases for each query subject provides more accurate subcortical segmentations than those given by non-selective combination of random atlas subsets. Using a database of 275 atlases, we tested an image-based similarity criterion as well as a demographic criterion (age) in a leave-one-out cross-validation study. Using a custom ranking of the database for each subject, we combined a varying number n of atlases from the top of the ranked list. The resulting segmentations were compared with manual reference segmentations using Dice overlap. Image-based selection provided better segmentations than random subsets (mean Dice overlap 0.854 vs. 0.811 for the estimated optimal subset size, n=20). Age-based selection resulted in a similar marked improvement. We conclude that selecting atlases from large databases for atlas-based brain image segmentation improves the accuracy of the segmentations achieved. We show that image similarity is a suitable selection criterion and give results based on selecting atlases by age that demonstrate the value of meta-information for selection.
    NeuroImage 03/2009; 46(3):726-38. DOI:10.1016/j.neuroimage.2009.02.018 · 6.36 Impact Factor
Show more