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
    • "al, [12] performed multiple registrations from all the atlases to the target and fusing the results to generate the target segmentation. Chupin, [13] developed a hybrid segmentation method that uses probabilistic atlas built from 16 young controls and registered using statistic parametric mapping (SPM). Pablo Mesejo, [14] describe the parameters of an empirically-derived deformable model of the hippocampus which maximize its overlap with the corresponding anatomical structure in histological brain images. "
    [Show abstract] [Hide abstract]
    ABSTRACT: The Hippocampus in a human brain is the focus of neuroimaging research for the recent years due to its important role in memory processes and the significance in neurological and psychiatric disorders. Hence the segmentation of hippocampus from MRI is inevitable to identify the diagnosis and the disease progression. But, the extraction of hippocampus is a tedious task since it is smaller in size and has a vague boundary. To facilitate the segmentation, in this paper we propose a method to segment Hc from MRI of human head scans. This segmentation method constitutes two phases. In the first phase, the approximate location of Hc in the input image is identified by atlas based approach. From that location, an enclosed rectangle called region of interest (ROI) is derived. In the second phase the ROI is processed by applying conservative smoothing and top-hat filter to preserve the edges of hippocampus. The filtered image is then binarized using Riddler Calvard method to differentiate the hippocampus from other irrelevant structures. Finally, hippocampus alone is segmented by connected component analysis (CCA).
    Full-text · Article · Jul 2015
  • 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.
    Full-text · Article · Sep 2009 · Epilepsia
  • 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.
    Full-text · Article · Jun 2009 · NeuroImage
Show more