Multi-atlas based segmentation of brain images: Atlas selection and its effect on accuracy

Visual Information Processing Group, Department of Computing, Imperial College London, 180 Queen's Gate, London, SW7 2AZ, UK.
NeuroImage (Impact Factor: 6.36). 03/2009; 46(3):726-38. DOI: 10.1016/j.neuroimage.2009.02.018
Source: PubMed


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.

Download full-text


Available from: Paul Aljabar,
    • "with a smoothed approximation via Large- Deformation Diffeomorphic Metric Mapping (LDDMM) [23]. Compared with single-atlas methods, approaches that combine maps from multiple atlases that best match any individual subject's scan features have been shown to improve segmentation accuracy and reduce biases [24]. We chose the nonverbal Faces subtest in the Wechsler Memory Scale III (WMS-III) [25] to assess episodic memory. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Alzheimer neuropathology (AD) is found in almost half of patients with non-semantic primary progressive aphasia (PPA). This study examined hippocampal abnormalities in PPA to determine similarities to those described in amnestic AD. In 37 PPA patients and 32 healthy controls, we generated hippocampal subfield surface maps from structural MRIs and administered a face memory test. We analyzed group and hemisphere differences for surface shape measures and their relationship with test scores and ApoE genotype. The hippocampus in PPA showed inward deformity (CA1 and subiculum subfields) and outward deformity (CA2-4+DG subfield) and smaller left than right volumes. Memory performance was related to hippocampal shape abnormalities in PPA patients, but not controls, even in the absence of memory impairments. Hippocampal deformity in PPA is related to memory test scores. This may reflect a combination of intrinsic degenerative phenomena with transsynaptic or Wallerian effects of neocortical neuronal loss.
    03/2015; 1(1):14-23. DOI:10.1016/j.dadm.2014.11.013
  • Source
    • "The propagated segmentations are then merged into a consensus label at each voxel in the target image. Voxelwise label conflicts can be resolved using either simple, unweighted approaches (Rohlfing et al., 2004a; Heckemann et al., 2006; Aljabar et al., 2009) or by weighting individual contributions locally based on the intensity information from the atlas and target images (Artaechevarria et al., 2009; Sabuncu et al., 2010). Alternative fusion strategies based on statistical optimisation have been proposed, with the most popular representative being STAPLE (Warfield et al., 2004) and its modifications (Asman and Landman, 2011, 2013; Landman et al., 2012; Cardoso et al., 2013a). "
    [Show abstract] [Hide abstract]
    ABSTRACT: We propose a framework for the robust and fully-automatic segmentation of magnetic resonance (MR) brain images called "Multi-Atlas Label Propagation with Expectation-Maximisation based refinement" (MALP-EM). The presented approach is based on a robust registration approach (MAPER), highly performant label fusion (joint label fusion) and intensity-based label refinement using EM. We further adapt this framework to be applicable for the segmentation of brain images with gross changes in anatomy. We propose to account for consistent registration errors by relaxing anatomical priors obtained by multi-atlas propagation and a weighting scheme to locally combine anatomical atlas priors and intensity-refined posterior probabilities. The method is evaluated on a benchmark dataset used in a recent MICCAI segmentation challenge. In this context we show that MALP-EM is competitive for the segmentation of MR brain scans of healthy adults when compared to state-of-the-art automatic labelling techniques. To demonstrate the versatility of the proposed approach, we employed MALP-EM to segment 125 MR brain images into 134 regions from subjects who had sustained traumatic brain injury (TBI). We employ a protocol to assess segmentation quality if no manual reference labels are available. Based on this protocol, three independent, blinded raters confirmed on 13 MR brain scans with pathology that MALP-EM is superior to established label fusion techniques. We visually confirm the robustness of our segmentation approach on the full cohort and investigate the potential of derived symmetry-based imaging biomarkers that correlate with and predict clinically relevant variables in TBI such as the Marshall Classification (MC) or Glasgow Outcome Score (GOS). Specifically, we show that we are able to stratify TBI patients with favourable outcomes from non-favourable outcomes with 64.7% accuracy using acute-phase MR images and 66.8% accuracy using follow-up MR images. Furthermore, we are able to differentiate subjects with the presence of a mass lesion or midline shift from those with diffuse brain injury with 76.0% accuracy. The thalamus, putamen, pallidum and hippocampus are particularly affected. Their involvement predicts TBI disease progression.
    Medical Image Analysis 02/2015; 21(1):40-58. DOI:10.1016/ · 3.65 Impact Factor
  • Source
    • "In addition, our healthy young adult atlas may not be the best template to achieve high transformation accuracy. More sophisticated approaches, such as multi-atlases (Aljabar, 2009; Heckemann, 2006; Iosifescu, 1997; Jia et al., 2012; Klein and Hirsch, 2005; Lao, 2004; Liu et al., 2004; Rohlfing et al., 2004; Wang, 2010; Warfield et al., 2004; Wu et al., 2007), may increase the accuracy in the future. For the image-vector conversion, ABA plays an important role in dimensional reduction. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Radiological diagnosis is based on subjective judgment by radiologists. The reasoning behind this process is difficult to document and share, which is a major obstacle in adopting evidence-based medicine in radiology. We report our attempt to use a comprehensive brain parcellation tool to systematically capture image features and use them to record, search, and evaluate anatomical phenotypes. Anatomical images (T1-weighted MRI) were converted to a standardized index by using a high-dimensional image transformation method followed by atlas-based parcellation of the entire brain. We investigated how the indexed anatomical data captured the anatomical features of healthy controls and a population with Primary Progressive Aphasia (PPA). PPA was chosen because patients have apparent atrophy at different degrees and locations, thus the automated quantitative results can be compared with trained clinicians' qualitative evaluations. We explored and tested the power of individual classifications and of performing a search for images with similar anatomical features in a database using partial least squares-discriminant analysis (PLS-DA) and principal component analysis (PCA). The agreement between the automated z-score and the averaged visual scores for atrophy (r = 0.8) was virtually the same as the inter-evaluator agreement. The PCA plot distribution correlated with the anatomical phenotypes and the PLS-DA resulted in a model with an accuracy of 88% for distinguishing PPA variants. The quantitative indices captured the main anatomical features. The indexing of image data has a potential to be an effective, comprehensive, and easily translatable tool for clinical practice, providing new opportunities to mine clinical databases for medical decision support.
    Clinical neuroimaging 01/2015; 46. DOI:10.1016/j.nicl.2015.01.008 · 2.53 Impact Factor
Show more