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: 6.25). 03/2009; 46(3):726-38. DOI: 10.1016/j.neuroimage.2009.02.018
Source: PubMed

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.

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Echocardiography is one of the primary imaging modalities used in the diagnosis of cardiovascular diseases. It is commonly used to extract cardiac functional indices including the left ventricular (LV) volume, mass, and motion. The relevant echocardiography analysis meth-ods, including motion tracking, anatomical segmentation, and registra-tion, conventionally use the intensity values and/or phase images, which are highly sensitive to noise and do not encode contextual information and tissue properties directly. To achieve more accurate assessment, we propose a novel spectral representation for echo images to capture struc-tural information from tissue boundaries. It is computationally very effi-cient as it relies on manifold learning of image patches, which is approx-imated using sparse representations of dictionary atoms. The advantage of the proposed representation over intensity and phase images is demon-strated in a multi-atlas LV segmentation framework, where the proposed spectral representation is directly used in deformable registration. The results suggest that the proposed spectral representation can provide more accurate registration between images. This in turn provides a more accurate LV segmentation. Finally, it is the first time that a multi-atlas approach achieves state-of-the-art results in echo image segmentation.
    MICCAI 2014 Workshop -- Sparsity Techniques in Medical Imaging (STMI), Boston, USA; 09/2014
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Extraction of surface models of a hip joint from CT data is a pre-requisite step for computer assisted diagnosis and planning (CADP) of periacetabular osteotomy (PAO). Most of existing CADP systems are based on manual segmentation, which is time-consuming and hard to achieve reproducible results. In this paper, we present a Fully Automatic CT Segmentation (FACTS) approach to simultaneously extract both pelvic and femoral models. Our approach works by combining fast random forest (RF) regression based landmark detection, multi-atlas based segmentation, with articulated statistical shape model (aSSM) based fitting. The two fundamental contributions of our approach are: (1) an improved fast Gaussian transform (IFGT) is used within the RF regression framework for a fast and accurate landmark detection, which then allows for a fully automatic initialization of the multi-atlas based segmentation; and (2) aSSM based fitting is used to preserve hip joint structure and to avoid penetration between the pelvic and femoral models. Taking manual segmentation as the ground truth, we evaluated the present approach on 30 hip CT images (60 hips) with a 6-fold cross validation. When the present approach was compared to manual segmentation, a mean segmentation accuracy of 0.40, 0.36, and 0.36 mm was found for the pelvis, the left proximal femur, and the right proximal femur, respectively. When the models derived from both segmentations were used to compute the PAO diagnosis parameters, a difference of 2.0 ± 1.5°, 2.1 ± 1.6°, and 3.5 ± 2.3% were found for anteversion, inclination, and acetabular coverage, respectively. The achieved accuracy is regarded as clinically accurate enough for our target applications.
    Annals of biomedical engineering. 11/2014;
  • Source
    CLIP, 134-142(2013); 09/2013

Full-text (2 Sources)

Available from
Jun 3, 2014