Effects of registration regularization and atlas sharpness on segmentation accuracy

Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA.
Medical image analysis (Impact Factor: 3.65). 11/2008; 12(5):603-15. DOI: 10.1016/
Source: PubMed

ABSTRACT In non-rigid registration, the tradeoff between warp regularization and image fidelity is typically determined empirically. In atlas-based segmentation, this leads to a probabilistic atlas of arbitrary sharpness: weak regularization results in well-aligned training images and a sharp atlas; strong regularization yields a "blurry" atlas. In this paper, we employ a generative model for the joint registration and segmentation of images. The atlas construction process arises naturally as estimation of the model parameters. This framework allows the computation of unbiased atlases from manually labeled data at various degrees of "sharpness", as well as the joint registration and segmentation of a novel brain in a consistent manner. We study the effects of the tradeoff of atlas sharpness and warp smoothness in the context of cortical surface parcellation. This is an important question because of the increasingly availability of atlases in public databases, and the development of registration algorithms separate from the atlas construction process. We find that the optimal segmentation (parcellation) corresponds to a unique balance of atlas sharpness and warp regularization, yielding statistically significant improvements over the FreeSurfer parcellation algorithm. Furthermore, we conclude that one can simply use a single atlas computed at an optimal sharpness for the registration-segmentation of a new subject with a pre-determined, fixed, optimal warp constraint. The optimal atlas sharpness and warp smoothness can be determined by probing the segmentation performance on available training data. Our experiments also suggest that segmentation accuracy is tolerant up to a small mismatch between atlas sharpness and warp smoothness.

Download full-text


Available from: Mert R Sabuncu, Jun 19, 2014
17 Reads
  • Source
    • "Spatial normalisation of the training atlases can be achieved with different registration algorithms. Because registration methods are a trade-off between warp regularisation and the fidelity term, probabilistic atlases possess arbitrary sharpness: weak regularisation leads to a sharp atlas, whereas strong regularisation yields a blurry atlas [14]. Given a smoothness parameter that controls the registration, an iterative atlas generation scheme is usually employed [11, 15, 16]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: An atlas-based segmentation approach is presented that combines low-level operations, an affine probabilistic atlas, and a multiatlas-based segmentation. The proposed combination provides highly accurate segmentation due to registrations and atlas selections based on the regions of interest (ROIs) and coarse segmentations. Our approach shares the following common elements between the probabilistic atlas and multiatlas segmentation: (a) the spatial normalisation and (b) the segmentation method, which is based on minimising a discrete energy function using graph cuts. The method is evaluated for the segmentation of the liver in computed tomography (CT) images. Low-level operations define a ROI around the liver from an abdominal CT. We generate a probabilistic atlas using an affine registration based on geometry moments from manually labelled data. Next, a coarse segmentation of the liver is obtained from the probabilistic atlas with low computational effort. Then, a multiatlas segmentation approach improves the accuracy of the segmentation. Both the atlas selections and the nonrigid registrations of the multiatlas approach use a binary mask defined by coarse segmentation. We experimentally demonstrate that this approach performs better than atlas selections and nonrigid registrations in the entire ROI. The segmentation results are comparable to those obtained by human experts and to other recently published results.
    Computational and Mathematical Methods in Medicine 09/2014; 2014:182909. DOI:10.1155/2014/182909 · 0.77 Impact Factor
  • Source
    • "The degree of the smoothness depends on the number of averaged subjects, the anatomical homogeneity of the population, and the image transformation algorithms; thus, the degree of smoothness is difficult to predict. The structural blurring contains important information about residual anatomical variability after normalization, and could be beneficial for the accuracy of the volume-to-volume image registration by providing natural weighting toward well-defined (population-preserved) structures (Yeo et al., 2008). However, the utilization of a smoothed image as a template for highly nonlinear transformation on sharp individual images may require careful examination (Wu et al., 2011). "
    [Show abstract] [Hide abstract]
    ABSTRACT: MRI-based human brain atlases, which serve as a common coordinate system for image analysis, play an increasingly important role in our understanding of brain anatomy, image registration, and segmentation. Study-specific brain atlases are often obtained from one of the subjects in a study or by averaging the images of all participants after linear or non-linear registration. The latter approach has the advantage of providing an unbiased anatomical representation of the study population. But, the image contrast is influenced by both inherent MR contrasts and residual anatomical variability after the registration; in addition, the topology of the brain structures cannot reliably be preserved. In this study, we demonstrated a population-based template-creation approach, which is based on Bayesian template estimation on a diffeomorphic random orbit model. This approach attempts to define a population-representative template without the cross-subject intensity averaging; thus, the topology of the brain structures is preserved. It has been tested for segmented brain structures, such as the hippocampus, but its validity on whole-brain MR images has not been examined. This paper validates and evaluates this atlas generation approach, i.e., Volume-based Template Estimation (VTE). Using datasets from normal subjects and Alzheimer's patients, quantitative measurements of sub-cortical structural volumes, metric distance, displacement vector, and Jacobian were examined to validate the group-averaged shape features of the VTE. In addition to the volume-based quantitative analysis, the preserved brain topology of the VTE allows surface-based analysis within the same atlas framework. This property was demonstrated by analyzing the registration accuracy of the pre- and post-central gyri. The proposed method achieved registration accuracy within 1mm for these population-preserved cortical structures in an elderly population.
    NeuroImage 09/2013; 84. DOI:10.1016/j.neuroimage.2013.09.011 · 6.36 Impact Factor
  • Source
    • "By using the complete image data to recover dense correspondences at pixel-level precision, most intensity-based nonrigid registration approaches are regarded as global model based methods that are often formulated as global energy minimization problems with the energy being composed of an regularization term and a similarity term [12][13]. The relative weight of similarity term and regularization term can cause the well-known trade-off between the registration accuracy and the smoothness of the deformation field [14]. In the presence of outliers, the accurate and plausible local structure matching does not exist using whole-intensity driven transformation model. "
    [Show abstract] [Hide abstract]
    ABSTRACT: For nonrigid image registration, matching the particular structures (or the outliers) that have missing correspondence and/or local large deformations, can be more difficult than matching the common structures with small deformations in the two images. Most existing works depend heavily on the outlier segmentation to remove the outlier effect in the registration. Moreover, these works do not handle simultaneously the missing correspondences and local large deformations. In this paper, we defined the nonrigid image registration as a local adaptive kernel regression which locally reconstruct the moving image's dense deformation vectors from the sparse deformation vectors in the multi-resolution block matching. The kernel function of the kernel regression adapts its shape and orientation to the reference image's structure to gather more deformation vector samples of the same structure for the iterative regression computation, whereby the moving image's local deformations could be compliant with the reference image's local structures. To estimate the local deformations around the outliers, we use joint saliency map that highlights the corresponding saliency structures (called Joint Saliency Structures, JSSs) in the two images to guide the dense deformation reconstruction by emphasizing those JSSs' sparse deformation vectors in the kernel regression. The experimental results demonstrate that by using local JSS adaptive kernel regression, the proposed method achieves almost the best performance in alignment of all challenging image pairs with outlier structures compared with other five state-of-the-art nonrigid registration algorithms.
Show more