Documentation/4.4/Modules/ABC

From Slicer Wiki
Jump to: navigation, search
Home < Documentation < 4.4 < Modules < ABC

For the latest Slicer documentation, visit the 4.10 page.


Introduction and Acknowledgements

Author: Marcel Prastawa
Contact: Marcel Prastawa, <email>marcel.prastawa@gmail.com</email>
Website: http://www.nitrc.org/projects/abc

Acknowledgments: This project was supported by NIH grant U54 EB005149.



Module Description

ABC (Atlas Based Classification) is a full segmentation pipeline designed and developed for healthy human brain MRIs, and can be adapted to other applications that involve multi-channel MR images and a pre-defined atlas. The processing pipeline includes image registration, filtering, inhomogeneity correction, and skull stripping.


Tutorials

The software is designed and tested for healthy brain MRI (pediatric - adult). Initiating the pipeline requires the specification of an atlas (which contains a template image and prior probability images) and at least one image modality for a subject. The module can accommodate up to five modalities, which need not be registered or skull-stripped beforehand. All images are assumed to have the correct metadata for spatial orientation, voxel spacing, and image origin.

Example Parameters. Typical execution using default parameters.
Basic Extension Panels. Panels with the minimal number of parameters that need to be specified for executing the software.

The input images are specified in the first panel. The choice of the first image in the list is crucial, as the outputs are generated in the space of the first image. All other image channels and the atlas are registered to the first image during processing.

The atlas can be specified through the second panel. The module assumes that it is stored in a directory where the template image (e.g., a T1 image) is specified as template.mha and that the prior images are stored in sequence (1.mha, 2.mha, ...). An example atlas is available through NITRC for adult brains: Adult Brain Atlas, which needs to be uncompressed and stored in a local path before running the module.

The output images are specified in the third panel. Users can create and specify the target volumes for the segmentation labels as well as the bias corrected images for each modality. The bias corrected output images do not need to be specified if they are of no interest.

Once all input parameters have been specified, execution can be initiated by clicking the Apply button.

Example Output. Brain MRI segmented using ABC

The processing involved in the module can take up to five minutes for a typical MR image, using the default setting that was chosen to generate coarser results. Speed-ups are possible by increasing the number of threads (specified in the Speed panel). Results with higher accuracy can be obtained by increasing the maximum polynomial degree of the bias field (in the Advanced panel), increasing the number of pre-filtering iterations (in the Advanced panel), and switching to finer sampling for image registration (in the Speed panel).

Panels and their use

Parameters:

  • Input images: Multimodal input images for a subject
    • Input image 1 (inputImage1): Input image modality 1, outputs are generated in this space
    • Input image 2 (inputImage2): Input image modality 2
    • Input image 3 (inputImage3): Input image modality 3
    • Input image 4 (inputImage4): Input image modality 4
    • Input image 5 (inputImage5): Input image modality 5
  • Atlas: Atlas data and parameters
    • Atlas MRB (atlasMRB): MRML bundle that contains an atlas composed of a template image and prior probability images (template.mha, 1.mha, 2.mha, ... , n.mha)
    • Prior weight adjustments (priorAdjustVec): Global scaling factors for adjusting prior weights (list of comma separated numbers with the same count as number of prior images).
  • Output images: Volumes for storing output images
    • Output label image (labelImage): Output label image
    • Bias corrected output image 1 (outputImage1): Bias corrected output image 1
    • Bias corrected output image 2 (outputImage2): Bias corrected output image 2
    • Bias corrected output image 3 (outputImage3): Bias corrected output image 3
    • Bias corrected output image 4 (outputImage4): Bias corrected output image 4
    • Bias corrected output image 5 (outputImage5): Bias corrected output image 5
  • Speed: Options for parallel execution and efficiency
    • Number of threads: (NumberOfThreads): Number of threads used for ITK filter modules
    • Registration Mode: (RegistrationMode): Registration mode, for selecting faster or more accurate estimation.
  • Advanced Parameters: Advanced parameters
    • PreFiltering method: (FilterMethod): Method for initial non-linear image denoising
    • PreFiltering iterations: (FilterIterations): Number of iterations for initial image filtering (0 = off)
    • PreFiltering time steps: (FilterTimeSteps): Time steps for initial image filtering for each modality
    • Bias Field Polynomial Degree: (biasDegree): Maximum polynomial degree for the bias field, typically range from 4 to 6 (0 = off).
    • Initial distribution estimator: (InitialDistributionEstimator): Type of initial distribution estimator, can be standard using sample mean and covariance or robust using the fast MCD estimator.
    • Atlas Transform Type: (atlasMapType): Type of linear transform for atlas mapping (rigid, affine, identity). Use identity when the first image is already in atlas space.
    • Coregistration Transform Type: (coregMapType): Type of transform for mapping between modalities (rigid, affine, identity). Use identity when all images are pre-registered to the space of the first image.
    • Atlas Warping Fluid Iterations: (atlasFluidIters): Number of iterations for computing fluid warps that map atlas to subject (0 = off).
    • Atlas Warping Fluid Maximum Step: (atlasFluidMaxStep): Maximum step size for fluid warp estimation via gradient descent


List of parameters generated transforming this XML file using this XSL file. To update the URL of the XML file, edit this page.


Similar Modules

EMSegmenter


References

  • Automated model-based tissue classification of MR images of the brain. K Van Leemput, F Maes, D Vandermeulen, P Suetens. Medical Imaging, IEEE Transactions on 18 (10), 897-908.
  • Automated model-based bias field correction of MR images of the brain. K Van Leemput, F Maes, D Vandermeulen, P Suetens. Medical Imaging, IEEE Transactions on 18 (10), 885-896.

Information for Developers


Source code can be found at http://www.nitrc.org/plugins/scmsvn/viewcvs.php/?root=abc