Documentation/4.8/Modules/AFTSegmenter

For the latest Slicer documentation, visit the read-the-docs.

Introduction and Acknowledgements

Extension: LesionSpotlight Webpage: http://dcm.ffclrp.usp.br/csim/ Author: Antonio Carlos da S. Senra Filho, CSIM Laboratory (University of Sao Paulo, Department of Computing and Mathematics) Contact: Antonio Carlos da S. Senra Filho, <email>acsenrafilho@usp.br</email>

CSIM Laboratory   University of Sao Paulo   CAPES Brazil

Module Description

This module offers an implementation of a recent Multiple Sclerosis lesion segmentation approach based on a unsupervised method described by Cabezas et al. . This module is intended to be used with FLAIR and T1 MRI volumes, which the MS lesions can be detected.

Use Cases

• Use Case 1: Multiple Sclerosis (MS) lesions segmentation
  • Using T1 and FLAIR MRI volumes, it can be possible to detect abnormal voxel signal using a parametric strategy, which delineates white matter signals that does not belongs to the majority neighborhood pattern. More details can be found in the original paper

• 

  Input T2-FLAIR image with Multiple Sclerosis lesions

• 

  Lesion map resulted from AFT Segmenter module

Panels and their use

User Interface

IO:

• T1 Volume
  • Input T1 volume
• T2-FLAIR Volume
  • Input T2-FLAIR volume
• Lesion Label
  • Output a global lesion mask
• Is brain extracted?
  • Is the input data (T1 and T2-FLAIR) already brain extracted?

Segmentation Parameters:

• Absolute Error Threshold
  • Define the absolute error threshold for gray matter statistics. This measure evaluated the similarity between the MNI152 template and the T2-FLAIR gray matter fluctuation estimative. A higher error gives a higher variability in the final lesion segmentation
• Gamma
  • Define the outlier detection based on units of standard deviation in the T2-FLAIR gray matter voxel intensity distribution
• White Matter Matching
  • Set the local neighborhood searching for label refinement step. This metric defines the percentage of white matter tissue that surrounds the hyperintense lesions. Large values defines a conservative segmentation, i.e. in order to define a true MS lesion, it must be close to certain percentage of white matter area.
• Minimum Lesion Size
  • Set the minimum lesion size adopted as a true lesion in the final lesion map. Units are given in number of voxels
• Gray Matter Mask Value
  • Set the mask value that represents the gray matter. Default is defined based on the (Basic Brain Tissues module) output
• White Matter Mask Value
  • Set the mask value that represents the white matter. Default is defined based on the (Basic Brain Tissues module) output

Similar Modules

• LS Segmenter

References

• Cabezas, M., Oliver, A., Roura, E., Freixenet, J., Vilanova, J. C., Ramió-Torrentà, L., Rovira, À. and Lladó, X. (2014) ‘Automatic multiple sclerosis lesion detection in brain MRI by FLAIR thresholding’, Computer Methods and Programs in Biomedicine. Elsevier Ireland Ltd, 115(3), pp. 147–161. DOI: 10.1016/j.cmpb.2014.04.006.