[Insight-users] Atlas segmentation : Segmentation by registration with an atlas.

[Bill Lorensen]

As a follow up, here at GE Dan Blezek has used a modification of the cited example to successfully warp MRI data to the Brigham and Women's brain atlas. The Demon's works great!!

At 09:56 AM 8/7/03 -0400, Luis Ibanez wrote:
>Hi Yasser,
>
>Yes, ITK offers options for atlas based segmentation.
>That is, to achieve segmentation by registering an
>input data set against a pre-segmented dataset (the
>atlas).
>
>You may want to look at the Demon's registration
>method described in the software guide.
>http://www . itk . org/ItkSoftwareGuide . pdf
>Section 8.13, pdf-page 312.
>
>You will also find a validation application of Atlas-
>Segmentation using FEM-based deformable registration
>in the InsightApplications module:
>
>InsightApplications/IBSRValidation/FEMAtlasSegmentation
>http://www . itk . org/cgi-bin/cvsweb . cgi/InsightApplications/IBSRValidation/FEMAtlasSegmentation/?cvsroot=Insight
>
>----
>
>In principle you could use any of the registration
>combinations available in ITK (not only Demons or FEM).
>
>If the segmentation of your atlas is a crisp segmentation
>(that is a real binary mask), you could also try the
>NarrowBand-to-Image registration method. For this you may
>have to combine the filter BinaryMaskToNarrowBandPointSet
>http://www . itk . org/Insight/Doxygen/html/classitk_1_1BinaryMaskToNarrowBandPointSetFilter . html
>and then the PointSetToImageRegistrationMethod
>http://www . itk . org/Insight/Doxygen/html/classitk_1_1PointSetToImageRegistrationMethod . html
>
>
>Please let us know if you have further questions.
>
>
>  Thanks
>
>
>    Luis
>
>
>--------------------------------------------------
>yasser salman wrote:
>>hi luis..,
>>can i use ITK to label a "brain tissue" from Digital
>>Brain atlas using registration process..
>
>_______________________________________________
>Insight-users mailing list
>Insight-users at itk . org
>http://www . itk . org/mailman/listinfo/insight-users