<div>Dear Itk users,</div>
<div> </div>
<div>I'm using GeodesicActiveContourShapePriorLevelSetFilter image filter to segment 2d sagittal</div>
<div>images of vertebrae from L1 to S1. We created an average shape as described within the </div>
<div>itk programming guide using about 50 images for each vertebrae, so the segmented vertebrae</div>
<div>were registered ,we did the pca and so on.... </div>
<div>After the training set has been created we tried the algorithm on some image, the user was</div>
<div>able to click on the vertebrae and from this seed point the segmentation started. We found that the</div>
<div>final resul is a lot influenced by the rotation of the object to be segmented, than we modified a bit</div>
<div>our user interface so that the user could specify an initial rotation of the vertebrae to be segmented.</div>
<div>The results we got were quite good, but still there are some cases like those attached where the </div>
<div>final segmentation is not perfectly adherent to the vertebrae border and the segmented object</div>
<div>is not perfectly rotated.</div>
<div> </div>
<div>Could you please give me some advice ?</div>
<div>Any hint would help.</div>
<div>Kind regards</div>
<div>-Loris</div>
<div> </div>