I am working in level set/active contour method using spatial prior information . The main papers that I am focusing:"Automatic segmentation of neonatal images using convex optimization and coupled level sets"-2011. It is very nice papers.

However, I am confusing about some points in the paper. In the paper, the author said that "For a given subject image, by using HAMMER algorithm to warp the atlas image into the subject image space, we can derive spatial prior information priori for WM, GM and CSF, respectively, for the subject image".As my understand, we have a original image (need to segment), a template image, and a spatial prior image (range [0,1]). Using HAMMER method, you will transform spatial prior image in to original image. Then, original image is fixed and prior image is moving. Is it right? Or vice versa, the spatial prior image is fixed and original image is moving, which is correct? Because the main reason of warping step is that we want to find a corresponding prior value of a given input pixel in the spatial prior map.

When I read some tool such as SPM, I saw that original image often fixed and spatial prior information is moving. Is it correct?

Thanks in advance


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.