Understanding the "Demon's Algorithm": 3D Non-Rigid registration by Gradient Descent Export

@inproceedings{Pennec99, abstract = {The "Demons Algorithm" in increasingly used for non-rigid registration of 3D medical images. However, if it is fast and usually accurate, the algorithm is based on intuitive ideas about image registration and it is difficult to predict when it will fail and why. We show in this paper that this algorithm can be considered as an approximation of a second order gradient descent on the sum of square of intensity differences criterion. We also reformulate Gaussian and physical model regularizations as minimization problems. Experimental results on synthetic and 3D Ultrasound images show that this formalization helps identifying the weak points of the algorithm and offers new research openings.}, author = {Pennec, X. and Cachier, P. and Ayache, N.}, booktitle = {2nd int. conf. on medical image computing and computer-assisted intervention (MICCAI'99) LNSC}, citeulike-article-id = {4785880}, citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.35.2299}, keywords = {3d-imaging, demon-algorithm, non-rigid-registration}, pages = {597--605}, posted-at = {2009-06-09 12:55:24}, priority = {2}, title = {Understanding the "Demon's Algorithm": 3D Non-Rigid registration by Gradient Descent}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.35.2299}, volume = {1679}, year = {1999} }

TY - CONF ID - Pennec99 L3 - citeulike-article-id:4785880 N2 - The "Demons Algorithm" in increasingly used for non-rigid registration of 3D medical images. However, if it is fast and usually accurate, the algorithm is based on intuitive ideas about image registration and it is difficult to predict when it will fail and why. We show in this paper that this algorithm can be considered as an approximation of a second order gradient descent on the sum of square of intensity differences criterion. We also reformulate Gaussian and physical model regularizations as minimization problems. Experimental results on synthetic and 3D Ultrasound images show that this formalization helps identifying the weak points of the algorithm and offers new research openings. EP - 605 TI - Understanding the "Demon's Algorithm": 3D Non-Rigid registration by Gradient Descent VL - 1679 T2 - 2nd int. conf. on medical image computing and computer-assisted intervention (MICCAI'99) LNSC SP - 597 KW - 3d-imaging KW - demon-algorithm KW - non-rigid-registration AU - Pennec, X AU - Cachier, P AU - Ayache, N PY - 1999/// UR - http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.35.2299 ER -