TY - GEN
T1 - Application of trace-norm and low-rank matrix decomposition for computational anatomy
AU - Batmanghelich, Nematollah
AU - Gooya, Ali
AU - Kanterakis, Stathis
AU - Taskar, Ben
AU - Davatzikos, Christos
PY - 2010/9/17
Y1 - 2010/9/17
N2 - We propose a generative model to distinguish normal anatomical variations from abnormal deformations given a group of images with normal and abnormal subjects. We assume that abnormal subjects share common factors which characterize the abnormality. These factors are hard to discover due to large variance of normal anatomical differences. Assuming that the deformation fields are parametrized by their stationary velocity fields, these factors constitute a low-rank subspace (abnormal space) that is corrupted by high variance normal anatomical differences. We assume that these normal anatomical variations are not correlated. We form an optimization problem and propose an efficient iterative algorithm to recover the low-rank subspace. The algorithm iterates between image registration and the decomposition steps and hence can be seen as a group-wise registration algorithm. We apply our method on synthetic and real data and discover abnormality of the population that cannot be recovered by some of the well-known matrix decompositions (e.g. Singular Value Decomposition).
AB - We propose a generative model to distinguish normal anatomical variations from abnormal deformations given a group of images with normal and abnormal subjects. We assume that abnormal subjects share common factors which characterize the abnormality. These factors are hard to discover due to large variance of normal anatomical differences. Assuming that the deformation fields are parametrized by their stationary velocity fields, these factors constitute a low-rank subspace (abnormal space) that is corrupted by high variance normal anatomical differences. We assume that these normal anatomical variations are not correlated. We form an optimization problem and propose an efficient iterative algorithm to recover the low-rank subspace. The algorithm iterates between image registration and the decomposition steps and hence can be seen as a group-wise registration algorithm. We apply our method on synthetic and real data and discover abnormality of the population that cannot be recovered by some of the well-known matrix decompositions (e.g. Singular Value Decomposition).
UR - http://www.scopus.com/inward/record.url?scp=77956553889&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=77956553889&partnerID=8YFLogxK
U2 - 10.1109/CVPRW.2010.5543596
DO - 10.1109/CVPRW.2010.5543596
M3 - Conference contribution
AN - SCOPUS:77956553889
SN - 9781424470297
T3 - 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops, CVPRW 2010
SP - 146
EP - 153
BT - 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops, CVPRW 2010
T2 - 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops, CVPRW 2010
Y2 - 13 June 2010 through 18 June 2010
ER -