Anomaly detection through registration

Author

Chen, Mei ; Kanade, Takeo ; Rowley, Henry A. ; Pomerleau, Dean

Author_Institution

Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA

fYear

1998

fDate

23-25 Jun 1998

Firstpage

304

Lastpage

310

Abstract

We study an application of image registration in the medical domain. Based on a 3-D hierarchical deformable registration algorithm, we have developed a prototype system which automatically aligns a standard atlas to a subject´s data to create a customized atlas. Combined with domain knowledge, the registration algorithm can also detect asymmetries and abnormal variations in the subject´s data that indicate the existence and location of pathologies. We have conducted tests on 106 MRI scans of normal brains, 3 MRI and 1 CT scan of brains with pathologies, with results qualitatively comparable to manual segmentation

Keywords

biomedical NMR; brain; image registration; 3-D hierarchical deformable registration algorithm; MRI scans; anomaly detection; brains; image registration; manual segmentation; medical domain; normal brains; pathologies; prototype system; registration algorithm; Anatomical structure; Computer science; Interpolation; Iterative algorithms; Morphology; Robust control; Sampling methods; Spinal cord; Stochastic processes;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Vision and Pattern Recognition, 1998. Proceedings. 1998 IEEE Computer Society Conference on

Conference_Location

Santa Barbara, CA

ISSN

1063-6919

Print_ISBN

0-8186-8497-6

Type

conf

DOI

10.1109/CVPR.1998.698624

Filename

698624