Automated CT and MR brain image registration using geometrical feature correlation

Author

van den Elsen, P.A. ; Viergever, Max A.

Author_Institution

Utrecht Univ., Netherlands

fYear

1993

fDate

31 Oct-6 Nov 1993

Firstpage

1827

Abstract

Describes an automated, retrospective approach to register CT and MR brain images, using patient related image properties only. Mathematically well founded differential operators in scale space are applied to 2D or 3D image data, resulting in feature images depicting “ridgeness” The CT and MR feature images show similarity which can be used for matching using a fully automatic hierarchical correlation scheme. Results of 2D and 3D matching experiments are presented

Keywords

biomedical NMR; brain; computerised tomography; geometry; image registration; medical image processing; CT brain images; MR brain images; automated image registration; automated retrospective approach; feature images; fully automatic hierarchical correlation scheme; geometrical feature correlation; matching experiments; mathematically well founded differential operators; medical diagnostic imaging; ridgeness; scale space; Biomedical imaging; Brain; Computed tomography; Feature extraction; Hospitals; Image registration; Image resolution; Magnetic resonance imaging; Medical diagnostic imaging; Radiology;

fLanguage

English

Publisher

ieee

Conference_Titel

Nuclear Science Symposium and Medical Imaging Conference, 1993., 1993 IEEE Conference Record.

Conference_Location

San Francisco, CA

Print_ISBN

0-7803-1487-5

Type

conf

DOI

10.1109/NSSMIC.1993.373608

Filename

373608