Active appearance motion model segmentation

Author

Sonka, Milan ; Lelieveldt, Boudewijn P F ; Mitchell, Steven C. ; Bosch, Johan G. ; Van der Geest, Rob J. ; Reiber, Johan H C

Author_Institution

Dept. of Electr. & Comput. Eng., Iowa Univ., Iowa City, IA, USA

fYear

2001

fDate

2001

Firstpage

64

Lastpage

68

Abstract

An adaptive method for temporal sequence segmentation was developed and its performance assessed in the segmentation of cardiac motion image sequences. The primary contribution of this paper is the development of a novel, 2D+time active appearance motion model (AAMM) that represents the dynamics of the cardiac cycle in combination with the shape and image appearance of the heart. Cootes´ 2D active appearance model (AAM) framework was extended by considering a complete image sequence as a single shape/intensity sample. This way, the proven strength of AAMs, like robustness and ability to capture observer preference, are augmented with temporal consistency over an image sequence

Keywords

cardiology; image segmentation; image sequences; medical image processing; 2D active appearance model framework; active appearance motion model segmentation; adaptive method; cardiac cycle dynamics; cardiac motion image sequences; complete image sequence; heart image appearance; heart shape; image sequence; observer preference; single shape/intensity sample; temporal consistency; temporal sequence segmentation; Active appearance model; Active shape model; Biomedical engineering; Cities and towns; Heart; Image segmentation; Image sequences; Principal component analysis; Radiology; Robustness;

fLanguage

English

Publisher

ieee

Conference_Titel

Digital and Computational Video, 2001. Proceedings. Second International Workshop on

Conference_Location

Tampa, FL

Print_ISBN

0-7695-1110-4

Type

conf

DOI

10.1109/DCV.2001.929943

Filename

929943