Automatic 3D left ventricular border detection using active appearance models

Author

Leung, K. Y Esther ; Van Stralen, Marijn ; Van Burken, Gerard ; Van der Steen, Antonius F W ; De Jong, Nico ; Bosch, Johan G.

Author_Institution

Thoraxcenter Biomed. Eng., Erasmus MC, Rotterdam, Netherlands

fYear

2010

fDate

11-14 Oct. 2010

Firstpage

197

Lastpage

200

Abstract

A fully automated segmentation for 3D echocardiography (3DE) using 3D Active Appearance Models (AAM) was developed and evaluated on end-diastolic (ED) and end-systolic (ES) images of 99 patients. The method used ultrasound specific grey value normalization and employed both regular matching and jacobian tuning. The 3D AAM detected the endocardial contours accurately, even in the presence of large variations in left ventricular appearance and shape. Matching was successful in 87% of patients and resulted in good median point-to-surface errors of 2.65 mm for ED and 3.21 for ES, and good volume regressions (ED: y = -3.2 +1.01x, r=0.95; ES: y = -4.6 + 1.01x, r=0.92). Results show that fully automated AAM analysis is practically feasible in 3DE datasets of mixed origin and quality.

Keywords

blood vessels; echocardiography; edge detection; image segmentation; medical image processing; 3D echocardiography; active appearance model; automatic 3D left ventricular border detection; end-diastolic image; end-systolic image; endocardial contour; jacobian tuning; regular matching; ultrasound specific grey value normalization; Active appearance model; Echocardiography; Image segmentation; Jacobian matrices; Shape; Three dimensional displays; Ultrasonic imaging; 3D echocardiography; Automatic segmentation; active appearance models; left ventricular volume; ultrasound;

fLanguage

English

Publisher

ieee

Conference_Titel

Ultrasonics Symposium (IUS), 2010 IEEE

Conference_Location

San Diego, CA

ISSN

1948-5719

Print_ISBN

978-1-4577-0382-9

Type

conf

DOI

10.1109/ULTSYM.2010.5935446

Filename

5935446