Atlas based AAM and SVM model for fully automatic MRI prostate segmentation

Author

Ruida Cheng ; Turkbey, Baris ; Gandler, William ; Agarwal, H.K. ; Shah, Vijay P. ; Bokinsky, Alexandra ; McCreedy, Evan ; Wang, Shuhui ; Sankineni, Sandeep ; Bernardo, Marcelino ; Pohida, Thomas ; Choyke, Peter ; McAuliffe, Matthew J.

Author_Institution

Image Sci. Lab., Nat. Inst. of Health, Bethesda, MD, USA

fYear

2014

fDate

26-30 Aug. 2014

Firstpage

2881

Lastpage

2585

Abstract

Automatic prostate segmentation in MR images is a challenging task due to inter-patient prostate shape and texture variability, and the lack of a clear prostate boundary. We propose a supervised learning framework that combines the atlas based AAM and SVM model to achieve a relatively high segmentation result of the prostate boundary. The performance of the segmentation is evaluated with cross validation on 40 MR image datasets, yielding an average segmentation accuracy near 90%.

Keywords

biological organs; biomedical MRI; edge detection; image segmentation; image texture; medical image processing; support vector machines; unsupervised learning; atlas based AAM model; atlas based SVM model; fully automatic MRI prostate boundary segmentation; interpatient prostate shape variability; interpatient prostate texture variability; supervised learning framework; Active appearance model; Image segmentation; Magnetic resonance imaging; Shape; Solid modeling; Support vector machines; Training;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society (EMBC), 2014 36th Annual International Conference of the IEEE

Conference_Location

Chicago, IL

ISSN

1557-170X

Type

conf

DOI

10.1109/EMBC.2014.6944225

Filename

6944225