Atlas based AAM and SVM model for fully automatic MRI prostate segmentation
Ruida Cheng, Barış Türkbey, William Gandler, Harsh Agarwal, Vijay P. Shah, Alexandra Bokinsky, Evan S. McCreedy, Shijun Wang, Sandeep Sankineni, Marcelino Bernardo, Thomas J. Pohida, Peter L. Choyke, Matthew McAuliffe · 2014
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%.