Title :
A fast model-based prostate boundary segmentation using normalized cross-correlation and representative patterns in ultrasound images
Author :
Vafaie, R. ; Alirezaie, J. ; Babyn, Paul
Author_Institution :
Dept. of Electr. & Comput. Eng., Ryerson Univ., Toronto, ON, Canada
Abstract :
Segmentation of prostate boundaries in transrectal ultrasound (TRUS) images plays a great role in early detection of prostate cancer. Due to the low signal to noise ratio and existence of the speckle noise in TRUS images, prostate image segmentation has proven to be an extremely difficult task. This paper introduces a new fully automatic model-based prostate boundary segmentation method based on normalized cross-correlation (NCC). Using lower and upper boundary representative patterns, a strip rotates around the center of the probe and emphasizes the prostate boundaries. Representative patterns are constructed from a dictionary learning method, referred to as iterative least squares dictionary learning algorithm (ILS-DLA). Affine transformation parameters transform the prostate model to a position that best fit on the emphasized boundaries. Dice similarity coefficient (DSC) is adopted to evaluate the accuracy of the automatic segmentation procedure. Successful experimental results and the average DSC value of 90.6% and computational time of 3.08 seconds validate the proposed method.
Keywords :
affine transforms; biomedical ultrasonics; cancer; image representation; image segmentation; iterative methods; learning (artificial intelligence); least squares approximations; medical image processing; speckle; DSC; ILS-DLA; NCC; TRUS image; affine transformation parameters; automatic model-based prostate boundary segmentation method; computational time; dice similarity coefficient; dictionary learning method; fast model-based prostate boundary segmentation; iterative least squares dictionary learning algorithm; lower boundary representative patterns; normalized cross-correlation; prostate cancer detection; prostate image segmentation; signal-to-noise ratio; speckle noise; transrectal ultrasound image; upper boundary representative patterns; Iterative least squares dictionary learning algorithm; Model-based prostate boundary segmentation; Normalized cross-correlation (NCC); Representative pattern construction; Transrectal ultrasound (TRUS);
Conference_Titel :
Biomedical Engineering and Sciences (IECBES), 2012 IEEE EMBS Conference on
Conference_Location :
Langkawi
Print_ISBN :
978-1-4673-1664-4
DOI :
10.1109/IECBES.2012.6498132