Copyright Statement: This is an open access article licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, even commercially as long as the original work is properly cited.
Digital Object Identifier (DOI) : 10.14569/SpecialIssue.2011.010310
Article Published in International Journal of Advanced Computer Science and Applications(IJACSA), Special Issue on Artificial Intelligence, 2011.
Abstract: A method for line feature extraction from multifidus muscle of Computer Tomography (CT) scanned image with morphologic filter together with wavelet based Multi Resolution Analysis (MRA) is proposed. The contour of the multifidus muscle can be extracted from hip CT image. The area of multifidus muscle is then estimated and is used for an index of belly fat because there is a high correlation between belly fat and multifidus muscle. When the area of the multifidus muscle was calculated from the CT image, the MRA with Daubechies base functions and with the parameter of MRA of level is three would appropriate. After the wavelet transformation is applied to the original hip CT image three times and LLL (3D low frequency components) is filled “0” then inverse wavelet transformation is applied for reconstruction. The proposed method is validated with four patients.
Kohei Arai, Yuichiro Eguchi and Yoichiro Kitajima, “Extraction of Line Features from Multifidus Muscle of CT Scanned Images with Morphologic Filter Together with Wavelet Multi Resolution Analysis” International Journal of Advanced Computer Science and Applications(IJACSA), Special Issue on Artificial Intelligence, 2011. http://dx.doi.org/10.14569/SpecialIssue.2011.010310