Segmentation of kidney from ultrasound images based on texture and shape priors Export

@article{citeulike:364201, abstract = {This work presents a novel texture and shape priors based method for kidney segmentation in ultrasound (US) images. Texture features are extracted by applying a bank of Gabor filters on test images through a two-sided convolution strategy. The texture model is constructed via estimating the parameters of a set of mixtures of half-planed Gaussians using the expectation-maximization method. Through this texture model, the texture similarities of areas around the segmenting curve are measured in the inside and outside regions, respectively. We also present an iterative segmentation framework to combine the texture measures into the parametric shape model proposed by Leventon and Faugeras. Segmentation is implemented by calculating the parameters of the shape model to minimize a novel energy function. The goal of this energy function is to partition the test image into two regions, the inside one with high texture similarity and low texture variance, and the outside one with high texture variance. The effectiveness of this method is demonstrated through experimental results on both natural images and US data compared with other image segmentation methods and manual segmentation.}, author = {Xie, Jun and Jiang, Yifeng and Tsui, Hung-Tat}, citeulike-article-id = {364201}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/TMI.2004.837792}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1375160}, doi = {10.1109/TMI.2004.837792}, journal = {Medical Imaging, IEEE Transactions on}, keywords = {application, med\_app, similarity, texture}, number = {1}, pages = {45--57}, posted-at = {2008-11-12 22:28:51}, priority = {2}, title = {Segmentation of kidney from ultrasound images based on texture and shape priors}, url = {http://dx.doi.org/10.1109/TMI.2004.837792}, volume = {24}, year = {2005} }

TY - JOUR ID - citeulike:364201 L3 - citeulike-article-id:364201 N2 - This work presents a novel texture and shape priors based method for kidney segmentation in ultrasound (US) images. Texture features are extracted by applying a bank of Gabor filters on test images through a two-sided convolution strategy. The texture model is constructed via estimating the parameters of a set of mixtures of half-planed Gaussians using the expectation-maximization method. Through this texture model, the texture similarities of areas around the segmenting curve are measured in the inside and outside regions, respectively. We also present an iterative segmentation framework to combine the texture measures into the parametric shape model proposed by Leventon and Faugeras. Segmentation is implemented by calculating the parameters of the shape model to minimize a novel energy function. The goal of this energy function is to partition the test image into two regions, the inside one with high texture similarity and low texture variance, and the outside one with high texture variance. The effectiveness of this method is demonstrated through experimental results on both natural images and US data compared with other image segmentation methods and manual segmentation. IS - 1 JF - Medical Imaging, IEEE Transactions on EP - 57 TI - Segmentation of kidney from ultrasound images based on texture and shape priors VL - 24 SP - 45 KW - application KW - med_app KW - similarity KW - texture AU - Xie, Jun AU - Jiang, Yifeng AU - Tsui, Hung-Tat PY - 2005/// UR - http://dx.doi.org/10.1109/TMI.2004.837792 ER -