Automatic medical image segmentation using gradient and intensity combined level set method. Export

@article{citeulike:2352550, abstract = {This paper presents a new level set based solution for automatic medical image segmentation. Study shows that level set methods using image intensity or gradient information alone can not generate satisfying segmentation on some complex organic structures, such as lung bronchia or nodules. We investigate the intensity distribution of these organic structures, and propose a calibrating mechanism to automatically weight image intensity and gradient information in the level set speed function. The new method can tolerate estimation error in intensity distribution and detect object boundaries whose gradient is low. The experimental results show that the proposed method gives stable and accurate segmentation results on public lung image data.}, address = {Dept. of Comput. Sci. \& Eng., Oklahoma Univ., Rochester, MI.}, author = {Liu, S. and Li, J.}, citeulike-article-id = {2352550}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/IEMBS.2006.259615}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4462457}, citeulike-linkout-2 = {http://view.ncbi.nlm.nih.gov/pubmed/17946548}, citeulike-linkout-3 = {http://www.hubmed.org/display.cgi?uids=17946548}, doi = {10.1109/IEMBS.2006.259615}, issn = {1557-170X}, journal = {Conf Proc IEEE Eng Med Biol Soc}, keywords = {image}, pages = {3118--3121}, posted-at = {2008-02-08 08:25:03}, priority = {3}, title = {Automatic medical image segmentation using gradient and intensity combined level set method.}, url = {http://dx.doi.org/10.1109/IEMBS.2006.259615}, volume = {1}, year = {2006} }

TY - JOUR ID - citeulike:2352550 L3 - citeulike-article-id:2352550 N2 - This paper presents a new level set based solution for automatic medical image segmentation. Study shows that level set methods using image intensity or gradient information alone can not generate satisfying segmentation on some complex organic structures, such as lung bronchia or nodules. We investigate the intensity distribution of these organic structures, and propose a calibrating mechanism to automatically weight image intensity and gradient information in the level set speed function. The new method can tolerate estimation error in intensity distribution and detect object boundaries whose gradient is low. The experimental results show that the proposed method gives stable and accurate segmentation results on public lung image data. JF - Conf Proc IEEE Eng Med Biol Soc SN - 1557-170X AD - Dept. of Comput. Sci. & Eng., Oklahoma Univ., Rochester, MI. EP - 3121 TI - Automatic medical image segmentation using gradient and intensity combined level set method. VL - 1 SP - 3118 KW - image AU - Liu, S AU - Li, J PY - 2006/// UR - http://dx.doi.org/10.1109/IEMBS.2006.259615 ER -