Xu Li1, Chunming Li2, Hairong Liu3, Xiaoping Yang4. 1. School of Mathematical Sciences, Zhejiang University, Hangzhou, Zhejiang 310027, PR China. 2. School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, PR China. 3. School of Science, Nanjing Forestry University, Nanjing 210037, PR China. 4. Department of Mathematics, Nanjing University, Nanjing 210093, PR China. Electronic address: xpyang@nju.edu.cn.
Abstract
PURPOSE: The segmentation of organs and lesions from medical images is a challenging task due to the presents of noise, intensity inhomogeneity, blurry/weak boundaries. In this paper, a point distance shape constraint is proposed and incorporated in the level set framework for the segmentation of objects with various shapes. METHODS: The proposed shape constraint is a linear combination of the Euclidean distance of user selected points. By selecting different numbers of points, it can generate different shape constraints and therefore is more flexible in dealing with different shapes. Then this shape constraint is incorporated into the variational level set framework. A convex relaxation is applied to get a convex model which can be efficiently solved by a primal-dual hybrid gradient algorithm. RESULTS: The proposed algorithm is tested on 60 CT images with the nodular type of hepatic cellular cancer (HCC), 100 ultrasound kidney images, 20 prostate MR images, 20 lumbar CT images and 100 transrectal ultrasound prostate images. The algorithms performance is evaluated using a number of metrics by comparison with expert delineations. The validation results show that, for five datasets mentioned previously, the average DSCs of the proposed algorithm are 95.6% ± 1.4%, 94.3% ± 3.1%, 91.3% ± 3.8%, 92.7% ± 1.5% and 94.4% ± 2.2% respectively. Both quantitative and qualitative evaluation confirm that the proposed method can provide more accurate segmentation than four state-of-the-art methods. CONCLUSION: The proposed point distance shape constraint segmentation model can accurately segment organs and lesions with a number of shapes in medical images.
PURPOSE: The segmentation of organs and lesions from medical images is a challenging task due to the presents of noise, intensity inhomogeneity, blurry/weak boundaries. In this paper, a point distance shape constraint is proposed and incorporated in the level set framework for the segmentation of objects with various shapes. METHODS: The proposed shape constraint is a linear combination of the Euclidean distance of user selected points. By selecting different numbers of points, it can generate different shape constraints and therefore is more flexible in dealing with different shapes. Then this shape constraint is incorporated into the variational level set framework. A convex relaxation is applied to get a convex model which can be efficiently solved by a primal-dual hybrid gradient algorithm. RESULTS: The proposed algorithm is tested on 60 CT images with the nodular type of hepatic cellular cancer (HCC), 100 ultrasound kidney images, 20 prostate MR images, 20 lumbar CT images and 100 transrectal ultrasound prostate images. The algorithms performance is evaluated using a number of metrics by comparison with expert delineations. The validation results show that, for five datasets mentioned previously, the average DSCs of the proposed algorithm are 95.6% ± 1.4%, 94.3% ± 3.1%, 91.3% ± 3.8%, 92.7% ± 1.5% and 94.4% ± 2.2% respectively. Both quantitative and qualitative evaluation confirm that the proposed method can provide more accurate segmentation than four state-of-the-art methods. CONCLUSION: The proposed point distance shape constraint segmentation model can accurately segment organs and lesions with a number of shapes in medical images.