Interactive Three-Dimensional Segmentation Using Region Growing Algorithms. Issue 2 (June 2015)

• Record Type: Journal Article
• Authors: Yuan, Youwei; Chen, Dou; Yan, Lamei
• Is Part Of: Journal of algorithms & computational technology. Volume 9:Issue 2(2015)
• Page Start: 199
• Page End: 213
• Publication Date: 2015-06
• Subjects: Region growing -- Image Segmentation -- Computerized Tomography(CT) -- Mesh generation; Computer algorithms -- Periodicals; Numerical calculations -- Periodicals; Computer algorithms; Numerical calculations; Periodicals; 518.1
• DOI: 10.1260/1748-3018.9.2.199
• Languages: English
• ISSNs: 1748-3018

Abstract

This paper presents a new interactive three-dimensional(3D) segmentation using region growing algorithms. The principle of this method is to build region growing sequence by increasing the maximal homogeneity threshold recursively until it satisfied with the needs. Firstly we calculate the average of the markers' coordination to get the seed point. Then calculate the difference between the neighbours and the average intensity of the seed points as well as using the modification of the Euclidean distance. Finally by conducting extensive performance evaluation to prove the proposed method more accurate and robust to the noise in CT images. We have successfully applied this approach to 3D segmentations of human femur obtained from CT scans. Satisfactory results have been achieved showing the effectiveness and superiority of the proposed method.