Yankai Jiang1, Jiahong Qian1, Shijuan Lu1, Yubo Tao1,2, Jun Lin3, Hai Lin4,5. 1. State Key Laboratory of CAD and CG, Zhejiang University, Hangzhou, China. 2. Innovation Center for Minimally Invasive Technique and Device, Zhejiang University, Hangzhou, China. 3. Department of Stomatology, The First Affiliated Hospital, College of Medicine, Zhejiang University, Hangzhou, China. linjun2@zju.edu.cn. 4. State Key Laboratory of CAD and CG, Zhejiang University, Hangzhou, China. lin@cad.zju.edu.cn. 5. Innovation Center for Minimally Invasive Technique and Device, Zhejiang University, Hangzhou, China. lin@cad.zju.edu.cn.
Abstract
OBJECTIVES: To segment the mandible from cone-beam computed tomography (CBCT) images efficiently and accurately for the 3D mandible model is essential for subsequent research and diagnosis. METHODS: This paper proposes a local region-based variational region growing algorithm, which integrates local region and shape prior to segment the mandible accurately. Firstly, we select initial seeds in the CBCT image and then calculate candidate point sets and the local region energy function of each point. If a point reduces the energy, it is selected to be a pixel of the foreground region. By multiple iterations, the mandible segmentation of the slice can be obtained. Secondly, the segmented result of the previous slice is adopted as the shape prior to the next slice until all of the slices in CBCT are segmented. At last, the final mandible model is reconstructed by the Marching Cubes algorithm. RESULTS: The experimental results on CBCT datasets illustrate the LRVRG algorithm can obtain satisfied 3D mandible models from CBCT images and it can solve the fuzzy problem effectively. Furthermore, quantitative comparisons with other methods demonstrate the proposed method achieves the state-of-the-art performance in mandible segmentation. CONCLUSIONS: Experiments demonstrate that our method is efficient and accurate for the mandible model segmentation.
OBJECTIVES: To segment the mandible from cone-beam computed tomography (CBCT) images efficiently and accurately for the 3D mandible model is essential for subsequent research and diagnosis. METHODS: This paper proposes a local region-based variational region growing algorithm, which integrates local region and shape prior to segment the mandible accurately. Firstly, we select initial seeds in the CBCT image and then calculate candidate point sets and the local region energy function of each point. If a point reduces the energy, it is selected to be a pixel of the foreground region. By multiple iterations, the mandible segmentation of the slice can be obtained. Secondly, the segmented result of the previous slice is adopted as the shape prior to the next slice until all of the slices in CBCT are segmented. At last, the final mandible model is reconstructed by the Marching Cubes algorithm. RESULTS: The experimental results on CBCT datasets illustrate the LRVRG algorithm can obtain satisfied 3D mandible models from CBCT images and it can solve the fuzzy problem effectively. Furthermore, quantitative comparisons with other methods demonstrate the proposed method achieves the state-of-the-art performance in mandible segmentation. CONCLUSIONS: Experiments demonstrate that our method is efficient and accurate for the mandible model segmentation.
Keywords:
CBCT images; Local region; Mandible segmentation; Shape prior; Variational region growing
Authors: Pei-yong Tan; Jin-huan Chen; Peng Li; Ji-xiang Guo; Wei Tang; Jie Long; Lei Liu; Wei-dong Tian Journal: Sichuan Da Xue Xue Bao Yi Xue Ban Date: 2015-05