|
|
- 2018
基于胸部CT影像的肺血管树分割关键技术研究
|
Abstract:
肺支气管的排除和血管组织的精确探测, 是影响肺血管树分割精度的重要因素．经形态学处理后的CT影像可提高对器官信息的探测能力, 因此提出形态学辅助的区域生长方法用于支气管分割, 并引入泄漏判断条件抑制分割泄漏．针对血管组织的提取, 提出多阈值分割方法, 通过引入多尺度滤波器获取不同尺寸半径血管的最大响应尺度信息, 计算血管组织相应的分割阈值, 实现分割阈值的动态匹配．实验结果表明：应用于10套CT影像, 血管组织分割准确率为97.062% , 血管分支抽取率为93.95% , 肺血管树分割精度得到较大提高．
The elimination of lung bronchus and the precise detection of vascular tissues are the major factors affecting the segmentation accuracy of pulmonary vascular trees. The morphological disposal with CT image could improve the ability of organ detection，thus a morphology-assisted region growing method was proposed to segment bronchus. Besides，the leak judgment function was also introduced to avoid the leakage phenomenon. In order to extract vascular tissues，the multi-threshold segmentation method was proposed，which is based on the multi-scale enhancement filter. By acquiring the max response information of vascular tissues with different radius，the corresponding segmentation threshold of vascular tissues was calculated and the dynamic matching between vascular tissues and segmentation threshold was achieved. Being applied to 10 sets of CT images，the proposed algorithm exhibited promising results. The segmentation accuracy rate of vascular tissues and the extraction rate of vascular branches were 97.062% and 93.95% ，respectively，considerably improving the segmentation accuracy of pulmonary vascular trees
| [1] | Liu Zhongqiang. Pulmonary Vascular Segmentation Methods in CT Images[D]. Wuhan:School of Computer Science and Technology, Huazhong University of Science and Technology, 2016(in Chinese). |
| [2] | van Dongen E, van Ginneken B. Automatic segmentation of pulmonary vasculature in thoracic CT scans with local thresholding and airway wall removal[C]// <i>IEEE International Conference on Biomedical Imaging</i>:<i>From Nano to Macro.<i> Rotterdam, Netherlands, 2010:668-671. |
| [3] | 黄煜峰, 王兴家, 赖凯, 等. 基于SMDC 连接代价算子的肺血管分割算法研究[J]. 北京生物医学工程, 2010, 29(3):235-240. |
| [4] | Huang Yufeng, Wang Xingjia, Lai Kai, et al. Algorithm of lung segmentation based on SMDC-connection cost[J]. <i>Beijing Biomedical Engineering</i>, 2010, 29(3):235-240(in Chinese). |
| [5] | 高齐新, 杨金柱, 赵大哲, 等. 一种基于Canny算子的level-set肺部血管分割算法[J]. 系统仿真学报, 2008, 20(20):5534-5537. |
| [6] | Lai J, Huang Y, Wang Y, et al. Three-dimension segmentation of pulmonary vascular trees for low dose CT scans[J]. <i>Sensing and Imaging</i>, 2016, 17(1):1-15. |
| [7] | Gao Qixin, Yang Jinzhu, Zhao Dazhe, et al. Pulmonary vessel for X-ray CT images segmented through Canny level-set[J]. <i>Journal of System Simulation</i>, 2008, 20(20):5534-5537(in Chinese). |
| [8] | van Rikxoort E M, van Ginneken B. Automated segmentation of pulmonary structures in thoracic computed tomography scans:A review[J]. <i>Physics in Medicine & Biology</i>, 2013, 58(17):187-220. |
| [9] | Zhu Y, Tan Y, Hua Y, et al. Automatic segmentation of ground-glass opacities in lung CT images by using Markov random field-based algorithms[J]. <i>Journal of Digital Imaging</i>, 2012, 25(3):409-422. |
| [10] | Chen B, Kitasaka T, Honma H, et al. Automatic segmentation of pulmonary blood vessels and nodules based on local intensity structure analysis and surface propagation in 3D chest CT images[J]. <i>International Journal of Computer Assisted Radiology and Surgery</i>, 2012, 7(3):465-482. |
| [11] | 刘忠强. CT图像中的肺血管分割方法[D]. 武汉:华中科技大学计算机科学与技术学院, 2016. |
| [12] | Fabija？？ska A. Segmentation of pulmonary vascular tree from 3D CT thorax scans[J]. <i>Biocybernetics and Biomeical Engineering</i>, 2015, 35(2):106-119. |
| [13] | Orkisz M, Hoyos M H, Romanello V P, et al. Segmentation of the pulmonary vascular trees in 3D CT images using variational region-growing[J]. <i>IRBM</i>, 2014, 35(1):11-19. |
| [14] | Manivila K D. Automatic vessel segmentation of lung affected patterns in MDCT using decision tree classification[J]. <i>Middle-East Journal of Scientific Research</i>, 2014, 22(11):1679-1685. |
| [15] | Lorenson W E, Cline H E. Marching cubes:A high resolution 3D surface construction algorithm[J]. <i>Computer Graphics</i>, 1987, 21(4):163-169. |
| [16] | Zhu C, Qi S, Han V T, et al. Automatic 3D segmentation of human airway tree in CT image[C]// <i>International Conference on Biomedical Engineering and Informatics</i>. Yantai, China, 2010:132-136. |
| [17] | Bartz D, Mayer D, Fischer J, et al. <i>Hybrid segmentation and exploration of the human lungs</i>[C]// <i>Proceedings of the<i> 14<i>th IEEE Visualization Conference</i>(<i>VIS</i>’03). Washington, USA, 2003:177-184. |
| [18] | Frangi A F, Niessen W J, Vincken K L, et al. Multiscale vessel enhancement filtering[C]//<i>Medical Image Computing and Computer Assisted Intervention</i>. MA, USA, 1998:130-137. |
| [19] | Shikata H, Mclennan G, Hoffman E A, et al. Segmentation of pulmonary vascular trees from thoracic 3D CT images using level-set[C]//<i>International Conference on Intelligent Information Technology Application.<i> Qin-huangdao, China, 2009:24. |
| [20] | Zhou X, Hayashi T, Fujita H, et al. Automatic segmentation and recognition of anatomical lung structures from high-resolution chest CT images[J]. <i>Computerized Medical Imaging & Graphics the Official Journal of the Computerized Medical Imaging Society</i>, 2006, 30(5):299-313.</i></i></i></i></i></i> |
| [21] | El-Baz A, Suri J S. <i>Lung Imaging and Computer Aided Diagnosis</i>[M]. FL, USA:CRC Press, 2011:189-219. |
| [22] | Park S, Lee S M, Kim N, et al. Automatic reconstruct- |
| [23] | tion of the arterial and venous trees on volumetric chest CT[J]. <i>Medical Physics</i>, 2013, 40(7):563-572. |
