GVF Snake算法的改进及其在肺癌检测技术中的应用
|
摘要
肺部图像的自动分割技术,对于减少临床漏诊及误诊有重要的意义。肺部图像分割提取肺部图像中的肺实质,得到肺部肿瘤特征,给出肺部图像肿瘤的分割结果,帮助医生进行分析和判断。肺部图像中肺实质的提取在肺部图像自动分割系统中有重要的意义。
首先,通过对现有的肺部自动检测技术进行分析,针对活动轮廓模型无法解决深凹陷问题,提出了基于改进能量公式的GVF Snake算法。通过引入肺部图像的梯度和曲率等信息,并在它们的共同合力作用下,改进了能量公式,确定肺部图像边界,解决了活动轮廓算法无法对深凹陷进行分割的问题。
其次,改进能量公式后,活动轮廓曲线的停止条件将发生变化,针对改进后的GVF Sanke算法中,活动轮廓曲线将出现无法停止,并且越过真实边界,收敛于一点的现象,给出通过梯度信息和曲率信息对外力的引导方向。引入符号函数重新设定曲线运动的停止条件,解决曲线无法收敛于真实边界的问题。活动轮廓曲线的停止条件的重新设定提高了肺部图像分割的速度,降低算法的时间复杂度。
然后,针对胸膜处粘连的肺部肿瘤在分割中出现肺部图像边界不连续或是连续却与真实的肺部图像边界相差很远的漏分割问题,提出自适应边界行进算法。该算法通过几何方式平滑肺边界,解决肺部图像中肺部粘连肿瘤的漏分割问题。
最后,本文对计算机断层扫描的原图像分割进行模拟实验。根据大量实验,分析肺部图像分割算法中存在的问题,为进一步的研究提供方向和宝贵的经验。
Automatic segmentation techniques of lung image has an important clinical significance for the reduce misdiagnosis and missed diagnosis. Lung image segmentation extracts the first source image of the lung parenchymal get lung nodule characteristics, the final analysis and screening through the classifier, given the findings and diagnoses to help doctors analyze and judge. Extraction of pulmonary parenchyma in the lung image segmentation system has an important significance.
First of all, we aim at through the lungs of the existing automatic detection system for analysis, for active contour model can not solve the problem of deep depression is proposed to improve the energy formula based on GVF Snake algorithm, by introducing the image information such as gradient and curvature, in their common of forces, the improvement of the energy equation to determine the lung border, solve the active contour algorithm is unable to carry out the division of the deep depression.
Secondly, we research deeply based on the improvement of the energy equation, the stop condition of the curve will change when GVF sanke algorithm stop, the curve will occur can not stop crossing the border and converge to the true point phenomenon, put forward by gradient information and curvature information to external guidance direction, the introduction of sign function to re-set the curve of the movement to stop the conditions to solve the boundary curve can not converge to the real problems and improve the speed of image segmentation and reduce the algorithm's time complexity.
Then,we proposed adaptive border marching algorithm for the pleural adhesion at segmentation of lung nodules in the lungs appeared discontinuous or continuous, boundary is the boundary with the actual lung very far split the leakage issue, it is a new frontier repair method, using geometric means smooth lung boundary, solve the leakage lung cancer division of adhesions.
Finally, in this paper we use the original CT image segmentation to experiment. According to a large number of experiments, analysis of lung image segmentation problems, provide direction for further research and valuable experience.
首先,通过对现有的肺部自动检测技术进行分析,针对活动轮廓模型无法解决深凹陷问题,提出了基于改进能量公式的GVF Snake算法。通过引入肺部图像的梯度和曲率等信息,并在它们的共同合力作用下,改进了能量公式,确定肺部图像边界,解决了活动轮廓算法无法对深凹陷进行分割的问题。
其次,改进能量公式后,活动轮廓曲线的停止条件将发生变化,针对改进后的GVF Sanke算法中,活动轮廓曲线将出现无法停止,并且越过真实边界,收敛于一点的现象,给出通过梯度信息和曲率信息对外力的引导方向。引入符号函数重新设定曲线运动的停止条件,解决曲线无法收敛于真实边界的问题。活动轮廓曲线的停止条件的重新设定提高了肺部图像分割的速度,降低算法的时间复杂度。
然后,针对胸膜处粘连的肺部肿瘤在分割中出现肺部图像边界不连续或是连续却与真实的肺部图像边界相差很远的漏分割问题,提出自适应边界行进算法。该算法通过几何方式平滑肺边界,解决肺部图像中肺部粘连肿瘤的漏分割问题。
最后,本文对计算机断层扫描的原图像分割进行模拟实验。根据大量实验,分析肺部图像分割算法中存在的问题,为进一步的研究提供方向和宝贵的经验。
Automatic segmentation techniques of lung image has an important clinical significance for the reduce misdiagnosis and missed diagnosis. Lung image segmentation extracts the first source image of the lung parenchymal get lung nodule characteristics, the final analysis and screening through the classifier, given the findings and diagnoses to help doctors analyze and judge. Extraction of pulmonary parenchyma in the lung image segmentation system has an important significance.
First of all, we aim at through the lungs of the existing automatic detection system for analysis, for active contour model can not solve the problem of deep depression is proposed to improve the energy formula based on GVF Snake algorithm, by introducing the image information such as gradient and curvature, in their common of forces, the improvement of the energy equation to determine the lung border, solve the active contour algorithm is unable to carry out the division of the deep depression.
Secondly, we research deeply based on the improvement of the energy equation, the stop condition of the curve will change when GVF sanke algorithm stop, the curve will occur can not stop crossing the border and converge to the true point phenomenon, put forward by gradient information and curvature information to external guidance direction, the introduction of sign function to re-set the curve of the movement to stop the conditions to solve the boundary curve can not converge to the real problems and improve the speed of image segmentation and reduce the algorithm's time complexity.
Then,we proposed adaptive border marching algorithm for the pleural adhesion at segmentation of lung nodules in the lungs appeared discontinuous or continuous, boundary is the boundary with the actual lung very far split the leakage issue, it is a new frontier repair method, using geometric means smooth lung boundary, solve the leakage lung cancer division of adhesions.
Finally, in this paper we use the original CT image segmentation to experiment. According to a large number of experiments, analysis of lung image segmentation problems, provide direction for further research and valuable experience.
引文
1 J. P. Ko, D. P. Naidich. Lung Nodule Detection and Characterization With Multislice CT. Radiol Clin North Am, 2003,41(3):575-597
2 C. Xu, J. L. Prince. Shapes And Gradient Vector Flow. Transactions On Image Processing, 2004,23(2):181-194
3 Tangwei Liu, Huiyu Zhou, Faquan Lin, et al. Improving Image Segmentation by Gradient Vector Flow and Mean Shift. Pattern Recognition Letters. 2008,29(3):90-95
4 D. Adalsteinsson, J. A. Sethian. The Fast Cconstruction of Extension Velocities in Level Set Methods . Journal of Computational Physics, 1999,148(1):2-22
5魏颖,徐心和,贾同,等.基于优化水平集方法的CT图像肺结节检测算法.系统仿真学报, 2006,z2:909-911,915
6 M. Kass, A. Witkin, D. Terzopoulous. Snake:active Contour modes. International Journal of Computer Vision, 1978,1(4):321-331
7周则明,王洪元,尤建洁,等.基于改进快速活动轮廓模型的左心室核磁共振图像分割.计算机研究与发展, 2004,41(1):136-141
8 Jia Li, Xiaojun Jin. Edge Detection Basesd on Decision-Level Information Fusion and Its Application in Hybrid Image Filtering Proceedings. International Conference on Image Processing, 2004,23(4):251-254
9 J Tang. A Multi-direction GVF Snake for the Segmentation of Skin Cancer Images. Pattern Recognition, 2009,4(6):23-34
10 S. H. Goh, P. S. Nowinski. Medical Image Segmentation Using Feature-based GVF Snake. Engineering in Medicine and Biology Society, 2007,23(4):111-120
11 K. Chuang, H. Tzeng, S. Chen, et al. Fuzzy C-means Clustering with Spatial Information for Image Segmentation. Computerized Medical Imaging and Graphics, 2009,1(30):9-15
12 A. C. Liew, H. Yan, N. F. Law. Image Segmentation Based on Adaptive Clusterprototype Estimation. Transactionson Fuzzy Systems, 2005,13(4):444-453
13 A. B. Faruquzzaman, P. N. Rabbani, A. Jahidul, et al. Object Segmentation Based on Split and Merge algorithm IEEE Region 10 Annual International Conference, 2008,6(4):789-796
14 K. Ziaul, P. N. Rabbani, A. M. Ameer, et al. Pattern Based Object Segmentation using Split and Merge. IEEE International Conference on Fuzzy Systems, 2009,8(12):2166-2169
15 S. Poonquzhali, G. Ravindran, A Complete Automatic Region Growing Method for Segmentation of Masses on Ultrasound Images. ICBPE Proceedings of the 2006 International Conference on Biomedical and Pharmaceutical Engineering, 2006,4(2):88-92
16 Weihong, Cui, Zwqun, et al. An Improved Region Growing Algorithm for Image Segmentation, International Conference on Computer Science and Software Engineering, CSSE 2008,6(16):93-96,
17 MingJun Zhang, Yan Li, Jie Yang. Visual Image Segmentation of Mobile Robot Based on Sub-region Growing. Beijing Ligong Daxue Xuebao. 2009,7(29):608-613
18曲迎东,李荣德,袁晓光,等.两级Zernike矩算子的快速亚像素边缘检测.哈尔滨工业大学学报, 2009,5(12):136-141
19 E. B. Williamson, U. G. Bronas, D. R. Dengel. Automated Edge Detection Versus Manual Edge Measurement in Analysis of Brachial Artery Reactivity a Comparison Study. Ultrasound in Medicine and Biology, 2008,34(9):1499-1503
20李峰,徐诚,任国全,等.基于数学形态学的铁谱磨粒图像分割研究.南京理工大学学报(自然科学版), 2005,22(1):87-91
21 Kazemi. Farhad Mohamad. Akbarzadeh-T.Mohamad-R,et al. Fast image segmentation using C-means based Fuzzy Hopfield neural network. Canadian Conference on Electrical and Computer Engineering, 2008,5(34):1855-1859
22赵于前.基于数学形态学的医学图像处理理论与方法研究.中南大学, 2006,4(8):1232-1236
23 V. Caselles, R. Kimmel, G. sapiro. Geodesic Active Contoure. International Journal of Computer Vision,1997,22(1):61-79
24 T. F. Chan, L. A. Vase. Active Contours without Edges. Transactions on Image Processing, 2001,10(2):266-277
25 Dong.Guo,Xie.Ming, Color clustering and learning for image segmentation based on neural networks, IEEE Transactions on Neural Networks, 2005,4(16):925-936
26 S. Liu, J. Li. Automatic Medical Image Segmentation Using Gradient and Intensity Combined Level Set Method. Annual International Conference, 2006:1223-1228
27 Z. Dokur. A Unified Framework for Image Compression and Segmentation by Using an Incremental Neural Network. Expert Systems with Applications, 2008,4(5):101-105
28孟琭,赵宏,贾同,等.基于胸部CT影像的肺部功能评估.第十四届全国图象图形学学术会议论文集, 2009,2(10):78-81
29 S. Ukil, J. M. Reinhardt. Smoothing Lung Segmentation Surfaces In Threedimensional X-ray CT Images Using Anatomic Guidance. Acad Radiol, 2005,12(2):1502-1511
30 S. K. Pal, R. A. King, A. A. Hashim. Automatic Gray Level Thresholding though Index of Fuzziness and Entropy. Pattern Rceognition Letters, 1983,1(3):141-146
31杜晓晨,刘建平.改进的模糊阈值图像分割方法.光电工程, 2005,32(10):51-53,57
32 D. Y. Kim, J. H. Kim, S. M. Noh, et al. Pulmonary Nodule Detection Using Chest CT Images. Acta Radiol, 2003,44(16):252-257
33 J. M. Goo, J. W. Lee, H. J. Lee, et al. Automated Lung Nodule Detection At Low-dose CT: Preliminary Experience. Korean J Radiol, 2003,4(10):211-216
34 C. T. Chen, A. V. Clough. Fast Pulmonary Contour Extraction in X-ray CT Images: A Methodology and Quality Assessment. Physiology and Function from Multidimensional Images, 2001,43(21):216-224
35 G. Camara, I. A. Reis, L. S. Bins G. M. Espindola. Parameter Selection for Region-Growing Image Segmentation Algorithms Using Spatial. International Journal of Remote Sensing, 2006,16(2):1008-1011
36 Y. Lu, J. Miao, L. Duan, Y. Qiao, et al. A New Approach to Image Segmentation Based on Simplified Region Growing. Applied Mathematics and Computation, 2008,2(12):456-459
37 J. P. Ko, M. Betke. C. T. Chest: Automated Nodule Detection and Assessment of Change over Time. Radiology, 2001,2(18):267-273
38 K. Kanazawa, Y. Kawata, N. Niki, et al. Computer-aided Diagnosis for Pulmonary Nodules Based on Helical CT Images. Comput Med Imaging Graphics, 1998,2(2):157-167
39 M. N. Gurcan, B. Sahiner, N. Petrick, et al. Lung Nodule Detection on Thoracic Computed Tomography Images:Preliminary Evaluation of a Computer-aided Diagnosis System. Med Phys, 2002,29(18):2552-2558
40 Tangwei Liu, Huiyu zhou, Faquan Lin, Yusheng Pang, Ji Wu. Improving Image Segmentation by Gradient Vector Flow and Mean Shift. Pattern Rceognition Letters, 2008,(29):90-95
41 K. T. Bae, J. S. Kim, Y. H. Na, et al. Pulmonary Nodules: Automated Detection on CT Images with Morphologic Matching Algorithm Preliminary Results. Radiology, 2005,2(3):286-294
42 G. D. Rubin, J. Lyo, D. S. Paik, et al. Pulmonary Nodules in MDCT Scans. Impact of Computer-aided Detection, 2005,23(5):274-283
43林开颜,吴军辉,徐立鸿.彩色图像分割方法综述.中国图象图形学报, 2005,10(1):1-10
44 I. Sluimer, M. Prokop, B. Ginneken. Toward Automated Segmentation of the Pathological Lung in CT. Transactions on Medical Imaging, 2005,24(8):1025-1038
45喻忠全,张建州.基于肋骨信息的CT图像肺区疑似粘连肿瘤检测. Computer Engineer and Applications, 2008,44(3):202-204
46 M. S. Charmi, S. Derrode, F. Ghorbel. Fourier-basedgeometric Shape Prior for Snakes. Pattern Recognition Letters, 2008,29(5):897-904
47 J. Cheng, R. Xue, W. Lu, R. Jia. Segmentation of Medical Images with Canny Operator and GVF Snake Model. Intelligent Control and Automation, 2008:234-241
48张红颖,张加万,孙济洲,等.基于层次B样条的医学图像弹性配准方法.天津大学学报, 2007,40(1):35-40
49黄文明.曲线拟合的模糊医学图像分割算法.计算机工程与应用, 2009,45(18):194-197
50 K. Sun, Y. Yang, L. Ye, Q. Zhang. Image Restoration Using Piecewise Iterative Curve Fitting and Texture Synthesis. Proceedings of the 4th International Conference , 2008:890-899
51 M. Kakar, D. R. Olsen. Automatic Segmentation and Recognition of Lungs and Lesion from CT Scans of Thorax. Computerized Medical Imaging and Graphics, 2009,33(1):72-82
2 C. Xu, J. L. Prince. Shapes And Gradient Vector Flow. Transactions On Image Processing, 2004,23(2):181-194
3 Tangwei Liu, Huiyu Zhou, Faquan Lin, et al. Improving Image Segmentation by Gradient Vector Flow and Mean Shift. Pattern Recognition Letters. 2008,29(3):90-95
4 D. Adalsteinsson, J. A. Sethian. The Fast Cconstruction of Extension Velocities in Level Set Methods . Journal of Computational Physics, 1999,148(1):2-22
5魏颖,徐心和,贾同,等.基于优化水平集方法的CT图像肺结节检测算法.系统仿真学报, 2006,z2:909-911,915
6 M. Kass, A. Witkin, D. Terzopoulous. Snake:active Contour modes. International Journal of Computer Vision, 1978,1(4):321-331
7周则明,王洪元,尤建洁,等.基于改进快速活动轮廓模型的左心室核磁共振图像分割.计算机研究与发展, 2004,41(1):136-141
8 Jia Li, Xiaojun Jin. Edge Detection Basesd on Decision-Level Information Fusion and Its Application in Hybrid Image Filtering Proceedings. International Conference on Image Processing, 2004,23(4):251-254
9 J Tang. A Multi-direction GVF Snake for the Segmentation of Skin Cancer Images. Pattern Recognition, 2009,4(6):23-34
10 S. H. Goh, P. S. Nowinski. Medical Image Segmentation Using Feature-based GVF Snake. Engineering in Medicine and Biology Society, 2007,23(4):111-120
11 K. Chuang, H. Tzeng, S. Chen, et al. Fuzzy C-means Clustering with Spatial Information for Image Segmentation. Computerized Medical Imaging and Graphics, 2009,1(30):9-15
12 A. C. Liew, H. Yan, N. F. Law. Image Segmentation Based on Adaptive Clusterprototype Estimation. Transactionson Fuzzy Systems, 2005,13(4):444-453
13 A. B. Faruquzzaman, P. N. Rabbani, A. Jahidul, et al. Object Segmentation Based on Split and Merge algorithm IEEE Region 10 Annual International Conference, 2008,6(4):789-796
14 K. Ziaul, P. N. Rabbani, A. M. Ameer, et al. Pattern Based Object Segmentation using Split and Merge. IEEE International Conference on Fuzzy Systems, 2009,8(12):2166-2169
15 S. Poonquzhali, G. Ravindran, A Complete Automatic Region Growing Method for Segmentation of Masses on Ultrasound Images. ICBPE Proceedings of the 2006 International Conference on Biomedical and Pharmaceutical Engineering, 2006,4(2):88-92
16 Weihong, Cui, Zwqun, et al. An Improved Region Growing Algorithm for Image Segmentation, International Conference on Computer Science and Software Engineering, CSSE 2008,6(16):93-96,
17 MingJun Zhang, Yan Li, Jie Yang. Visual Image Segmentation of Mobile Robot Based on Sub-region Growing. Beijing Ligong Daxue Xuebao. 2009,7(29):608-613
18曲迎东,李荣德,袁晓光,等.两级Zernike矩算子的快速亚像素边缘检测.哈尔滨工业大学学报, 2009,5(12):136-141
19 E. B. Williamson, U. G. Bronas, D. R. Dengel. Automated Edge Detection Versus Manual Edge Measurement in Analysis of Brachial Artery Reactivity a Comparison Study. Ultrasound in Medicine and Biology, 2008,34(9):1499-1503
20李峰,徐诚,任国全,等.基于数学形态学的铁谱磨粒图像分割研究.南京理工大学学报(自然科学版), 2005,22(1):87-91
21 Kazemi. Farhad Mohamad. Akbarzadeh-T.Mohamad-R,et al. Fast image segmentation using C-means based Fuzzy Hopfield neural network. Canadian Conference on Electrical and Computer Engineering, 2008,5(34):1855-1859
22赵于前.基于数学形态学的医学图像处理理论与方法研究.中南大学, 2006,4(8):1232-1236
23 V. Caselles, R. Kimmel, G. sapiro. Geodesic Active Contoure. International Journal of Computer Vision,1997,22(1):61-79
24 T. F. Chan, L. A. Vase. Active Contours without Edges. Transactions on Image Processing, 2001,10(2):266-277
25 Dong.Guo,Xie.Ming, Color clustering and learning for image segmentation based on neural networks, IEEE Transactions on Neural Networks, 2005,4(16):925-936
26 S. Liu, J. Li. Automatic Medical Image Segmentation Using Gradient and Intensity Combined Level Set Method. Annual International Conference, 2006:1223-1228
27 Z. Dokur. A Unified Framework for Image Compression and Segmentation by Using an Incremental Neural Network. Expert Systems with Applications, 2008,4(5):101-105
28孟琭,赵宏,贾同,等.基于胸部CT影像的肺部功能评估.第十四届全国图象图形学学术会议论文集, 2009,2(10):78-81
29 S. Ukil, J. M. Reinhardt. Smoothing Lung Segmentation Surfaces In Threedimensional X-ray CT Images Using Anatomic Guidance. Acad Radiol, 2005,12(2):1502-1511
30 S. K. Pal, R. A. King, A. A. Hashim. Automatic Gray Level Thresholding though Index of Fuzziness and Entropy. Pattern Rceognition Letters, 1983,1(3):141-146
31杜晓晨,刘建平.改进的模糊阈值图像分割方法.光电工程, 2005,32(10):51-53,57
32 D. Y. Kim, J. H. Kim, S. M. Noh, et al. Pulmonary Nodule Detection Using Chest CT Images. Acta Radiol, 2003,44(16):252-257
33 J. M. Goo, J. W. Lee, H. J. Lee, et al. Automated Lung Nodule Detection At Low-dose CT: Preliminary Experience. Korean J Radiol, 2003,4(10):211-216
34 C. T. Chen, A. V. Clough. Fast Pulmonary Contour Extraction in X-ray CT Images: A Methodology and Quality Assessment. Physiology and Function from Multidimensional Images, 2001,43(21):216-224
35 G. Camara, I. A. Reis, L. S. Bins G. M. Espindola. Parameter Selection for Region-Growing Image Segmentation Algorithms Using Spatial. International Journal of Remote Sensing, 2006,16(2):1008-1011
36 Y. Lu, J. Miao, L. Duan, Y. Qiao, et al. A New Approach to Image Segmentation Based on Simplified Region Growing. Applied Mathematics and Computation, 2008,2(12):456-459
37 J. P. Ko, M. Betke. C. T. Chest: Automated Nodule Detection and Assessment of Change over Time. Radiology, 2001,2(18):267-273
38 K. Kanazawa, Y. Kawata, N. Niki, et al. Computer-aided Diagnosis for Pulmonary Nodules Based on Helical CT Images. Comput Med Imaging Graphics, 1998,2(2):157-167
39 M. N. Gurcan, B. Sahiner, N. Petrick, et al. Lung Nodule Detection on Thoracic Computed Tomography Images:Preliminary Evaluation of a Computer-aided Diagnosis System. Med Phys, 2002,29(18):2552-2558
40 Tangwei Liu, Huiyu zhou, Faquan Lin, Yusheng Pang, Ji Wu. Improving Image Segmentation by Gradient Vector Flow and Mean Shift. Pattern Rceognition Letters, 2008,(29):90-95
41 K. T. Bae, J. S. Kim, Y. H. Na, et al. Pulmonary Nodules: Automated Detection on CT Images with Morphologic Matching Algorithm Preliminary Results. Radiology, 2005,2(3):286-294
42 G. D. Rubin, J. Lyo, D. S. Paik, et al. Pulmonary Nodules in MDCT Scans. Impact of Computer-aided Detection, 2005,23(5):274-283
43林开颜,吴军辉,徐立鸿.彩色图像分割方法综述.中国图象图形学报, 2005,10(1):1-10
44 I. Sluimer, M. Prokop, B. Ginneken. Toward Automated Segmentation of the Pathological Lung in CT. Transactions on Medical Imaging, 2005,24(8):1025-1038
45喻忠全,张建州.基于肋骨信息的CT图像肺区疑似粘连肿瘤检测. Computer Engineer and Applications, 2008,44(3):202-204
46 M. S. Charmi, S. Derrode, F. Ghorbel. Fourier-basedgeometric Shape Prior for Snakes. Pattern Recognition Letters, 2008,29(5):897-904
47 J. Cheng, R. Xue, W. Lu, R. Jia. Segmentation of Medical Images with Canny Operator and GVF Snake Model. Intelligent Control and Automation, 2008:234-241
48张红颖,张加万,孙济洲,等.基于层次B样条的医学图像弹性配准方法.天津大学学报, 2007,40(1):35-40
49黄文明.曲线拟合的模糊医学图像分割算法.计算机工程与应用, 2009,45(18):194-197
50 K. Sun, Y. Yang, L. Ye, Q. Zhang. Image Restoration Using Piecewise Iterative Curve Fitting and Texture Synthesis. Proceedings of the 4th International Conference , 2008:890-899
51 M. Kakar, D. R. Olsen. Automatic Segmentation and Recognition of Lungs and Lesion from CT Scans of Thorax. Computerized Medical Imaging and Graphics, 2009,33(1):72-82
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |