Detection of carotid intima and media thicknesses based on ultrasound B-mode images clustered with Gaussian mixture model_Journal of Biomedical Engineering

Authors：

QI Guiling ¹ ,  HE Bingbing ¹ , ZHANG Yufeng ¹ , LI Zhiyao ² , MO Hong ¹ , CHENG Jie ¹

1. The Department of Electronic Engineering, School of Information, Yunnan University, Kunming 650091, P.R.China;
2. The Department of Ultrasound, the Third Affiliated Hospital of Kunming Medical College, Kunming 650118, P.R.China;

Corresponding author：

HE Bingbing, Email: he_bing_bing123@126.com

Keywords：

ultrasound images; carotid artery; intimal and medial thickness; gaussian mixture model; clustering

DOI：

10.7507/1001-5515.201906027

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

In clinic, intima and media thickness are the main indicators for evaluating the development of atherosclerosis. At present, these indicators are measured by professional doctors manually marking the boundaries of the inner and media on B-mode images, which is complicated, time-consuming and affected by many artificial factors. A grayscale threshold method based on Gaussian Mixture Model (GMM) clustering is therefore proposed to detect the intima and media thickness in carotid arteries from B-mode images in this paper. Firstly, the B-mode images are clustered based on the GMM, and the boundary between the intima and media of the vessel wall is then detected by the gray threshold method, and finally the thickness of the two is measured. Compared with the measurement technique using the gray threshold method directly, the clustering of B-mode images of carotid artery solves the problem of gray boundary blurring of inner and middle membrane, thereby improving the stability and detection accuracy of the gray threshold method. In the clinical trials of 120 healthy carotid arteries, means of 4 manual measurements obtained by two experts are used as reference values. Experimental results show that the normalized root mean square errors (NRMSEs) of the estimated intima and media thickness after GMM clustering were 0.104 7 ± 0.076 2 and 0.097 4 ± 0.068 3, respectively. Compared with the results of the direct gray threshold estimation, means of NRMSEs are reduced by 19.6% and 22.4%, respectively, which indicates that the proposed method has higher measurement accuracy. The standard deviations are reduced by 17.0% and 21.7%, respectively, which indicates that the proposed method has better stability. In summary, this method is helpful for early diagnosis and monitoring of vascular diseases, such as atherosclerosis.

Citation： QI Guiling, HE Bingbing, ZHANG Yufeng, LI Zhiyao, MO Hong, CHENG Jie. Detection of carotid intima and media thicknesses based on ultrasound B-mode images clustered with Gaussian mixture model. Journal of Biomedical Engineering, 2020, 37(6): 1080-1088, 1094. doi: 10.7507/1001-5515.201906027 Copy

1.	Roth G A, Johnson C, Abajobir A A, et al. Global, regional, and National burden of cardiovascular diseases for 10 causes, 1990 to 2015. J Am Coll Cardiol, 2017, 70(1): 1-25.
2.	Sanz J, Fayad Z A. Imaging of atherosclerotic cardiovascular disease. Nature, 2008, 451(7181): 953-957.
3.	Engelen L, Ferreira I, Stehouwer C D, et al. Reference intervals for common carotid intima-media thickness measured with echotracking: relation with risk factors. Eur Heart J, 2013, 34(30): 2368-2380.
4.	王怡, 段云友, 张莉, 等. 颈动脉内中膜厚度及弹性定量指标对冠状动脉粥样硬化性心脏病诊断的预测价值. 中华医学超声杂志:电子版, 2013, 10(9): 39-43.
5.	Delgado V, Knuuti J, Plein S, et al. The year in cardiology 2017: imaging. Eur Heart J, 2018, 39(4): 275-285.
6.	Li Q, Zhang W, Guan X, et al. An improved approach for accurate and efficient measurement of common carotid artery intima-media thickness in ultrasound images. Biomed Res Int, 2014: 740328.
7.	Xu X, Zhou Y, Cheng X, et al. Ultrasound intima-media segmentation using Hough transform and dual snake model. Comput Med Imaging Graph, 2012, 36(3): 248-258.
8.	Petroudi S, Loizou C, Pantziaris M, et al. Segmentation of the common carotid intima-media complex in ultrasound images using active contours. IEEE Trans Biomed Eng, 2012, 59(11): 3060-3069.
9.	Sumathi K, Mahesh V, Ramakrishnan S. Analysis of intima media thickness in ultrasound carotid artery images using level set segmentation without re-initialization//2014 International Conference on Informatics, Electronics & Vision (ICIEV), Dhaka, Bangladesh: IEEE, 2014: 1-4.
10.	Li H, Zhang S, Ma R, et al. Ultrasound intima-media thickness measurement of the carotid artery using ant colony optimization combined with a curvelet-based orientation-selective filter. Med Phys, 2016, 43(4): 1795-1807.
11.	Menchón-Lara R M, Sancho-Gómez J L, Bueno-Crespo A. Early-stage atherosclerosis detection using deep learning over carotid ultrasound images. Appl Soft Comput, 2016, 49: 616-628.
12.	Menchón-Lara R M, Bastida-Jumilla M C, Morales-Sánchez J, et al. Automatic detection of the intima-media thickness in ultrasound images of the common carotid artery using neural networks. Med Biol Eng Comput, 2014, 52(2): 169-181.
13.	刘一学, 李锵, 关欣, 等. 基于支持向量机的颈动脉超声图像内中膜厚度测量. 中国医学物理学杂志, 2016, 33(5): 451-455.
14.	孙萍, 李锵, 关欣, 等. 基于深度学习的颈动脉超声图像内中膜厚度测量. 国际生物医学工程杂志, 2016, 39(5): 257-262.
15.	Savaş S, Topaloğlu N, Kazcı Ö, et al. Classification of carotid artery intima media thickness ultrasound images with deep learning. J Med Syst, 2019, 43(8): 273.
16.	Xiao Lu, Li Qiang, Bai Yu, et al. Automated measurement method of common carotid artery intima-media thickness in ultrasound image based on Markov random field models. J Med Biol Eng, 2015, 35(5): 651-660.
17.	陈欣, 郝军, 李彦青. 颈动脉内膜增厚检测对防治颅内动脉硬化的临床意义. 当代医学, 2015, 21(36): 36-37.
18.	Subbotin V M. Neovascularization of coronary tunica intima (DIT) is the cause of coronary atherosclerosis. Lipoproteins invade coronary intima via neovascularization from adventitial vasa vasorum, but not from the arterial lumen: a hypothesis. Theor Biol Med Model, 2012, 9(11): 11.
19.	Bae J H, Kim W S, Rihal C S, et al. Individual measurement and significance of carotid intima, media, and intima-media thickness by B-mode ultrasonographic image processing. Arterioscler Thromb Vasc Biol, 2006, 26(10): 2380-2385.
20.	Macioch J E, Katsamakis C D, Robin J, et al. Effect of contrast enhancement on measurement of carotid artery intimal medial thickness. Vasc Med, 2004, 9(1): 7-12.
21.	Loizou C P, Pattichis C S, Nicolaides A, et al. Manual and automated media and intima thickness measurements of the common carotid artery. IEEE Trans Ultrason Ferroelectr Freq Control, 2009, 56(5): 983-994.
22.	袁绍锋, 杨丰, 徐琳, 等. 深度全卷积网络的IVUS图像内膜与中—外膜边界检测. 中国图象图形学报, 2018, 23(9): 1335-1348.
23.	Abdoli M, Sarikhani H, Ghanbari M, et al. Gaussian mixture model-based contrast enhancement. IET Image Process, 2015, 9(7): 569-577.
24.	吴杰, 朱家明, 张辉. 灰度不均的弱边界血管图像分割方法. 计算机应用, 2016, 36(S1): 154-156.
25.	Jakeman E, Tough R A. Generalized K distribution: a statistical model for weak scattering. J Opt Soc Amer, 1987, 4(9): 1764-1772.
26.	Insana M F, Wagner R F, Garra B S, et al. Analysis of ultrasound image texture via generalized Rician statistics. Opt Eng, 1986, 25(6): 743-748.
27.	Saha R K, Kolios M C. Effects of cell spatial organization and size distribution on ultrasound backscattering. IEEE Trans Ultrason Ferroelectr Freq Control, 2011, 58(10): 2118-2131.
28.	Mohana Shankar P. A general statistical model for ultrasonic backscattering from tissues. IEEE Trans Ultrason Ferroelectr Freq Control, 2000, 47(3): 727-736.
29.	柴五一, 杨丰, 袁绍锋, 等. 血管内超声斑点的概率模型建立及应用. 南方医科大学学报, 2017, 37(11): 1476-1483.
30.	Moon T K. The expectation-maximization algorithm. IEEE Signal Processing Mag, 1996, 13(6): 47-60.
31.	戴涛, 骆科东, 李春平. 个体行为数据聚类的双重混合高斯模型算法. 计算机应用, 2004, 24(8): 44-46, 49.
32.	Cadez I, Heckerman D, Meek C, et al. Visualization of navigation patterns on a web site using model-based clustering//Proceedings of the sixth ACM SIGKDD international conference on Knowledge discovery and data mining.Boston: KDD, 2000: 280-284.
33.	Molinari F, Zeng G, Suri J S. A state of the art review on intima-media thickness (IMT) measurement and wall segmentation techniques for carotid ultrasound. Comput Methods Programs Biomed, 2010, 100(3): 201-221.
34.	Basij M, Moallem P, Yazdchi M, et al. Automatic shadow detection in intra vascular ultrasound images using adaptive thresholding//2012 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Seoul: IEEE,, 2012: 2173-2177.
35.	Vartiainen J, Lehtomaki J J, Saarnisaari H. Double-threshold based narrowband signal extraction//2005 IEEE 61st Vehicular Technology Conference, Sweden: IEEE, 2005, 2: 1288-1292.

1. Roth G A, Johnson C, Abajobir A A, et al. Global, regional, and National burden of cardiovascular diseases for 10 causes, 1990 to 2015. J Am Coll Cardiol, 2017, 70(1): 1-25.
2. Sanz J, Fayad Z A. Imaging of atherosclerotic cardiovascular disease. Nature, 2008, 451(7181): 953-957.
3. Engelen L, Ferreira I, Stehouwer C D, et al. Reference intervals for common carotid intima-media thickness measured with echotracking: relation with risk factors. Eur Heart J, 2013, 34(30): 2368-2380.
4. 王怡, 段云友, 张莉, 等. 颈动脉内中膜厚度及弹性定量指标对冠状动脉粥样硬化性心脏病诊断的预测价值. 中华医学超声杂志:电子版, 2013, 10(9): 39-43.
5. Delgado V, Knuuti J, Plein S, et al. The year in cardiology 2017: imaging. Eur Heart J, 2018, 39(4): 275-285.
6. Li Q, Zhang W, Guan X, et al. An improved approach for accurate and efficient measurement of common carotid artery intima-media thickness in ultrasound images. Biomed Res Int, 2014: 740328.
7. Xu X, Zhou Y, Cheng X, et al. Ultrasound intima-media segmentation using Hough transform and dual snake model. Comput Med Imaging Graph, 2012, 36(3): 248-258.
8. Petroudi S, Loizou C, Pantziaris M, et al. Segmentation of the common carotid intima-media complex in ultrasound images using active contours. IEEE Trans Biomed Eng, 2012, 59(11): 3060-3069.
9. Sumathi K, Mahesh V, Ramakrishnan S. Analysis of intima media thickness in ultrasound carotid artery images using level set segmentation without re-initialization//2014 International Conference on Informatics, Electronics & Vision (ICIEV), Dhaka, Bangladesh: IEEE, 2014: 1-4.
10. Li H, Zhang S, Ma R, et al. Ultrasound intima-media thickness measurement of the carotid artery using ant colony optimization combined with a curvelet-based orientation-selective filter. Med Phys, 2016, 43(4): 1795-1807.
11. Menchón-Lara R M, Sancho-Gómez J L, Bueno-Crespo A. Early-stage atherosclerosis detection using deep learning over carotid ultrasound images. Appl Soft Comput, 2016, 49: 616-628.
12. Menchón-Lara R M, Bastida-Jumilla M C, Morales-Sánchez J, et al. Automatic detection of the intima-media thickness in ultrasound images of the common carotid artery using neural networks. Med Biol Eng Comput, 2014, 52(2): 169-181.
13. 刘一学, 李锵, 关欣, 等. 基于支持向量机的颈动脉超声图像内中膜厚度测量. 中国医学物理学杂志, 2016, 33(5): 451-455.
14. 孙萍, 李锵, 关欣, 等. 基于深度学习的颈动脉超声图像内中膜厚度测量. 国际生物医学工程杂志, 2016, 39(5): 257-262.
15. Savaş S, Topaloğlu N, Kazcı Ö, et al. Classification of carotid artery intima media thickness ultrasound images with deep learning. J Med Syst, 2019, 43(8): 273.
16. Xiao Lu, Li Qiang, Bai Yu, et al. Automated measurement method of common carotid artery intima-media thickness in ultrasound image based on Markov random field models. J Med Biol Eng, 2015, 35(5): 651-660.
17. 陈欣, 郝军, 李彦青. 颈动脉内膜增厚检测对防治颅内动脉硬化的临床意义. 当代医学, 2015, 21(36): 36-37.
18. Subbotin V M. Neovascularization of coronary tunica intima (DIT) is the cause of coronary atherosclerosis. Lipoproteins invade coronary intima via neovascularization from adventitial vasa vasorum, but not from the arterial lumen: a hypothesis. Theor Biol Med Model, 2012, 9(11): 11.
19. Bae J H, Kim W S, Rihal C S, et al. Individual measurement and significance of carotid intima, media, and intima-media thickness by B-mode ultrasonographic image processing. Arterioscler Thromb Vasc Biol, 2006, 26(10): 2380-2385.
20. Macioch J E, Katsamakis C D, Robin J, et al. Effect of contrast enhancement on measurement of carotid artery intimal medial thickness. Vasc Med, 2004, 9(1): 7-12.
21. Loizou C P, Pattichis C S, Nicolaides A, et al. Manual and automated media and intima thickness measurements of the common carotid artery. IEEE Trans Ultrason Ferroelectr Freq Control, 2009, 56(5): 983-994.
22. 袁绍锋, 杨丰, 徐琳, 等. 深度全卷积网络的IVUS图像内膜与中—外膜边界检测. 中国图象图形学报, 2018, 23(9): 1335-1348.
23. Abdoli M, Sarikhani H, Ghanbari M, et al. Gaussian mixture model-based contrast enhancement. IET Image Process, 2015, 9(7): 569-577.
24. 吴杰, 朱家明, 张辉. 灰度不均的弱边界血管图像分割方法. 计算机应用, 2016, 36(S1): 154-156.
25. Jakeman E, Tough R A. Generalized K distribution: a statistical model for weak scattering. J Opt Soc Amer, 1987, 4(9): 1764-1772.
26. Insana M F, Wagner R F, Garra B S, et al. Analysis of ultrasound image texture via generalized Rician statistics. Opt Eng, 1986, 25(6): 743-748.
27. Saha R K, Kolios M C. Effects of cell spatial organization and size distribution on ultrasound backscattering. IEEE Trans Ultrason Ferroelectr Freq Control, 2011, 58(10): 2118-2131.
28. Mohana Shankar P. A general statistical model for ultrasonic backscattering from tissues. IEEE Trans Ultrason Ferroelectr Freq Control, 2000, 47(3): 727-736.
29. 柴五一, 杨丰, 袁绍锋, 等. 血管内超声斑点的概率模型建立及应用. 南方医科大学学报, 2017, 37(11): 1476-1483.
30. Moon T K. The expectation-maximization algorithm. IEEE Signal Processing Mag, 1996, 13(6): 47-60.
31. 戴涛, 骆科东, 李春平. 个体行为数据聚类的双重混合高斯模型算法. 计算机应用, 2004, 24(8): 44-46, 49.
32. Cadez I, Heckerman D, Meek C, et al. Visualization of navigation patterns on a web site using model-based clustering//Proceedings of the sixth ACM SIGKDD international conference on Knowledge discovery and data mining.Boston: KDD, 2000: 280-284.
33. Molinari F, Zeng G, Suri J S. A state of the art review on intima-media thickness (IMT) measurement and wall segmentation techniques for carotid ultrasound. Comput Methods Programs Biomed, 2010, 100(3): 201-221.
34. Basij M, Moallem P, Yazdchi M, et al. Automatic shadow detection in intra vascular ultrasound images using adaptive thresholding//2012 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Seoul: IEEE,, 2012: 2173-2177.
35. Vartiainen J, Lehtomaki J J, Saarnisaari H. Double-threshold based narrowband signal extraction//2005 IEEE 61st Vehicular Technology Conference, Sweden: IEEE, 2005, 2: 1288-1292.

Journal of Biomedical Engineering

Detection of carotid intima and media thicknesses based on ultrasound B-mode images clustered with Gaussian mixture model

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content