北京生物医学工程

基于超声心动图的二叶式主动脉瓣钙化病灶自动分割算法

Automatic segmentation of bicuspid aortic valve calcification algorithm based on echocardiography

作者：赵志浩乔爱科

单位：北京工业大学环境与生命学部（北京 100124）<br />智能化生理测量与临床转化北京市国际科研合作基地（北京 100124）<br />通信作者：乔爱科，教授。E-mail: qak@bjut.edu.cn

分类号：R318.04

出版年·卷·期（页码）：2023·42·1（21-26）

摘要：

目的提出一种基于超声心动图(echocardiography, ECHO)的二叶式主动脉瓣钙化病灶(bicuspid aortic valve calcification, BAVC)自动分割算法，以提高BAVC识别效率。方法选取BAVC患者的ECHO，应用迭代均值滤波器、一二阶全变分和指定直方图均衡化算法对其进行降噪、灰度平衡化的图像预处理；根据钙化阈值特征，应用阈值滤波器、8邻域原理获取钙化病灶的初始轮廓，并根据ECHO中主动脉瓣的大小和位置特征，自适应的选择初始轮廓作为初始种子区域；根据钙化阈值、迭代终止条件、自适应调整迭代次数等相关参数，自动分割BAVC区域。将自动分割的结果与手动分割结果进行比较，并分析ECHO中不同的椒盐噪声(salt and pepper noise, SPN)及斑点噪声(speckle noise, SN)对分割结果的影响。结果所建立的自动分割算法的平均处理时间、平均迭代次数分别达到了4.747s、31，像素精确度(pixel accuracy,PA)、交并比(intersection-over-union,IOU)、Dice系数(Dice coeffcient，DC)分别达到了0.9615、0.9559、0.9773。与MorphGAC半自动算法相比，自动分割算法的平均处理时间提高了45.61%，平均PA、IoU、DC分别提高了13.25%、11.02%、7.69%。结论该算法有效地分割出ECHO中的BAVC，并解决人工参与分割个性差异大、识别效率低且易受到噪声干扰的问题。

Objective To propose an automatic segmentation algorithm of bicuspid aortic valve calcification (BAVC) based on echocardiography (ECHO) ，and to improve the efficiency of BACC identification. Methods The ECHO of BAVC patients was selected, the iterative mean filter and first- and second-order total variation and the specified histogram equalization algorithm was applied to perform image preprocessing of noise reduction and gray balance; the threshold filter and the principle of 8 neighborhood were used to obtain the initial contour of the calcification lesion according to the calcification threshold characteristics, and the initial contour was adaptively selected as the initial seed area according to the size and position characteristics of the aortic valve in ECHO; according to the calcification threshold and iteration termination conditions, adaptive adjustment of related parameters such as the number of iterations, and automatic segmentation of BAVC regions. The results of automatic segmentation were compared with the results of manual segmentation, and the influence of different salt and pepper noise (SPN) and speckle noise (SN) in ECHO on the segmentation results was analyzed. Results The average processing time and the average number of iterations of the established automatic segmentation algorithm reached 4.747s and 31 respectively, and the average pixel accuracy (PA), intersection-over-union (IoU), and Dice coefficient (DC) reached 0.9615, 0.9559, and 0.9773 respectively. Compared with MorphGAC semi-automatic algorithms, the average processing time of the automatic segmentation algorithm had increased by 45.61%, and the average PA, IoU, and DC had increased by 13.25%, 11.02%, and 7.69% respectively. Conclusions The established algorithm can effectively segment the BAVC in ECHO, and solve the problems of large individual differences, low recognition efficiency, and susceptibility to noise interference in manual segmentation.

参考文献：

[1] 李宜嘉，杨娅.主动脉瓣狭窄 ESC 指南解读和超声心动图评估[J]. 心血管外科杂志, 2013, 2(1): 11-16.
[2] 袁艺, 黄兰珍, 林小勇. 超声心动图诊断主动脉狭窄的应用价值分析[J]. 现代医用影像学, 2019, 28(11): 2501-2502.
[3] Baumgartner H, Hung J, Bermejo J, et al. Recommendations on the echocardiographic assessment of aortic valve stenosis: a focused update from the european association of cardiovascular imaging and the american society of echocardiography[J]. Journal of The American Society of Echocardiography, 2017，30:372-392.
[4] 赵睿, 何逸尧, 许宇辰, 等. 超声心动图在二叶式主动脉瓣及其并发症诊治中的应用价值[J]. 中华诊断学电子杂志, 2019, 7(2): 129-133.
Zhao R，He YY，Xu YC，et al. The application value of echocardiography in diagnosis and treatment of bicuspid aortic valve and its major complications[J]. Chinese Journal of Diagnostics(Electronic Edition), 2019, 7(2): 129-133.
[5] Tuncay V, Prakken N, van Ooijen PMA, et al. Semiautomatic, quantitative measurement of aortic valve area using CTA: validation and comparison with transthoracic echocardiography[J]. Biomed Research International, 2015, 10(1155): 648283.
[6] Heinonen T, Dastidar P, Eskola H, et al. Applicability of semi-automatic segmentation for volumetric analysis of brain lesions[J]. Journal of Medical Engineering & Technology, 1998, 22(4):173.
[7] Zhou Z, Wu W, Wu S. Semi-automatic breast ultrasound image segmentation based on mean shif and graph cuts[J]. Ultrasonic Imaging, 2014, 36(4):256-276.
[8] Peng J, Shen J, Li X. High-order energies for stereo segmentation[J]. IEEE Transactions on Cybernetics, 2016,46(7): 1616-1627.?
[9] Xian M, Zhang Y, Cheng HD, et al. Neutro-connectedness cut[J]. IEEE Transactions on Image Processing, 2016, 25(10): 4691-4703.
[10] Raymond H, Chung W, and Mila N. Salt-and-pepper noise removal by median-type noise detectors and detail-preserving regularization[J]. In IEEE Transactions on Image Processing, 2005, 14(10): 1479-1485.
[11] Wells P, Halliwell M. Speckle in ultrasonic imaging[J]. Ultrasonics, 1981, 19(5): 225-229.
[12] Erkan U, Thanh DNH, Hieu LM, et al. An iterative mean filter for image denoising [J]. IEEE Access, 2019, 7:167847-167859.
[13] Wang S, Huang TZ, Zhao XL, et al. Speckle noise removal in ultrasound images by first- and second-order total variation[J]. Numerical Algorithms, 2018,78:513-533.
[14] Reza AM. Realization of the contrast limited adaptive histogram equalization (CLAHE) for real-time image enhancement[J]. Journal of VLSI Signal Processing Systems for Signal, Image and Video Technology, 2004, 38(1): 35-44.
[15] Suzuki S, Abe K. Topological structural analysis of digitized binary images by border following[J]. Computer Vision, Graphics, and Image Processing,1985,30 (1): 32-46.
[16] Grossman W, Jones D, McLaurin LP. Wall stress and patterns of hypertrophy in the human left ventricle[J]. Journal Of Clinical Investigation, 1975, 56(1): 56–64.
[17] Marquez-Neila P , Baumela L , Alvarez L . A morphological approach to curvature-based evolution of curves and surfaces[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2013, 36(1):2-17..
[18] Rafael C, Richard E, Steven L, et al. 数字图像处理的MATLAB实现 [M]. 2版.阮秋琪译. 北京: 清华大学出版社, 2013.
[19] Pan Y, Birdwell JD, Djouadi SM. Efficient implementation of the chan-vese models without solving PDEs[M]. Berlin ：Springer International Publishing, 2014：350-354.
[20] Wang Z, Wang E, Zhu Y. Image segmentation evaluation: a survey of methods[J]. Artifcial Intelligence Review, 2020, 53:5637–5674.
[21] Zhou W, Alan C, Hamid R, et al. Image quality assessment: from error visibility to structural similarity[J]. In IEEE Transactions on Image Processing, 2004, 13(4): 600-612.
[22] 邵蒙恩, 严加勇, 崔崤峣, 等. 基于改进的CV?RSF模型的甲状腺结节超声图像自适应分割算法[J]. 北京生物医学工程, 2020, 39(3): 251-256.
? Shao ME，Yan JY，Cui XY，et al. Adaptive segmentation algorithm for thyroid nodules based on improved CV-RSF model[J]. Beijing Biomedical Engineering, 2020, 39(03): 251-256.
[23] 王桃, 孙运慧. 基于自适应机制的医学超声图像分割方法[J]. 电子质量, 2018 (3):38-40.
? Wang T，Sun YH. Medical ultrasound image segmentation based on adaptive mechanism[J]. Electronics Quality, 2018 (3):38-40.
[24] 黄建波, 倪东, 汪天富. 基于先验概率和统计形状的前列腺超声图像自动分割方法[J]. 生物医学工程研究, 2015, 34(1): 15-19.
Huang JB，Ni D，Wang TF. Automatic segmentation method based on probability priors and statistical shape for prostate TRUS images[J]. Journal of Biomedical Engineering Research, 2015, 34(1): 15-19.

服务与反馈：

【文章下载】【加入收藏】

提示：您还未登录，请登录！点此登录