北京生物醫(yī)學(xué)工程

基于超聲心動(dòng)圖的二葉式主動(dòng)脈瓣鈣化病灶自動(dòng)分割算法

Automatic segmentation of bicuspid aortic valve calcification algorithm based on echocardiography

作者：趙志浩喬愛(ài)科

單位：北京工業(yè)大學(xué)環(huán)境與生命學(xué)部（北京 100124）<br />智能化生理測(cè)量與臨床轉(zhuǎn)化北京市國(guó)際科研合作基地（北京 100124）<br />通信作者：?jiǎn)虗?ài)科，教授。E-mail: [email protected]

關(guān)鍵詞：超聲心動(dòng)圖；二葉式主動(dòng)脈瓣鈣化；圖像處理；圖像分割

分類(lèi)號(hào)：R318.04

出版年·卷·期（頁(yè)碼）：2023·42·1（21-26）

摘要：

目的提出一種基于超聲心動(dòng)圖(echocardiography, ECHO)的二葉式主動(dòng)脈瓣鈣化病灶(bicuspid aortic valve calcification, BAVC)自動(dòng)分割算法，以提高BAVC識(shí)別效率。方法選取BAVC患者的ECHO，應(yīng)用迭代均值濾波器、一二階全變分和指定直方圖均衡化算法對(duì)其進(jìn)行降噪、灰度平衡化的圖像預(yù)處理；根據(jù)鈣化閾值特征，應(yīng)用閾值濾波器、8鄰域原理獲取鈣化病灶的初始輪廓，并根據(jù)ECHO中主動(dòng)脈瓣的大小和位置特征，自適應(yīng)的選擇初始輪廓作為初始種子區(qū)域；根據(jù)鈣化閾值、迭代終止條件、自適應(yīng)調(diào)整迭代次數(shù)等相關(guān)參數(shù)，自動(dòng)分割BAVC區(qū)域。將自動(dòng)分割的結(jié)果與手動(dòng)分割結(jié)果進(jìn)行比較，并分析ECHO中不同的椒鹽噪聲(salt and pepper noise, SPN)及斑點(diǎn)噪聲(speckle noise, SN)對(duì)分割結(jié)果的影響。結(jié)果所建立的自動(dòng)分割算法的平均處理時(shí)間、平均迭代次數(shù)分別達(dá)到了4.747s、31，像素精確度(pixel accuracy,PA)、交并比(intersection-over-union,IOU)、Dice系數(shù)(Dice coeffcient，DC)分別達(dá)到了0.9615、0.9559、0.9773。與MorphGAC半自動(dòng)算法相比，自動(dòng)分割算法的平均處理時(shí)間提高了45.61%，平均PA、IoU、DC分別提高了13.25%、11.02%、7.69%。結(jié)論該算法有效地分割出ECHO中的BAVC，并解決人工參與分割個(gè)性差異大、識(shí)別效率低且易受到噪聲干擾的問(wèn)題。

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.

參考文獻(xiàn)：

[1] 李宜嘉，楊婭.主動(dòng)脈瓣狹窄 ESC 指南解讀和超聲心動(dòng)圖評(píng)估[J]. 心血管外科雜志, 2013, 2(1): 11-16.
[2] 袁藝, 黃蘭珍, 林小勇. 超聲心動(dòng)圖診斷主動(dòng)脈狹窄的應(yīng)用價(jià)值分析[J]. 現(xiàn)代醫(yī)用影像學(xué), 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] 趙睿, 何逸堯, 許宇辰, 等. 超聲心動(dòng)圖在二葉式主動(dòng)脈瓣及其并發(fā)癥診治中的應(yīng)用價(jià)值[J]. 中華診斷學(xué)電子雜志, 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. 數(shù)字圖像處理的MATLAB實(shí)現(xiàn) [M]. 2版.阮秋琪譯. 北京: 清華大學(xué)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, 嚴(yán)加勇, 崔崤峣, 等. 基于改進(jìn)的CV?RSF模型的甲狀腺結(jié)節(jié)超聲圖像自適應(yīng)分割算法[J]. 北京生物醫(yī)學(xué)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, 孫運(yùn)慧. 基于自適應(yīng)機(jī)制的醫(yī)學(xué)超聲圖像分割方法[J]. 電子質(zhì)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] 黃建波, 倪東, 汪天富. 基于先驗(yàn)概率和統(tǒng)計(jì)形狀的前列腺超聲圖像自動(dòng)分割方法[J]. 生物醫(yī)學(xué)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.

服務(wù)與反饋：

【文章下載】【加入收藏】

提示：您還未登錄，請(qǐng)登錄！點(diǎn)此登錄

51黑料吃瓜在线观看,51黑料官网|51黑料捷克街头搭讪_51黑料入口最新视频