Advances in the application of machine learning based on intravascular ultrasound in coronary artery disease

doi:10.3877/cma.j.issn.2095-655X.2023.03.002

Abstract

Abstract:

Intravascular ultrasound(IVUS) is an essential source of information for the clinical diagnosis and management of coronary artery disease. The diagnosis and management of coronary artery disease heavily relies on the medical professionals′ interpretation of IVUS images. Machine learning can analyze data, create medical diagnostic models, and extract information from IVUS images that human eyes cannot perceive. These capabilities help enhance the diagnosis of coronary artery disease, forecast patients′ disease states and clinical outcomes, and play a significant role in supporting clinical work. This article discusses the limitations and potential applications of machine learning techniques in IVUS for coronary artery imaging.

Key words: Machine learning, Ultrasonography, interventional, Coronary artery disease, Plaque, atherosclerotic

Xin Xiong, Yongzhi Deng. Advances in the application of machine learning based on intravascular ultrasound in coronary artery disease[J]. Chinese Journal of Diagnostics(Electronic Edition), 2023, 11(03): 153-157.

/ / Recommend

Add to citation manager EndNote|Ris|BibTeX

URL: https://zhzdxdzzz.cma-cmc.com.cn/EN/10.3877/cma.j.issn.2095-655X.2023.03.002

https://zhzdxdzzz.cma-cmc.com.cn/EN/Y2023/V11/I03/153

Figures/Tables 1

References 38

[1]	Räber L，Mintz GS，Koskinas KC，et al.Clinical use of intracoronary imaging.Part 1：guidance and optimization of coronary interventions.An expert consensus document of the European Association of Percutaneous Cardiovascular Interventions[J]．Eur Heart J，2018，39(35)：3281-3300.DOI：10.1093/eurheartj/ehy285.
[2]	Avanzo M，Wei L，Stancanello J，et al.Machine and deep learning methods for radiomics[J]．Med Phys，2020，47(5)：e185-e202.DOI：10.1002/mp.13678.
[3]	Schwalbe N，Wahl B．Artificial intelligence and the future of global health[J]．Lancet，2020，395(10236)：1579-1586.DOI：10.1016/S0140-6736(20)30226-9.
[4]	Xiang Y，Zhao L，Liu Z，et al.Implementation of artificial intelligence in medicine：status analysis and development suggestions[J]．Artif Intell Med，2020(102)：101780.DOI：10.1016/j.artmed.2019.101780.
[5]	Fedewa R, Puri R, Fleischman E, et al. Artificial intelligence in intracoronary imaging[J]．Curr Cardiol Rep，2020，22(7)：46.DOI：10.1007/s11886-020-01299-w.
[6]	Choi RY, Coyner AS, Kalpathy-Cramer J, et al. Introduction to machine learning，neural networks，and deep learning[J]．Transl Vis Sci Technol，2020，9(2)：14.DOI：10.1167/tvst.9.2.14.
[7]	Lopez-Jimenez F，Attia Z，Arruda-Olson AM，et al.Artificial intelligence in cardiology：present and future[J]．Mayo Clin Proc，2020，95(5)：1015-1039.DOI：10.1016/j.mayocp.2020.01.038.
[8]	Chan HP，Samala RK，Hadjiiski LM，et al.Deep learning in medical image analysis[J]．Adv Exp Med Biol，2020(1213)：3-21.DOI：10.1007/978-3-030-33128-3_1.
[9]	Sahiner B，Pezeshk A，Hadjiiski LM，et al.Deep learning in medical imaging and radiation therapy[J]．Med Phys，2019，46(1)：e1-e36.DOI：10.1002/mp.13264.
[10]	Sevakula RK, Au-Yeung WM, Singh JP, et al. State-of-the-art machine learning techniques aiming to improve patient outcomes pertaining to the cardiovascular system[J]．J Am Heart Assoc，2020，9(4)：e013924.DOI：10.1161/JAHA.119.013924.
[11]	Handelman GS，Kok HK，Chandra RV，et al.eDoctor：machine learning and the future of medicine[J]．J Intern Med，2018，284(6)：603-619.DOI：10.1111/joim.12822.
[12]	Xu J，Lo S．Fundamentals and role of intravascular ultrasound in percutaneous coronary intervention[J]．Cardiovasc Diagn Ther，2020，10(5)：1358-1370.DOI：10.21037/cdt.2020.01.15.
[13]	Lo Vercio L，Del Fresno M，Larrabide I．Lumen-intima and media-adventitia segmentation in IVUS images using supervised classifications of arterial layers and morphological structures[J]．Comput Methods Programs Biomed，2019(177)：113-121.DOI：10.1016/j.cmpb.2019.05.021.
[14]	Cui H，Xia Y，Zhang Y．Supervised machine learning for coronary artery lumen segmentation in intravascular ultrasound images[J]．Int J Numer Method Biomed Eng，2020，36(7)：e3348.DOI：10.1002/cnm.3348.
[15]	Bajaj R，Huang X，Kilic Y，et al.Advanced deep learning methodology for accurate，real-time segmentation of high-resolution intravascular ultrasound images[J]．Int J Cardiol，2021(339)：185-191.DOI：10.1016/j.ijcard.2021.06.030.
[16]	袁绍锋，杨丰，徐琳，等．有条件生成对抗网络的IVUS图像内膜与中-外膜边界检测[J]．中国生物医学工程学报，2019，38(2)：146-156.DOI：10.3969/j.issn.0258-8021.2019.02.003.
[17]	Szarski M，Chauhan S．Improved real-time segmentation of intravascular ultrasound images using coordinate-aware fully convolutional networks[J]．Comput Med Imaging Graph，2021(91)：101955.DOI：10.1016/j.compmedimag.2021.101955.
[18]	Jin HY, Weir-McCall JR, Leipsic JA, et al. The relationship between coronary calcification and the natural history of coronary artery disease[J]．JACC Cardiovasc Imaging，2021，14(1)：233-242.DOI：10.1016/j.jcmg.2020.08.036.
[19]	Jinnouchi H，Sato Y，Sakamoto A，et al.Calcium deposition within coronary atherosclerotic lesion：implications for plaque stability[J]．Atherosclerosis，2020(306)：85-95.DOI：10.1016/j.atherosclerosis.2020.05.017.
[20]	Cho H，Kang SJ，Min HS，et al.Intravascular ultrasound-based deep learning for plaque characterization in coronary artery disease[J]．Atherosclerosis，2021(324)：69-75.DOI：10.1016/j.atherosclerosis.2021.03.037.
[21]	Li YC，Shen TY，Chen CC，et al.Automatic detection of atherosclerotic plaque and calcification from intravascular ultrasound images by using deep convolutional neural networks[J]．IEEE Trans Ultrason Ferroelectr Freq Control，2021，68(5)：1762-1772.DOI：10.1109/TUFFC.2021.3052486.
[22]	Shinohara H，Kodera S，Ninomiya K，et al.Automatic detection of vessel structure by deep learning using intravascular ultrasound images of the coronary arteries[J]．PLoS One，2021，16(8)：e0255577.DOI：10.1371/journal.pone.0255577.
[23]	杨云，张立泽清，齐勇，等．基于残差网络的血管内超声图像识别[J]．计算机仿真，2020，37(4)：269-273.DOI：10.3969/j.issn.1006-9348.2020.04.056.
[24]	Stone GW，Narula J．Shining a light on plaque vulnerability and treatment[J]．JACC Cardiovasc Imaging，2022，15(7)：1322-1324.DOI：10.1016/j.jcmg.2022.04.019.
[25]	Erlinge D, Maehara A, Ben-Yehuda O, et al. Identification of vulnerable plaques and patients by intracoronary near-infrared spectroscopy and ultrasound (PROSPECT II)：a prospective natural history study[J]．Lancet，2021，397(10278)：985-995.DOI：10.1016/S0140-6736(21)00249-X.
[26]	Wang L，Tang D，Maehara A，et al.Using intravascular ultrasound image-based fluid-structure interaction models and machine learning methods to predict human coronary plaque vulnerability change[J]．Comput Methods Biomech Biomed Engin，2020，23(15)：1267-1276.DOI：10.1080/10255842.2020.1795838.
[27]	Bae Y，Kang SJ，Kim G，et al.Prediction of coronary thin-cap fibroatheroma by intravascular ultrasound-based machine learning[J]．Atherosclerosis，2019(288)：168-174.DOI：10.1016/j.atherosclerosis.2019.04.228.
[28]	Jun TJ，Kang SJ，Lee JG，et al.Automated detection of vulnerable plaque in intravascular ultrasound images[J]．Med Biol Eng Comput，2019，57(4)：863-876.DOI：10.1007/s11517-018-1925-x.
[29]	Cao Y, Xiao X, Liu Z, et al. Detecting vulnerable plaque with vulnerability index based on convolutional neural networks[J]．Comput Med Imaging Graph，2020(81)：101711.DOI：10.1016/j.compmedimag.2020.101711.
[30]	Whittington B，Tzolos E，Williams MC，et al.Imaging of intracoronary thrombus[J]．Heart，2023，109(10)：740-747.DOI：10.1136/heartjnl-2022-321361.
[31]	Fujimura T，Matsumura M，Witzenbichler B，et al.Stent expansion indexes to predict clinical outcomes：an IVUS substudy from ADAPT-DES[J]．JACC Cardiovasc Interv，2021，14(15)：1639-1650.DOI：10.1016/j.jcin.2021.05.019.
[32]	Watanabe Y，Sakakura K，Taniguchi Y，et al.Impact of intravascular ultrasound-incomplete stent apposition on stent failure[J]．Catheter Cardiovasc Interv，2022，100(6)：1000-1009.DOI：10.1002/ccd.30424.
[33]	Min HS，Ryu D，Kang SJ，et al.Prediction of coronary stent underexpansion by pre-procedural intravascular ultrasound-based deep learning[J]．JACC Cardiovasc Interv，2021，14(9)：1021-1029.DOI：10.1016/j.jcin.2021.01.033.
[34]	Nishi T，Yamashita R，Imura S，et al.Deep learning-based intravascular ultrasound segmentation for the assessment of coronary artery disease[J]．Int J Cardiol，2021(333)：55-59.DOI：10.1016/j.ijcard.2021.03.020.
[35]	Wissel T，Riedl KA，Schaefers K，et al.Cascaded learning in intravascular ultrasound：coronary stent delineation in manual pullbacks[J]．J Med Imaging (Bellingham)，2022，9(2)：025001.DOI：10.1117/1.JMI.9.2.025001.
[36]	Gao J，Hua Y，Hu GS，et al.Discrepancy-guided domain-adaptive data augmentation[J]．IEEE Trans Neural Netw Learn Syst，2021，PP.DOI：10.1109/TNNLS.2021.3128401.
[37]	Lee H，Yune S，Mansouri M，et al.An explainable deep-learning algorithm for the detection of acute intracranial haemorrhage from small datasets[J]．Nat Biomed Eng，2019，3(3)：173-182.DOI：10.1038/s41551-018-0324-9.
[38]	Liao W，Zou B，Zhao R，et al.Clinical interpretable deep learning model for glaucoma diagnosis[J]．IEEE J Biomed Health Inform，2020，24(5)：1405-1412.DOI：10.1109/JBHI.2019.2949075.

目的	数据	方法	评估方式	参考文献
管腔-内膜和中膜-外膜分割	435张IVUS图像	SVM，RF	IoU和HD	13
	1 450张IVUS图像	Boosting	IoU	14
	65例患者IVUS图像	ResNet	DSC、IoU和HD	15
	10例患者的435张IVUS图像	SHGN，C-GAN	IoU、PAD和HD	16
	10例患者的435张IVUS图像	U-Net	IoU和HD	17
IVUS斑块的不同成分分割	598例患者的137 989张IVUS图像	EfficientNet	DSC、准确率、敏感度和特异度	20
	18例患者的713张IVUS图像	U-Net	准确率、敏感度、特异度和DSC	21
	3 738张IVUS图像	U-Net	准确率，召回率，DSC和IoU	22
	63例患者的1 641张IVUS图像	ResNet	准确率	23
易损斑块的判断	9例患者的IVUS图像	GLMM，SVM，RF	准确率、敏感度、特异度和AUC	26
	517例患者的IVUS和OCT图像	ANN，SVM，naïve Bayes	准确率、敏感度、特异度和AUC	27
	100例患者的12 325张IVUS和OCT图像	AlexNet，VGGNet GoogLeNet和ResNet	敏感度、特异度和AUC	28
	3 535张IVUS图像	MatConvNet	准确率、敏感度、特异度和AUC	29
预测血管内支架效果	618条血管的IVUS图像	DenseNet	准确率、敏感度、特异度和AUC	33
	1 576条血管的45 449张IVUS图像	DeepLabv3	IoU和DSC	34
	35例患者的20 020张IVUS图像	DeepLabV3	DSC，召回率和AUC	35

目的	数据	方法	评估方式	参考文献
管腔-内膜和中膜-外膜分割	435张IVUS图像	SVM，RF	IoU和HD	13
	1 450张IVUS图像	Boosting	IoU	14
	65例患者IVUS图像	ResNet	DSC、IoU和HD	15
	10例患者的435张IVUS图像	SHGN，C-GAN	IoU、PAD和HD	16
	10例患者的435张IVUS图像	U-Net	IoU和HD	17
IVUS斑块的不同成分分割	598例患者的137 989张IVUS图像	EfficientNet	DSC、准确率、敏感度和特异度	20
	18例患者的713张IVUS图像	U-Net	准确率、敏感度、特异度和DSC	21
	3 738张IVUS图像	U-Net	准确率，召回率，DSC和IoU	22
	63例患者的1 641张IVUS图像	ResNet	准确率	23
易损斑块的判断	9例患者的IVUS图像	GLMM，SVM，RF	准确率、敏感度、特异度和AUC	26
	517例患者的IVUS和OCT图像	ANN，SVM，naïve Bayes	准确率、敏感度、特异度和AUC	27
	100例患者的12 325张IVUS和OCT图像	AlexNet，VGGNet GoogLeNet和ResNet	敏感度、特异度和AUC	28
	3 535张IVUS图像	MatConvNet	准确率、敏感度、特异度和AUC	29
预测血管内支架效果	618条血管的IVUS图像	DenseNet	准确率、敏感度、特异度和AUC	33
	1 576条血管的45 449张IVUS图像	DeepLabv3	IoU和DSC	34
	35例患者的20 020张IVUS图像	DeepLabV3	DSC，召回率和AUC	35

Please choose a citation manager

Content to export