切换至 "中华医学电子期刊资源库"
高级检索
中华医学超声杂志（电子版）

中华医学超声杂志（电子版） ›› 2022, Vol. 19 ›› Issue (10) : 1127 -1130. doi: 10.3877/cma.j.issn.1672-6448.2022.10.019

综述

基于超声图像的机器学习算法应用于颈动脉斑块风险评估的研究进展
李晓1, 胡兵1, 白文坤1,†()   
  1. 1. 200233　上海交通大学附属第六人民医院超声医学科　上海超声医学研究所
  • 收稿日期:2021-02-09 出版日期:2022-10-01
  • 通信作者: 白文坤
  • 基金资助:
    国家重点研发计划项目(2021YFC2009100); 上海市科技计划项目(21Y11910900); 上海浦江人才计划(2019PJD036); 上海市第六人民医院面上培育项目(ynms202110)

Advances in application of ultrasound image-based machine learning algorithms in carotid plaque risk assessment

Xiao Li1, Bing Hu1, Wenkun Bai1()   

  • Received:2021-02-09 Published:2022-10-01
  • Corresponding author: Wenkun Bai
全文 ( ) 下载PDF ( ) 导出引用
引用本文：

李晓, 胡兵, 白文坤. 基于超声图像的机器学习算法应用于颈动脉斑块风险评估的研究进展[J]. 中华医学超声杂志（电子版）, 2022, 19(10): 1127-1130.

Xiao Li, Bing Hu, Wenkun Bai. Advances in application of ultrasound image-based machine learning algorithms in carotid plaque risk assessment[J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2022, 19(10): 1127-1130.

表1 以超声图像为基础的人工智能系统在颈动脉斑块风险评估中的应用
文献 样本量 分类标准 分类特征 分类器 准确性（%） 敏感度（%） 特异度（%）
Skandha等（2020）［19］ 346 有无症状 MFS+高阶谱

DCNN

tCNN

95.66

83.33

 - -
Jamthikar等（2019）［24］ 395 管腔直径 临床特征+纹理特征+形态特征 RF 95.15 5.50 99.15
周然等（2017）［23］ 38 是否药物治疗 三维纹理特征 SVM 84.4 83.3 85.7
Saba等（2017）［16］ 407 管腔直径 纹理特征+管腔直径 PCA/SVM 98.55 - -
Araki等（2017）［15］ 407 管腔直径 纹理特征+管腔直径 SVM 95.08 - -
Lekadir等（2017）［18］ 56 斑块成分

脂质

纤维

钙化

CNN

CNN

CNN

83.4

70.2

76.6

83±12

70±16

76±15

90±13

80±14

89±12

赵媛等（2017）［25］ 1828 有无症状 纹理特征 CNN 91.8a - -
孙夏等（2016）［17］ 1160 有无症状 纹理特征 CNN 97.33 97.46 97.20
Huang等（2016）［26］ 268 斑块成分 纹理特征+形态特征 KNN 88.14 - -
Gastounioti等（2015）［14］ 56 有无症状 纹理特征+运动特征 SVM 88 82 96
Kyriacou等（2015）［13］ 92 有无症状 统计特征+纹理特征+形态特征 SVM 78 88 72
Pedro等（2014）［12］ 146 有无症状 纹理特征+形态特征 EAI 76.92 70.00 80.13
Acharya等（2013）［10］ 146 有无症状 离散小波变换+高阶谱+纹理特征 SVM 91.7 97.0 80.0
Acharya等（2013）［11］ 146 有无症状 纹理特征 Fuzzy 93.1 99.0 80.0
346 有无症状 纹理特征 SVM 85.3 84.4 85.9
Acharya等（2012）［7］ 346 有无症状 纹理特征

Adaboost

SVM

81.7

82.4

82.3

82.9

81.9

82.1

Acharya等（2012）［27］ 346 有无症状 纹理特征 SVM 83.0 87.4 79.7
Acharya等（2012）［9］ 346 有无症状 纹理特征 SVM 83.7 80.0 86.4
Kyriacou等（2012）［8］ 108 有无症状 纹理特征 SVM 77 82 72
Harun Uğuz（2012）［28］ 191 管腔直径 Burg自回归频谱分析 LVQ-NN 97.91 98.53 96.36
Tsiaparas等（2012）［29］ 20 有无症状 纹理特征 SVM 79.3 78.2 84.3
16
Saba L, Jain PK, Suri HS, et al. Plaque tissue morphology-based stroke risk stratification using carotid ultrasound: a polling-based PCA learning paradigm [J]. J Med Syst, 2017, 41(6): 98.
17
孙夏, 吴蔚, 吴鹏, 等. 基于卷积神经网络的颈动脉斑块超声图像特征识别 [J].中国医疗器械信息, 2016, 22(9): 4-8.
18
Lekadir K, Galimzianova A, Betriu A, et al. A convolutional neural network for automatic characterization of plaque composition in carotid ultrasound [J]. IEEE J Biomed Health Inform, 2017, 21(1): 48-55.
19
Skandha SS, Gupta SK, Saba L, et al. 3-D optimized classification and characterization artificial intelligence paradigm for cardiovascular/stroke risk stratification using carotid ultrasound-based delineated plaque: Atheromatic™ 2.0 [J]. Comput Biol Med, 2020, 125: 103958.
20
Qian C, Yang X. An integrated method for atherosclerotic carotid plaque segmentation in ultrasound image [J]. Comput Methods Programs Biomed, 2018, 153: 19-32.
21
Meshram NH, Mitchell CC, Wilbrand S, et al. Deep learning for carotid plaque segmentation using a dilated U-Net Architecture [J]. Ultrason Imaging, 2020, 42(4-5): 221-230.
22
蔡梦媛, 周然, 程新耀, 等. 基于深度学习的颈动脉超声图像斑块分割算法 [J]. 生命科学仪器, 2020, 18(3): 45-53.
23
周然, FensterAaron, 丁明跃. 三维颈动脉超声图像中斑块的纹理特征分析 [J]. 中国科技论文在线精品论文, 2018, 11(5): 530-536.
24
Jamthikar A, Gupta D, Khanna NN, et al. A low-cost machine learning-based cardiovascular/stroke risk assessment system: integration of conventional factors with image phenotypes [J]. Cardiovasc Diagn Ther, 2019, 9(5): 420-430.
25
赵媛. 基于卷积神经网络的小样本颈动脉超声斑块图像识别方法研究 [D]. 武汉: 华中科技大学, 2018.
26
Huang X, Zhang Y, Qian M, et al. Classification of carotid plaque echogenicity by combining texture features and morphologic characteristics [J]. J Ultrasound Med, 2016, 35(10): 2253-2261.
27
Acharya UR, Sree SV, Krishnan MM, et al. Atherosclerotic risk stratification strategy for carotid arteries using texture-based features [J]. Ultrasound Med Biol, 2012, 38(6): 899-915.
28
Uğuz H. Detection of carotid artery disease by using learning vector quantization neural network [J]. J Med Syst, 2012, 36(2): 533-540.
29
Tsiaparas NN, Golemati S, Andreadis I, et al. Assessment of carotid atherosclerosis from B-mode ultrasound images using directional multiscale texture features [J]. Meas Sci Technol, 2012, 23: 114004.
1
GBD 2016 Stroke Collaborators. Global, regional, and national burden of stroke, 1990-2016: a systematic analysis for the Global Burden of Disease Study 2016 [J]. Lancet Neurol, 2019, 18(5): 439-458.
2
Porcu M, Mannelli L, Melis M, et al. Carotid plaque imaging profiling in subjects with risk factors (diabetes and hypertension) [J]. Cardiovasc Diagn Ther, 2020, 10(4): 1005-1018.
3
Paraskevas KI, Nicolaides AN, Kakkos SK. Asymptomatic Carotid Stenosis and Risk of Stroke (ACSRS) study: what have we learned from it? [J]. Ann Transl Med, 2020, 8(19): 1271.
4
Kilic A. Artificial intelligence and machine learning in cardiovascular health care[J]. Ann Thorac Surg, 2020, 109(5): 1323-1329.
5
Shen D, Wu G, Suk HI. Deep learning in medical image analysis [J]. Annu Rev Biomed Eng, 2017, 19: 221-248.
6
Kyriacou EC, Pattichis C, Pattichis M, et al. A review of noninvasive ultrasound image processing methods in the analysis of carotid plaque morphology for the assessment of stroke risk [J]. IEEE Trans Inf Technol Biomed, 2010, 14(4): 1027-1038.
7
Acharya RU, Faust O, Alvin AP, et al. Symptomatic vs. asymptomatic plaque classification in carotid ultrasound [J]. J Med Syst, 2012, 36(3): 1861-1871.
8
Kyriacou EC, Petroudi S, Pattichis CS, et al. Prediction of high-risk asymptomatic carotid plaques based on ultrasonic image features [J]. IEEE Trans Inf Technol Biomed, 2012, 16(5): 966-973.
9
Acharya UR, Faust O, Sree SV, et al. An accurate and generalized approach to plaque characterization in 346 carotid ultrasound scans [J]. IEEE Trans Instrum Meas, 2012, 61: 1045-1053.
10
Acharya UR, Faust O, S VS, et al. Understanding symptomatology of atherosclerotic plaque by image-based tissue characterization [J]. Comput Methods Programs Biomed, 2013, 110(1): 66-75.
11
Acharya UR, Mookiah MR, Vinitha Sree S, et al. Atherosclerotic plaque tissue characterization in 2D ultrasound longitudinal carotid scans for automated classification: a paradigm for stroke risk assessment [J]. Med Biol Eng Comput, 2013, 51(5): 513-523.
12
Pedro LM, Sanches JM, Seabra J, et al. Asymptomatic carotid disease--a new tool for assessing neurological risk [J]. Echocardiography, 2014, 31(3): 353-361.
13
Kyriacou E, Vogazianos P, Christodoulou C, et al. Prediction of the time period of stroke based on ultrasound image analysis of initially asymptomatic carotid plaques [J]. Annu Int Conf IEEE Eng Med Biol Soc, 2015, 2015: 334-337.
14
Gastounioti A, Makrodimitris S, Golemati S, et al. A novel computerized tool to stratify risk in carotid atherosclerosis using kinematic features of the arterial wall [J]. IEEE J Biomed Health Inform, 2015, 19(3): 1137-1145. .
15
Araki T, Jain PK, Suri HS, et al. Stroke risk stratification and its validation using ultrasonic echolucent carotid wall plaque morphology: a machine learning paradigm [J]. Comput Biol Med, 2017, 80: 77-96.
No related articles found!
阅读次数
全文


摘要

版权所有 中华医学会 中华医学电子音像出版社有限责任公司  京ICP备14006079号-1  网络出版服务许可证：(署)网出证(京)字第075号