北京生物医学工程

机器学习在心血管疾病诊断中的研究进展

Review onmachine learning approaches forcardiovascular diseasediagnosis

作者：赵梦蝶孙九爱

单位：上海理工大学医疗器械与食品学院(上海 200093) 上海健康医学院(上海 201318)

关键词：机器学习；心血管疾病；医学影像；多模态数据；辅助诊断

分类号：R318

出版年·卷·期（页码）：2020·39·2（208-214）

摘要：

当前医生对心血管疾病的诊断主要依赖对患者心血管影像的分析，同时，医生还需要考虑患者的各项生理健康指标、既往病史、生活环境等信息，该方法存在效率低和成本高等问题。因此，人们试图利用机器学习方法辅助心血管疾病的诊断。本文首先总结了机器学习在冠状动脉计算机断层扫描、超声心动图、心电图等多种心血管影像处理中的应用；其次，对现有的机器学习模型进行了评估和分析；最后，本文认为虽然现有的基于机器学习的心血管疾病诊断方法已经可以媲美专业医生的水平，但是，该方法仍面临医学数据难以大量采集、医学成像信噪比低等困难。未来的研究方向应在小样本诊断模型的性能、多模态医学数据的融合、医学数据的共享等方面继续改进。

At present, the diagnosis of cardiovascular diseases mainly depends on the analysis of cardiovascular images. Meanwhile, doctors also need to take into account the health indicators, medical history, living environment and other information of patients. This method has the disadvantages of low efficiency and high cost, and therefore, machine learning method has been adapted to solve these problems. This paper, summarizes the applications of machine learning in coronary computed tomography, echocardiography, electrocardiogram and so on. By evaluating and analyzing the existing models, the existing machine learning based methods may achieve similar level as clinical doctors. However the machine learning approaches need to solve the problems such as less training data and low signal-to-noise ratio of medical imaging data. The future research direction should continue to improve the performance of small sample diagnostic model, the fusion of multimodal medical data, the sharing of medical diagnostic data and so on.

参考文献：

[1] 胡盛寿,高润霖,刘力生,等. 《中国心血管病报告2018》概要[J]. 中国循环杂志, 2019, 34(3): 209-220.

Hu SS, Gao RL, Liu LS, et al. Summary of the 2018 Report on Cardiovascular Diseases in China[J]. Chinese Circulation Journal, 2019, 34(3): 209-220.

[2] 中国医学影像AI产学研用创新联盟. 人工医学影像AI白皮书[EB/OL]. 2019, https://vcbeat.top.

China medical imaging AI industry-university-research innovation alliance. White paper medical imaging AI in China[EB/OL]. 2019, https://vcbeat.top.

[3] Wang G, Li W, Zuluaga MA, et al. Interactive medical image segmentation using deep learning with image-specific fine tuning[J]. IEEE Transactions on Medical Imaging, 2018, 37(7): 1562-1573.

[4] Balakrishnan G, Zhao A, Sabuncu MR, et al. An unsupervised learning model for deformable medical image registration[C]// In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Seattle, Washington, USA: IEEE Press, 2018: 9252-9260.

[5] Hu L, Cui J. Digital image recognition based on fractional-order-PCA-SVM coupling algorithm[J]. Measurement, 2019, 145: 150-159.

[6] Frid-Adar M, Diamant I, Klang E, et al. GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification[J]. Neurocomputing, 2018, 321: 321-331.

[7] Takx RAP, de Jong PA, Leiner T, et al. Automated coronary artery calcification scoring in non-gated chest CT: agreement and reliability[J]. PLoS One, 2014, 9(3): e91239.

[8] I?gum I, de Vos B, Wolterink J, et al. Automatic determination of cardiovascular risk by CT attenuation correction maps in Rb-82 PET/CT[J]. Journal of Nuclear Cardiology, 2018, 25(6): 2133-2142.

[9] Motwani M, Dey D, Berman D, et al. Machine learning for prediction of all-cause mortality in patients with suspected coronary artery disease: a 5-year multicentre prospective registry analysis[J]. European Heart Journal, 2016, 38(7): 500-507.

[10] Liu Y, Dai X, Wolf H, et al. A machine-learning model in predicting hemodynamically significant coronary artery disease: a prospective cohort study[J]. Circulation, 2018, 138(Suppl_1): A10602.

[11] Nakanishi R, Dey D, Commandeur F, et al. Machine learning in predicting coronary heart disease and cardiovascular disease events: results from the multi-ethnic study of atherosclerosis (mesa)[J]. Journal of the American College of Cardiology, 2018, 71(11 Supplement): A1483.

[12] Commandeur F, Goeller M, Betancur J, et al. Deep learning for quantification of epicardial and thoracic adipose tissue from non-contrast CT[J]. IEEE Transactions on Medical Imaging, 2018, 37(8):1835-1846.

[13] Zreik M, Lessmann N, van Hamersvelt RW, et al. Deep learning analysis of the myocardium in coronary CT angiography for identification of patients with functionally significant coronary artery stenosis[J]. Medical image analysis, 2018, 44: 72-85.

[14] Khamis H, Zurakhov G, Azar V, et al. Automatic apical view classification of echocardiograms using a discriminative learning dictionary[J]. Medical Image Analysis, 2017, 36: 15–21.

[15] Knackstedt C, Bekkers SC, Schummers G, et al. Fully automated versus standard tracking of left ventricular ejection fraction and longitudinal strain: the FAST-Efs Multicenter Study[J]. Journal of the American College of Cardiology , 2015, 66(13): 1456-1466.

[16] Dong S, Luo G, Sun G, et al. A left ventricular segmentation method on 3D echocardiography using deep learning and snake[C]// 2016 Computing in Cardiology Conference. Vancouver, BC, Canada: IEEE Press, 2016, 43: 473–476.

[17] Zhao Q, Zhang L. ECG feature extraction and classification using wavelet transform and support vector machines[C]// 2005 International Conference on Neural Networks and Brain. Beijing, China: IEEE Press, 2005, 2:1089–1092.

[18] Scirè A, Chatzigiannakis I, Anagnostopoulos A. Heartbeat detection and arrhythmia classification from the ECG signal using machine learning tech-niques[D]. Rome: University of Rome, 2018.

[19] Hannun AY, Rajpurkar P, Haghpanahi M, et al. Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network[J]. Nature Medicine, 2019, 25(1): 65-69.

[20] Betancur J, Rubeaux M, Fuchs T, et al. Automatic valve plane localization in myocardial perfusion SPECT/CT by machine learning: anatomic and clinical validation[J]. Journal of Nuclear Medicine, 2017, 58(6): 961–967.

[21] Betancur J, Commandeur F, Motlagh M, et al. Deep learning for prediction of obstructive disease from fast myocardial perfusion SPECT: a multicenter study[J]. JACC: Cardiovascular Imaging, 2018, 11(11): 1654-1663.

[22] Dey D, Diaz Zamudio M, Schuhbaeck A, et al. Relationship between quantitative adverse plaque features from coronary computed tomography angiography and downstream impaired myocardial flow reserve by 13N-ammonia positron emission tomography: a pilot study[J]. Circulation: Cardiovascular Imaging, 2015, 8(10): e003255.

[23] Dawes T, de Marvao A, Shi W, et al. Machine learning of three-dimensional right ventricular motion enables outcome prediction in pulmonary hypertension: a cardiac MR imaging study[J]. Radiology, 2017, 283(2): 381–390.

[24] Zhang L, Wahle A, Chen Z, et al. Predicting locations of high-risk plaques in coronary arteries in patients receiving statin therapy[J]. IEEE Transactions on Medical Imaging, 2018, 37(1): 151–161.

[25] Abdolmanafi A, Duong L, Dahdah N, et al. Deep feature learning for automatic tissue classification of coronary artery using optical coherence tomography[J]. Biomedical Optics Express, 2017, 8(2): 1203–1220.

[26] Shen D, Wu G, Suk HI. Deep learning in medical image analysis[J].Annual Review of Biomedical Engineering, 2017, 19: 221-248.

[27] 孙凯. 随机森林在医学影像分析中的应用研究进展[J]. 北京生物医学工程, 2018, 37(4): 413-418.

Sun K. Research progress on application of random forest in medical image analysis[J]. Beijing Biomedical Engineering, 2018, 37(4): 413-418.

[28] 袁丽, 吴水才, 袁延超. 一种改进的FastICA算法在胎儿心电提取中的应用[J]. 北京生物医学工程, 2018, 37(5): 488-493.

Yuan L, Wu SC, Yuan YC. Application of an improved FastICA algorithm in fetal electrocardiogram extraction[J]. Beijing Biomedical Engineering, 2018, 37(5): 488-493.

[29] 翟柏松, 赵向蕊, 陈向前, 等. 术中透视图像质量对双平面定位算法精度的影响[J]. 北京生物医学工程, 2017, 36(4): 372-377.

Zhai BS, Zhao XR, Chen XQ, et al. Influence of intraoperative fluoroscopy images’ quality on the accuracy of bi-planar positioning method[J]. Beijing Biomedical Engineering, 2017, 36(4): 372-377.

[30] 伍建林, 鄂亚军, 张清, 等. 嗅觉脑功能磁共振成像中提高磁敏感性脑区信噪比的参数优化研究[J]. 中国医学影像技术, 2007, 23(12): 1764-1768.

Wu JL, E YJ, Zhang Q, et al. Study of parameter optimum on the olfaction fMRI for increasing SNR of the susceptibility regions of human brain[J]. Chinese Journal of Medical Imaging Technology, 2007, 23(12): 1764-1768.

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