• 《工程索引》(EI)刊源期刊
  • 中文核心期刊(综合性理工农医类)
  • 中国科技论文统计源期刊
  • 中国科学引文数据库来源期刊

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于切面识别的房间隔缺损智能辅助诊断

张文静 李文秀 刘爱军 武兴坤 李剑峰 罗涛

张文静, 李文秀, 刘爱军, 武兴坤, 李剑峰, 罗涛. 基于切面识别的房间隔缺损智能辅助诊断[J]. 工程科学学报. doi: 10.13374/j.issn2095-9389.2021.01.14.007
引用本文: 张文静, 李文秀, 刘爱军, 武兴坤, 李剑峰, 罗涛. 基于切面识别的房间隔缺损智能辅助诊断[J]. 工程科学学报. doi: 10.13374/j.issn2095-9389.2021.01.14.007
ZHANG Wen-jing, LI Wen-xiu, LIU Ai-jun, WU Xing-kun, LI Jian-feng, LUO Tao. Intelligent auxiliary diagnosis of atrial septal defect based on view classification[J]. Chinese Journal of Engineering. doi: 10.13374/j.issn2095-9389.2021.01.14.007
Citation: ZHANG Wen-jing, LI Wen-xiu, LIU Ai-jun, WU Xing-kun, LI Jian-feng, LUO Tao. Intelligent auxiliary diagnosis of atrial septal defect based on view classification[J]. Chinese Journal of Engineering. doi: 10.13374/j.issn2095-9389.2021.01.14.007

基于切面识别的房间隔缺损智能辅助诊断

doi: 10.13374/j.issn2095-9389.2021.01.14.007
基金项目: 国家自然科学基金资助项目(61571065)
详细信息
    通讯作者:

    E-mail: tluo@bupt.edu.cn

  • 中图分类号: R318

Intelligent auxiliary diagnosis of atrial septal defect based on view classification

More Information
  • 摘要: 针对超声心动图像质量差、噪声多,传统卷积神经网络架构对超声心动图像的学习能力有限、表达不充分的缺点,提出了一种基于标准切面识别的房间隔缺损(Atrial septal defect,ASD)智能辅助诊断模型。该模型通过对超声心动图像进行切面识别,充分融合其不同切面的语义特征,使得诊断的准确率得到明显提升。此外,还对其进行双边滤波保边去噪,并基于此模型搭建房间隔缺损智能辅助诊断系统(简称ASD辅助诊断系统)。结果表明,该ASD辅助诊断系统的准确率高达97.8%,且与传统卷积神经网络相比大大降低了假阴性率。

     

  • 图  1  超声心动图对比。(a)ASD患者;(b)健康人

    Figure  1.  Contrast in echocardiography of ASD patient (a) and healthy people (b)

    图  2  超声心动图6类标准切面。(a)胸骨旁大动脉短轴;(b)心尖四腔心;(c)胸骨旁四腔心;(d)剑突下上下腔长轴;(e)剑突下大动脉短轴;(f)剑突下双房心

    Figure  2.  Six normal views of echocardiography: (a) parasternal short-axis view; (b) apical four-chamber view; (c) parasternal four-chamber view; (d) subcostal inferior vena cava; (e) subcostal short axial of aorta; (f) subcostal left and right atrium

    图  3  噪声滤波效果对比。(a)原始图像;(b)均值滤波;(c)高斯滤波;(d)双边滤波

    Figure  3.  Comparison of different noise filter algorithms: (a) original image; (b) mean filter; (c) Gaussian filter; (d) bilateral filter

    图  4  ASD辅助诊断模型总体架构

    Figure  4.  ASD auxiliary diagnosis model overall architecture

    图  5  ASD辅助诊断模型完整架构

    Figure  5.  ASD auxiliary diagnosis model completed architecture

    图  6  网络结构及参数

    Figure  6.  Network structure and parameters

    图  7  房间隔遮挡测试。(a,c)遮挡前;(b,d)遮挡后

    Figure  7.  Atrial septal covering test: (a,c) before covering; (b,d)covered

    表  1  ASD诊断测试结果

    Table  1.   Contrast among different models

    ModelWith bilateral
    filtering
    Accuracy /
    %
    False negative
    rate / %
    False positive
    rate / %
    Resnet50‒no view-netYes86.72.855.6
    Densenet121‒no view-netYes86.713.911.1
    Densenet‒with view-netNo93.35.611
    Densenet‒with view-netYes97.82.80
    下载: 导出CSV
  • [1] Wang X F, Xie M X. Textbook of Echocardiography. 5th Ed. Beijing: People’s Medical Publishing House, 2016

    王新房, 谢明星. 超声心动图学. 5版. 北京: 人民卫生出版社, 2016
    [2] Li J W. Trend and epidemiological analysis of congenital heart disease. Chin J Cardiovasc Rehabilitation Med, 2017, 26(1): 60 doi: 10.3969/j.issn.1008-0074.2017.01.17

    黎洁雯. 先天性心脏病的流行趋势及流行病学分析. 心血管康复医学杂志, 2017, 26(1):60 doi: 10.3969/j.issn.1008-0074.2017.01.17
    [3] Zhang L Y, Qiao Y H, Ning S F, et al. Analysis of ultrasonic diagnosis of 39 atrial septal defects. China Pract Med, 2009, 4(14): 95 doi: 10.3969/j.issn.1673-7555.2009.14.067

    张丽媛, 乔玉红, 宁淑范, 等. 房间隔缺损39例超声诊断分析. 中国实用医药, 2009, 4(14):95 doi: 10.3969/j.issn.1673-7555.2009.14.067
    [4] Tao P, Fu Z L, Zhu K, et al. Echocardiogram view recognition using deep convolutional neural network. J Comput Appl, 2017, 37(5): 1434 doi: 10.11772/j.issn.1001-9081.2017.05.1434

    陶攀, 付忠良, 朱锴, 等. 基于深度学习的超声心动图切面识别方法. 计算机应用, 2017, 37(5):1434 doi: 10.11772/j.issn.1001-9081.2017.05.1434
    [5] Madani A, Arnaout R, Mofrad M, et al. Fast and accurate view classification of echocardiograms using deep learning. Npj Digit Med, 2018, 1(1): 6 doi: 10.1038/s41746-017-0013-1
    [6] Madani A, Ong J R, Tibrewal A, et al. Deep echocardiography: Data-efficient supervised and semi-supervised deep learning towards automated diagnosis of cardiac disease. Npj Digit Med, 2018, 1(1): 59 doi: 10.1038/s41746-017-0008-y
    [7] Teng L, Fu Z L, Yao Y. Interactive translation in echocardiography training system with enhanced cycle-GAN. IEEE Access, 2020, 8: 106147 doi: 10.1109/ACCESS.2020.3000666
    [8] Teng L, Fu Z L, Ma Q, et al. Interactive echocardiography translation using few-shot GAN transfer learning. Comput Math Methods Med, 2020, 2020: 1487035
    [9] Ghorbani A, Ouyang D, Abid A, et al. Deep learning interpretation of echocardiograms. Npj Digit Med, 2020, 3(1): 1 doi: 10.1038/s41746-019-0211-0
    [10] Veni G, Moradi M, Bulu H K, et al. Echocardiography segmentation based on a shape-guided deformable model driven by a fully convolutional network prior // 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018). Washington, 2018: 898
    [11] Leclerc S, Smistad E, Pedrosa J, et al. Deep learning for segmentation using an open large-scale dataset in 2D echocardiography. IEEE Trans Med Imaging, 2019, 38(9): 2198 doi: 10.1109/TMI.2019.2900516
    [12] Li Y W, Ho C P, Toulemonde M, et al. Fully automatic myocardial segmentation of contrast echocardiography sequence using random forests guided by shape model. IEEE Trans Med Imaging, 2017, 37(5): 1081
    [13] Lu Y, Fu X H, Li X Q, et al. Cardiac chamber segmentation using deep learning on magnetic resonance images from patients before and after atrial septal occlusion surgery // 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). Montreal, 2020: 1211
    [14] Zyuzin V, Mukhtarov A, Neustroev D, et al. Segmentation of 2D echocardiography images using residual blocks in U-net architectures // 2020 Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT). Yekaterinburg, 2020: 499
    [15] Smistad E, Østvik A, Salte I M, et al. Fully automatic real-time ejection fraction and MAPSE measurements in 2D echocardiography using deep neural networks // 2018 IEEE International Ultrasonics Symposium (IUS). Kobe, 2018: 1
    [16] Davis A, Billick K, Horton K, et al. Artificial intelligence and echocardiography: A primer for cardiac sonographers. J Am Soc Echocardiogr, 2020, 33(9): 1061 doi: 10.1016/j.echo.2020.04.025
    [17] Huang Q, Zhang F, Li X. Machine learning in ultrasound computer-aided diagnostic systems: A survey. Biomed Res Int, 2018, 2018: 5137904
    [18] Wang X, Jia Y G, Sevenster M, et al. Representation learning of finding codes in structured echocardiogram reporting // 2018 IEEE International Conference on Healthcare Informatics (ICHI). New York, 2018: 429
    [19] Liao Z B, Girgis H, Abdi A, et al. On modelling label uncertainty in deep neural networks: Automatic estimation of intra- observer variability in 2D echocardiography quality assessment. IEEE Trans Med Imaging, 2020, 39(6): 1868 doi: 10.1109/TMI.2019.2959209
    [20] Singh Y, Roehr C C, Tissot C, et al. Education, training, and accreditation of neonatologist performed echocardiography in Europe—framework for practice. Pediatr Res, 2018, 84(1): 13
    [21] Mishra D, Chaudhury S, Sarkar M, et al. Ultrasound image enhancement using structure oriented adversarial network. IEEE Signal Process Lett, 2018, 25(9): 1349 doi: 10.1109/LSP.2018.2858147
    [22] Sable A H, Jondhale K C. Modified double bilateral filter for sharpness enhancement and noise removal // 2010 International Conference on Advances in Computer Engineering. Bangalore, 2010: 295
    [23] Patil P D, Kumbhar A D. Bilateral filter for image denoising // 2015 International Conference on Green Computing and Internet of Things (ICGCIoT). Greater Noida, 2015: 299
    [24] Huang G, Liu Z, van der Maaten L, et al. Densely connected convolutional networks // 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, 2017: 4700
    [25] Li J Y, Zhao Y K, Xue Z E, et al. A survey of model compression for deep neural networks. Chin J Eng, 2019, 41(10): 1229

    李江昀, 赵义凯, 薛卓尔, 等. 深度神经网络模型压缩综述. 工程科学学报, 2019, 41(10):1229
  • 加载中
图(7) / 表(1)
计量
  • 文章访问数:  48
  • HTML全文浏览量:  21
  • PDF下载量:  9
  • 被引次数: 0
出版历程
  • 收稿日期:  2021-01-14
  • 网络出版日期:  2021-04-07

目录

    /

    返回文章
    返回