Echocardiography-based AI for detection and quantification of atrial septal defect

被引:6
|
作者
Lin, Xixiang [1 ,2 ]
Yang, Feifei [1 ]
Chen, Yixin [3 ]
Chen, Xu [1 ,2 ]
Wang, Wenjun [1 ]
Li, Wenxiu [4 ]
Wang, Qiushuang [5 ]
Zhang, Liwei [5 ]
Li, Xin [6 ]
Deng, Yujiao [1 ]
Pu, Haitao [3 ]
Chen, Xiaotian [3 ]
Wang, Xiao [1 ,2 ]
Luo, Dong [1 ,2 ]
Zhang, Peifang [3 ]
Burkhoff, Daniel [7 ]
He, Kunlun [1 ]
机构
[1] Chinese Peoples Liberat Army Gen Hosp, Med Big Data Ctr, Beijing, Peoples R China
[2] Med Sch Chinese PLA, Beijing, Peoples R China
[3] BioMind Technol, Beijing, Peoples R China
[4] Capital Med Univ, Beijing Anzhen Hosp, Dept Pediat Cardiac Ctr, Beijing, Peoples R China
[5] Chinese Peoples Liberat Army Gen Hosp, Med Ctr 4, Dept Cardiol, Beijing, Peoples R China
[6] Chinese Peoples Liberat Army Gen Hosp, Med Ctr 6, Dept Ultrasonog, Beijing, Peoples R China
[7] Cardiovasc Res Fdn, New York, NY USA
来源
基金
中国国家自然科学基金;
关键词
artificial intelligence; deep learning; echocardiography; atrial septal defects; congenital heart disease; TRANSESOPHAGEAL ECHOCARDIOGRAPHY; SOCIETY; DISEASE;
D O I
10.3389/fcvm.2023.985657
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
ObjectivesWe developed and tested a deep learning (DL) framework applicable to color Doppler echocardiography for automatic detection and quantification of atrial septal defects (ASDs). BackgroundColor Doppler echocardiography is the most commonly used non-invasive imaging tool for detection of ASDs. While prior studies have used DL to detect the presence of ASDs from standard 2D echocardiographic views, no study has yet reported automatic interpretation of color Doppler videos for detection and quantification of ASD. MethodsA total of 821 examinations from two tertiary care hospitals were collected as the training and external testing dataset. We developed DL models to automatically process color Doppler echocardiograms, including view selection, ASD detection and identification of the endpoints of the atrial septum and of the defect to quantify the size of defect and the residual rim. ResultsThe view selection model achieved an average accuracy of 99% in identifying four standard views required for evaluating ASD. In the external testing dataset, the ASD detection model achieved an area under the curve (AUC) of 0.92 with 88% sensitivity and 89% specificity. The final model automatically measured the size of defect and residual rim, with the mean biases of 1.9 mm and 2.2 mm, respectively. ConclusionWe demonstrated the feasibility of using a deep learning model for automated detection and quantification of ASD from color Doppler echocardiography. This model has the potential to improve the accuracy and efficiency of using color Doppler in clinical practice for screening and quantification of ASDs, that are required for clinical decision making.
引用
收藏
页数:10
相关论文
共 50 条
  • [1] Echocardiography-based AI detection of regional wall motion abnormalities and quantification of cardiac function in myocardial infarction
    Lin, Xixiang
    Yang, Feifei
    Chen, Yixin
    Chen, Xiaotian
    Wang, Wenjun
    Chen, Xu
    Wang, Qiushuang
    Zhang, Liwei
    Guo, Huayuan
    Liu, Bohan
    Yu, Liheng
    Pu, Haitao
    Zhang, Peifang
    Wu, Zhenzhou
    Li, Xin
    Burkhoff, Daniel
    He, Kunlun
    FRONTIERS IN CARDIOVASCULAR MEDICINE, 2022, 9
  • [2] LEFT-TO-RIGHT SHUNT IN ATRIAL SEPTAL-DEFECT - QUANTIFICATION BY ECHOCARDIOGRAPHY
    BODEM, R
    HO, A
    KUBLER, W
    STORCH, HH
    KLINISCHE WOCHENSCHRIFT, 1979, 57 (06): : 279 - 284
  • [3] DETECTION OF ATRIAL SEPTAL-DEFECT BY RIGHT STERNAL BORDER ECHOCARDIOGRAPHY
    ILICETO, S
    ANTONELLI, G
    SORINO, M
    RICCI, A
    AMERICAN JOURNAL OF CARDIOLOGY, 1984, 54 (03): : 376 - 378
  • [4] Latest Echocardiography: "Lifesaving" atrial Septal Defect
    Battyanyi, B.
    Fazekas, L.
    JOURNAL FUR KARDIOLOGIE, 2016, 23 (3-4): : 91 - 93
  • [5] Echocardiography guidance of atrial septal defect closure
    Rana, Bushra S.
    JOURNAL OF THORACIC DISEASE, 2018, 10 : S2899 - S2908
  • [6] Natural history of the atrial septal defect in the age of echocardiography
    Popelova, J
    Telekes, P
    Antonova, P
    EUROPEAN HEART JOURNAL, 2003, 24 : 9 - 9
  • [7] ECHOCARDIOGRAPHY IN DIAGNOSING ATRIAL SEPTAL-DEFECT (ASD)
    MALINOVSKII, NN
    YUDINTSEVA, IA
    BOBKOV, VV
    SOVETSKAYA MEDITSINA, 1976, (01): : 3 - 8
  • [8] Application of echocardiography on device closure of atrial septal defect
    Kang, Y.
    Tang, H.
    Song, H.
    Bai, W.
    An, Q.
    Lin, K.
    Zhang, E.
    EUROPEAN HEART JOURNAL SUPPLEMENTS, 2010, 12 (0A) : S20 - S21
  • [9] CONTRAST ECHOCARDIOGRAPHY IN THE DIAGNOSIS OF ATRIAL SEPTAL-DEFECT
    STOCKINS, B
    SAAVEDRA, J
    OPAZO, JA
    SALVATICI, R
    LANAS, F
    REVISTA MEDICA DE CHILE, 1980, 108 (07) : 612 - 615
  • [10] DETECTION OF SINUS VENOSUS ATRIAL SEPTAL-DEFECT BY 2-DIMENSIONAL ECHOCARDIOGRAPHY
    MUHLER, EG
    ENGELHARDT, W
    VONBERNUTH, G
    EUROPEAN HEART JOURNAL, 1992, 13 (04) : 453 - 456