Automatic extraction of coronary arteries using deep learning in invasive coronary angiograms

被引:6
|
作者
Meng, Yinghui [1 ]
Du, Zhenglong [1 ]
Zhao, Chen [2 ]
Dong, Minghao [1 ]
Pienta, Drew [3 ]
Tang, Jinshan [4 ]
Zhou, Weihua [2 ,5 ,6 ]
机构
[1] Zhengzhou Univ Light Ind, Sch Comp & Commun Engn, Zhengzhou, Henan, Peoples R China
[2] Michigan Technol Univ, Dept Appl Comp, 1400 Townsend Dr, Houghton, MI 49931 USA
[3] Michigan Technol Univ, Dept Mech Engn Engn Mech, Houghton, MI 49931 USA
[4] George Mason Univ, Dept Hlth Adm & Policy, Coll Hlth & Human Serv, Fairfax, VA 22030 USA
[5] Michigan Technol Univ, Inst Comp & Cybersyst, Ctr Biocomp & Digital Hlth, Houghton, MI 49931 USA
[6] Michigan Technol Univ, Hlth Res Inst, Houghton, MI 49931 USA
关键词
Coronary artery disease; invasive coronary angiography; image segmentation; deep learning; convolutional neural network; SEGMENTATION; VESSELS; NETWORK;
D O I
10.3233/THC-230278
中图分类号
R19 [保健组织与事业(卫生事业管理)];
学科分类号
摘要
BACKGROUND: Accurate extraction of coronary arteries from invasive coronary angiography (ICA) images is essential for the diagnosis and risk stratification of coronary artery disease (CAD). OBJECTIVE: In this study, a novel deep learning (DL) method is proposed for automatically extracting coronary arteries from ICA images. METHODS: A convolutional neural network (CNN) was developed with full-scale skip connections and full-scale deep supervisions. The encoder architecture was based on the residual and inception modules to obtain multi-scale features from multiple convolutional layers with different window shapes. Transfer learning was utilized to improve both the initial performance and learning efficiency. A hybrid loss function was employed to further optimize the segmentation model. RESULTS: The model was tested on a data set of 616 ICAs obtained from 210 patients, composed of 437 images for training, 49 images for validation, and 130 images for testing. The segmentation model achieved a Dice score of 0.8942, a sensitivity of 0.8735, a specificity of 0.9954, and a Hausdorff distance of 6.0794 mm; it could predict arteries for a single ICA frame in 0.2114 seconds. CONCLUSIONS: The results showed that our model outperformed the state-of-the-art deep-learning models. Our new method has great potential for clinical use.
引用
收藏
页码:2303 / 2317
页数:15
相关论文
共 50 条
  • [41] Computerized analysis of coronary artery disease: Performance evaluation of segmentation and tracking of coronary arteries in CT angiograms
    Zhou, Chuan
    Chan, Heang-Ping
    Chughtai, Aamer
    Kuriakose, Jean
    Agarwal, Prachi
    Kazerooni, Ella A.
    Hadjiiski, Lubomir M.
    Patel, Smita
    Wei, Jun
    MEDICAL PHYSICS, 2014, 41 (08) : 372 - 382
  • [42] Prognostic value of abnormal vasoreactivity of epicardial coronary arteries to sympathetic stimulation in patients with normal coronary angiograms
    Schindler, TH
    Hornig, B
    Buser, PT
    Olschewski, M
    Magosaki, N
    Pfisterer, M
    Nitzsche, EU
    Solzbach, U
    Just, H
    ARTERIOSCLEROSIS THROMBOSIS AND VASCULAR BIOLOGY, 2003, 23 (03) : 495 - 501
  • [43] Segmentation Method Based on Transition Region Extraction for Coronary Angiograms
    Kang, Wenwei
    Wang, Ke
    Wang, Qingzhu
    An, Donghong
    2009 IEEE INTERNATIONAL CONFERENCE ON MECHATRONICS AND AUTOMATION, VOLS 1-7, CONFERENCE PROCEEDINGS, 2009, : 905 - +
  • [44] An automatic deep learning approach for coronary artery calcium segmentation
    Santini, G.
    Della Latta, D.
    Martini, N.
    Valvano, G.
    Gori, A.
    Ripoli, A.
    Susini, C. L.
    Landini, L.
    Chiappino, D.
    EMBEC & NBC 2017, 2018, 65 : 374 - 377
  • [45] Deep learning for automatic diagnosis of coronary artery disease using SPECT MPI images
    Papandrianos, N.
    Feleki, A.
    Kokkinos, K.
    Apostolopoulos, D.
    Papageorgiou, E.
    EUROPEAN JOURNAL OF NUCLEAR MEDICINE AND MOLECULAR IMAGING, 2022, 49 (SUPPL 1) : S617 - S617
  • [46] Deep learning approaches for image restoration in invasive coronary angiography
    Oh, S. U.
    Park, H. B.
    Jeong, H. S.
    Lee, J. N.
    Heo, R.
    Hong, Y. T.
    Chang, H. J.
    EUROPEAN HEART JOURNAL, 2024, 45
  • [47] Automatic segmentation of coronary arteries using Bayesian driven implicit surfaces
    Yang, Yan
    Tannenbaum, Allen
    Giddens, Don
    Stillman, Arthur
    2007 4TH IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING : MACRO TO NANO, VOLS 1-3, 2007, : 189 - +
  • [48] Automatic Segmentation of Coronary Arteries and Detection of Stenosis
    Mirunalini, P.
    Aravindan, Chandrabose
    2013 IEEE INTERNATIONAL CONFERENCE OF IEEE REGION 10 (TENCON), 2013,
  • [49] Patient-Specific Computational Models of Coronary Arteries Using Monoplane X-Ray Angiograms
    Zifan, Ali
    Liatsis, Panos
    COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE, 2016, 2016
  • [50] Decreasing Unnecessary Invasive Coronary Angiograms With Photon-Counting Detector Coronary Computed Tomography Angiography
    Einstein, Andrew J.
    JOURNAL OF THE AMERICAN COLLEGE OF CARDIOLOGY, 2025, 85 (04) : 349 - 351