Fully Automated Multi-heartbeat Echocardiography Video Segmentation and Motion Tracking

被引:4
作者
Chen, Yida [1 ]
Zhang, Xiaoyan [2 ]
Haggerty, Christopher M. [2 ]
Stough, Joshua, V [1 ]
机构
[1] Bucknell Univ, Comp Sci, Lewisburg, PA 17837 USA
[2] Geisinger, Translat Data Sci & Informat, Danville, PA USA
来源
MEDICAL IMAGING 2022: IMAGE PROCESSING | 2022年 / 12032卷
关键词
Echocardiography; Segmentation; Quantitative Image Analysis; Neural Networks; VENTRICULAR EJECTION FRACTION; VOLUMES;
D O I
10.1117/12.2607871
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Neural network-based video segmentation has proven effective in producing temporally-coherent segmentation and motion tracking of heart substructures in echocardiography. However, prior methods confine analysis to half-heartbeat systolic phase clips from end-diastole (ED) to end-systole (ES), requiring the specification of these frames in the video and limiting clinical applicability. Here we introduce CLAS-FV, a fully automated framework that extends upon this prior work, providing joint semantic segmentation and motion tracking in multi-beat echocardiograms. Our framework first employs a modified R2+1D ResNet stem, which is efficient in encoding spatiotemporal features, and further leverages sliding windows for both training and test time augmentation to accommodate the full cardiac cycle. First, through 10-fold cross-validation on the half-beat CAMUS dataset, we show that the R2+1D-based stem outperforms the prior 3D U-Net both in Dice overlap for all substructures, and in derived clinical indices of ED and ES ventricular volumes and ejection fraction (EF). Next, we use the large clinical EchoNet-Dynamic dataset to extend our framework to full multi-beat video segmentation. We obtain mean Dice overlap of 0.94/0.91 on left ventricle endocardium in ED/ES phases, and accurately infer EF (mean absolute error 5.3%) over 1269 test patients. The presented multi-heartbeat video segmentation framework promises fast and coherent segmentation and motion tracking for the rich phenotypic analysis of echocardiography.
引用
收藏
页数:8
相关论文
共 19 条
  • [1] Symmetric diffeomorphic image registration with cross-correlation: Evaluating automated labeling of elderly and neurodegenerative brain
    Avants, B. B.
    Epstein, C. L.
    Grossman, M.
    Gee, J. C.
    [J]. MEDICAL IMAGE ANALYSIS, 2008, 12 (01) : 26 - 41
  • [2] VoxelMorph: A Learning Framework for Deformable Medical Image Registration
    Balakrishnan, Guha
    Zhao, Amy
    Sabuncu, Mert R.
    Guttag, John
    Dalca, Adrian, V
    [J]. IEEE TRANSACTIONS ON MEDICAL IMAGING, 2019, 38 (08) : 1788 - 1800
  • [3] Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensation
    Caballero, Jose
    Ledig, Christian
    Aitken, Andrew
    Acosta, Alejandro
    Totz, Johannes
    Wang, Zehan
    Shi, Wenzhe
    [J]. 30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 2848 - 2857
  • [4] Assessing the Generalizability of Temporally-Coherent Echocardiography Video Segmentation
    Chen, Yida
    Zhang, Xiaoyan
    Haggerty, Christopher M.
    Stough, Joshua, V
    [J]. MEDICAL IMAGING 2021: IMAGE PROCESSING, 2021, 11596
  • [5] Cicek Ozgun, 2016, Medical Image Computing and Computer-Assisted Intervention - MICCAI 2016. 19th International Conference. Proceedings: LNCS 9901, P424, DOI 10.1007/978-3-319-46723-8_49
  • [6] ASSESSMENT OF LEFT-VENTRICULAR EJECTION FRACTION AND VOLUMES BY REAL-TIME, 2-DIMENSIONAL ECHOCARDIOGRAPHY - COMPARISON OF CINEANGIOGRAPHIC AND RADIONUCLIDE TECHNIQUES
    FOLLAND, ED
    PARISI, AF
    MOYNIHAN, PF
    JONES, DR
    FELDMAN, CL
    TOW, DE
    [J]. CIRCULATION, 1979, 60 (04) : 760 - 766
  • [7] Label Fusion in Atlas-Based Segmentation Using a Selective and Iterative Method for Performance Level Estimation (SIMPLE)
    Langerak, Thomas Robin
    van der Heide, Uulke A.
    Kotte, Alexis N. T. J.
    Viergever, Max A.
    van Vulpen, Marco
    Pluim, Josien P. W.
    [J]. IEEE TRANSACTIONS ON MEDICAL IMAGING, 2010, 29 (12) : 2000 - 2008
  • [8] Deep Learning for Segmentation Using an Open Large-Scale Dataset in 2D Echocardiography
    Leclerc, Sarah
    Smistad, Erik
    Pedrosa, Joao
    Ostvik, Andreas
    Cervenansky, Frederic
    Espinosa, Florian
    Espeland, Torvald
    Berg, Erik Andreas Rye
    Jodoin, Pierre-Marc
    Grenier, Thomas
    Lartizien, Carole
    D'hooge, Jan
    Lovstakken, Lasse
    Bernard, Olivier
    [J]. IEEE TRANSACTIONS ON MEDICAL IMAGING, 2019, 38 (09) : 2198 - 2210
  • [9] Recurrent Aggregation Learning for Multi-view Echocardiographic Sequences Segmentation
    Li, Ming
    Zhang, Weiwei
    Yang, Guang
    Wang, Chengjia
    Zhang, Heye
    Liu, Huafeng
    Zheng, Wei
    Li, Shuo
    [J]. MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2019, PT II, 2019, 11765 : 678 - 686
  • [10] Video-based AI for beat-to-beat assessment of cardiac function
    Ouyang, David
    He, Bryan
    Ghorbani, Amirata
    Yuan, Neal
    Ebinger, Joseph
    Langlotz, Curtis P.
    Heidenreich, Paul A.
    Harrington, Robert A.
    Liang, David H.
    Ashley, Euan A.
    Zou, James Y.
    [J]. NATURE, 2020, 580 (7802) : 252 - +