Unsupervised Image Segmentation on 2D Echocardiogram

被引:1
|
作者
Cacao, Gabriel Farias [1 ]
Du, Dongping [1 ]
Nair, Nandini [2 ]
机构
[1] Texas Tech Univ, Dept Ind Mfg & Syst Engn IMSE, Lubbock, TX 79409 USA
[2] Milton S Hershey Med Ctr, Heart & Vasc Inst, PennState Coll Med, 500 Univ Dr, Hershey, PA 17033 USA
关键词
unsupervised learning; image segmentation; echocardiography; convolutional neural networks; medical imaging;
D O I
10.3390/a17110515
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Echocardiography is a widely used, non-invasive imaging technique for diagnosing and monitoring heart conditions. However, accurate segmentation of cardiac structures, particularly the left ventricle, remains a complex task due to the inherent variability and noise in echocardiographic images. Current supervised models have achieved state-of-the-art results but are highly dependent on large, annotated datasets, which are costly and time-consuming to obtain and depend on the quality of the annotated data. These limitations motivate the need for unsupervised methods that can generalize across different image conditions without relying on annotated data. In this study, we propose an unsupervised approach for segmenting 2D echocardiographic images. By combining customized objective functions with convolutional neural networks (CNNs), our method effectively segments cardiac structures, addressing the challenges posed by low-resolution and gray-scale images. Our approach leverages techniques traditionally used outside of medical imaging, optimizing feature extraction through CNNs in a data-driven manner and with a new and smaller network design. Another key contribution of this work is the introduction of a post-processing algorithm that refines the segmentation to isolate the left ventricle in both diastolic and systolic positions, enabling the calculation of the ejection fraction (EF). This calculation serves as a benchmark for evaluating the performance of our unsupervised method. Our results demonstrate the potential of unsupervised learning to improve echocardiogram analysis by overcoming the limitations of supervised approaches, particularly in settings where labeled data are scarce or unavailable.
引用
收藏
页数:28
相关论文
共 50 条
  • [1] An unsupervised color image segmentation based on morphological 2D clustering and fusion
    Lezoray, O
    CGIV 2004: SECOND EUROPEAN CONFERENCE ON COLOR IN GRAPHICS, IMAGING, AND VISION - CONFERENCE PROCEEDINGS, 2004, : 173 - 177
  • [2] Unsupervised 2D gel electrophoresis image segmentation based on active contours
    Savelonas, Michalis A.
    Mylona, Eleftheria A.
    Maroulis, Dimitris
    PATTERN RECOGNITION, 2012, 45 (02) : 720 - 731
  • [3] Unsupervised 2D multiband histogram clustering and region merging for color image segmentation
    Lezoray, O
    PROCEEDINGS OF THE 3RD IEEE INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING AND INFORMATION TECHNOLOGY, 2003, : 267 - 270
  • [4] Unsupervised texture segmentation for 2D probabilistic occupancy maps
    Abou Merhy, Bassel
    Payeur, Pierre
    Petriu, Emil M.
    ROSE 2005: PROCEEDINGS OF THE 2005 IEEE INTERNATIONAL WORKSHOP ON ROBOTIC SENSING: ROBOTIC AND SENSORS ENVIRONMENTS, 2005, : 40 - 45
  • [5] Unsupervised Learning for 2D Image Texture Enhancement
    Labinghisa, Boney
    Kim, Jeong-Su
    Lee, Dong Myung
    12TH INTERNATIONAL CONFERENCE ON ICT CONVERGENCE (ICTC 2021): BEYOND THE PANDEMIC ERA WITH ICT CONVERGENCE INNOVATION, 2021, : 587 - 589
  • [6] Adversarial Unsupervised Domain Adaptation for 3D Semantic Segmentation with 2D Image Fusion of Dense Depth
    Zhang, Xindan
    Li, Ying
    Sheng, Huankun
    Zhang, Xinnian
    COMPUTER GRAPHICS FORUM, 2024, 43 (07)
  • [7] Unsupervised segmentation of 3D and 2D seismic reflection data
    Köster, K
    Spann, M
    VISION INTERFACE - REAL WORLD APPLICATIONS OF COMPUTER VISION, 1999, 35 : 57 - 77
  • [8] Unsupervised segmentation of 3D and 2D seismic reflection data
    Köster, K
    Spann, M
    INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 1999, 13 (05) : 643 - 663
  • [9] Dynamic edge tracing for 2D image segmentation
    Withey, DJ
    Koles, ZJ
    Pedrycz, W
    PROCEEDINGS OF THE 23RD ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY, VOLS 1-4: BUILDING NEW BRIDGES AT THE FRONTIERS OF ENGINEERING AND MEDICINE, 2001, 23 : 2657 - 2660
  • [10] Video segmentation based on 2D image analysis
    Guimaraes, SJF
    Couprie, M
    Araújo, AD
    Leite, NJ
    PATTERN RECOGNITION LETTERS, 2003, 24 (07) : 947 - 957