skip to main content
10.1145/3265689.3265710acmotherconferencesArticle/Chapter ViewAbstractPublication PagesiccseConference Proceedingsconference-collections
research-article

Automatic Segmentation of Left Myocardium in CMR Based on Fully Convolutional Networks

Authors:
Yifan Du
School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China
,
Yuanlin Zhu
School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China
,
Shengjie Wu
School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China
,
Wang Lihui
Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province, School of Computer Science and Technology, Guizhou University, Guiyang China
,
Zhu YueMin
Univ. Lyon, INSA-Lyon, Université Claude Bernard Lyon 1, UJM-Saint Etienne, CNRS, Inserm, LYON France
,
Yang Feng
School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China
Authors Info & Claims
Published: 28 July 2018 Publication History

Abstract

Myocardial segmentation plays an important role for quantitative evaluation of heart diseases and cardiac image processing and analysis. However, myocardial segmentation has always been a challenging task because gray scale intensities of the myocardium and tissues around the heart are very close and that significant differences exist in myocardial structure between different slices or slices at different times. Traditional segmentation algorithms are difficult to obtain accurate and robust segmentation results and are usually semi-automatic which require manual operations and extra workload. Therefore, the development of a fully automatic myocardial segmentation algorithm is an appealing research goal. In this paper, we propose an automatic myocardial segmentation algorithm based on fully convolutional neural networks. By building an end-to-end model, the segmentation speed has been improved without affecting the segmentation accuracy. Performance comparisons between the proposed HeartNet and state-of-art methods demonstrated the effectiveness of our algorithm, which achieved an average DSC of 90.48% by segmenting 144.9 frames per second.

References

[1]
Cao Wu. 2016. Research on Image Segmentation Algorithm of Cardiac CT Sequence{D}. Biomedical Engineering, Beijing Jiaotong University.
[2]
Zhenhua Li, Xue Mei, Xiaoyao Guo, et al. 2015. Fuzzy-level Heart CT Image Sequence Segmentation Method{J}. Computer Engineering and Design, 2015(11): 3030--3034.
[3]
Cordero-Grande L, Vegas-Sanchez-Ferrero G, Casaseca-de-la-Higuera P, et al. 2011. Unsupervised 4D myocardium segmentation with a Markov Random Field based deformable model{J}. MED IMAGE ANAL, 2011,15(3): 283--301.
[4]
Qian X, Lin Y, Zhao Y, et al. 2015. Segmentation of myocardium from cardiac MR images using a novel dynamic programming based segmentation method{J}. MED PHYS, 2015,42(3): 1424--1435.
[5]
Yue Zhao, Yi Shen, Adeline Bernard, Christian Cachard, Herve Liebgott. 2017. Evaluation and Comparison of current biopsy needl localization and tacking methods using 3D ultrasound, Ultrasonics, 2017, 73: 206--220.
[6]
Lynch M, Ghita O, Whelan P F. 2006. Automatic segmentation of the left ventricle cavity and myocardium in MRI data{J}. COMPUT BIOL MED, 2006,36(4): 389--407.
[7]
C. Li, C. Y. Kao, J. C. Gore, and Z. Ding. 2008. Minimization of region-scalable fitting energy for image segmentation. IEEE Transactions on Image Processing, 17: 1940--1949, 2008.
[8]
Wantanajittikul K, Theera-Umpon N, Saekho S, et al. 2016. Automatic cardiac T2*relaxation time estimation from magnetic resonance images using region growing method with automatically initialized seed points{J}. COMPUT METH PROG BIO, 2016,130: 76--86.
[9]
Fanli Huang. 2015. Research on Heart CT Image Segmentation Algorithm Based on Random Forest Model{D}. Chongqing University, 2015. 58.
[10]
Guibao Cao. 2014. Application of Random Forest and Convolutional Neural Network in Image Segmentation of Neurons{D}. Computer Application Technology of Shandong University, 2014.
[11]
Ciofolo C, Fradkin M, Mory B, et al. 2008. Automatic myocardium segmentation in late-enhancement MRI{M}//IEEE International Symposium on Biomedical Imaging. 2008:225.
[12]
Dong Y, Frey E, Madar I, et al. 2014. Automatic segmentation of left ventricle myocardium volume-of-interest from cardiac PET images{J}. J NUCL MED, 2014,551.
[13]
Tufvesson J, Carlsson M, Aletras A H, et al. 2016. Automatic segmentation of myocardium at risk from contrast enhanced SSFP CMR: validation against expert readers and SPECT{J}. BMC MED IMAGING, 2016,16(19).
[14]
Ronneberger O,Fischer P,Brox T. 2015. U-Net:Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015.
[15]
Wang, Y., Seguro, F., Kao, E., Zhang, Y., Faraji, F., Zhu, C., Haraldsson, H., Hope, M., Saloner, D., and Liu. J. 2017. Segmentation of lumen and outer wall of abdominal aortic aneurysms from 3D black-blood MRI with a registration based geodesic active contour model. Medical image analysis 40 (2017): 1.
[16]
Wang, Y., Navarro, L., Zhang, Y., Kao, E., Zhu, Y. M., and Courbebaisse, G. 2017. Intracranial aneurysm phantom segmentation using a 4D lattice Boltzmann method. Computing in Science & Engineering 19, no 4 (2017): 56--67.
[17]
Chao Cong. 2013. Quantitative Evaluation Framework of Medical Heart Image Segmentation Algorithm{J}. Journal of Chongqing University of Technology (Natural Science), 2013(07): 71--75.
[18]
Shengjie Wu, Feng Yang, Gaoyun An. 2017. An Automatic Segmentation of Left Myorcardium Based on SSD Model and CNN. 2017 The International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), Nov. 2017, Xiamen, China.

Index Terms

  1. Automatic Segmentation of Left Myocardium in CMR Based on Fully Convolutional Networks

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Other conferences
    ICCSE'18: Proceedings of the 3rd International Conference on Crowd Science and Engineering
    July 2018
    220 pages
    ISBN:9781450365871
    DOI:10.1145/3265689
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from Permissions@acm.org

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 28 July 2018

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. Deep learning
    2. convolutional neural network
    3. myocardium segmentation

    Qualifiers

    • Research-article
    • Research
    • Refereed limited

    Conference

    ICCSE'18

    Acceptance Rates

    ICCSE'18 Paper Acceptance Rate 33 of 89 submissions, 37%;
    Overall Acceptance Rate 92 of 247 submissions, 37%

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • 0
      Total Citations
    • 59
      Total Downloads
    • Downloads (Last 12 months)2
    • Downloads (Last 6 weeks)0
    Reflects downloads up to 16 Jan 2025

    Other Metrics

    Citations

    Media

    Figures

    Other

    Tables

    Share

    Share

    Share this Publication link

    Share on social media

    Get Access

    Get Access

    Login options

    References

    References

    [1]
    Cao Wu. 2016. Research on Image Segmentation Algorithm of Cardiac CT Sequence{D}. Biomedical Engineering, Beijing Jiaotong University.
    [2]
    Zhenhua Li, Xue Mei, Xiaoyao Guo, et al. 2015. Fuzzy-level Heart CT Image Sequence Segmentation Method{J}. Computer Engineering and Design, 2015(11): 3030--3034.
    [3]
    Cordero-Grande L, Vegas-Sanchez-Ferrero G, Casaseca-de-la-Higuera P, et al. 2011. Unsupervised 4D myocardium segmentation with a Markov Random Field based deformable model{J}. MED IMAGE ANAL, 2011,15(3): 283--301.
    [4]
    Qian X, Lin Y, Zhao Y, et al. 2015. Segmentation of myocardium from cardiac MR images using a novel dynamic programming based segmentation method{J}. MED PHYS, 2015,42(3): 1424--1435.
    [5]
    Yue Zhao, Yi Shen, Adeline Bernard, Christian Cachard, Herve Liebgott. 2017. Evaluation and Comparison of current biopsy needl localization and tacking methods using 3D ultrasound, Ultrasonics, 2017, 73: 206--220.
    [6]
    Lynch M, Ghita O, Whelan P F. 2006. Automatic segmentation of the left ventricle cavity and myocardium in MRI data{J}. COMPUT BIOL MED, 2006,36(4): 389--407.
    [7]
    C. Li, C. Y. Kao, J. C. Gore, and Z. Ding. 2008. Minimization of region-scalable fitting energy for image segmentation. IEEE Transactions on Image Processing, 17: 1940--1949, 2008.
    [8]
    Wantanajittikul K, Theera-Umpon N, Saekho S, et al. 2016. Automatic cardiac T2*relaxation time estimation from magnetic resonance images using region growing method with automatically initialized seed points{J}. COMPUT METH PROG BIO, 2016,130: 76--86.
    [9]
    Fanli Huang. 2015. Research on Heart CT Image Segmentation Algorithm Based on Random Forest Model{D}. Chongqing University, 2015. 58.
    [10]
    Guibao Cao. 2014. Application of Random Forest and Convolutional Neural Network in Image Segmentation of Neurons{D}. Computer Application Technology of Shandong University, 2014.
    [11]
    Ciofolo C, Fradkin M, Mory B, et al. 2008. Automatic myocardium segmentation in late-enhancement MRI{M}//IEEE International Symposium on Biomedical Imaging. 2008:225.
    [12]
    Dong Y, Frey E, Madar I, et al. 2014. Automatic segmentation of left ventricle myocardium volume-of-interest from cardiac PET images{J}. J NUCL MED, 2014,551.
    [13]
    Tufvesson J, Carlsson M, Aletras A H, et al. 2016. Automatic segmentation of myocardium at risk from contrast enhanced SSFP CMR: validation against expert readers and SPECT{J}. BMC MED IMAGING, 2016,16(19).
    [14]
    Ronneberger O,Fischer P,Brox T. 2015. U-Net:Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015.
    [15]
    Wang, Y., Seguro, F., Kao, E., Zhang, Y., Faraji, F., Zhu, C., Haraldsson, H., Hope, M., Saloner, D., and Liu. J. 2017. Segmentation of lumen and outer wall of abdominal aortic aneurysms from 3D black-blood MRI with a registration based geodesic active contour model. Medical image analysis 40 (2017): 1.
    [16]
    Wang, Y., Navarro, L., Zhang, Y., Kao, E., Zhu, Y. M., and Courbebaisse, G. 2017. Intracranial aneurysm phantom segmentation using a 4D lattice Boltzmann method. Computing in Science & Engineering 19, no 4 (2017): 56--67.
    [17]
    Chao Cong. 2013. Quantitative Evaluation Framework of Medical Heart Image Segmentation Algorithm{J}. Journal of Chongqing University of Technology (Natural Science), 2013(07): 71--75.
    [18]
    Shengjie Wu, Feng Yang, Gaoyun An. 2017. An Automatic Segmentation of Left Myorcardium Based on SSD Model and CNN. 2017 The International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), Nov. 2017, Xiamen, China.