Abstract
Along with the widespread achievement of machine learning in computer vision in recent years, plenty of deep learning models for medical image segmentation have been published, with impressive results. However, the majority of those model just leverages supervised technics while others additionally utilize semi-supervised and unsupervised technics, with the results are not as good as supervised ones though. Inspired by the efficiency of Mumford-Shah functional for unsupervised and Active Contour functional for supervised tasks, in this work, we proposed the new loss functional which integrates those two with some modifications and extension to the case of multiphase segmentation. It allows our deep learning model to segment multi-class simultaneously with high accuracy instead of binary segmentation. The proposed approach is applied to the segmentation of left ventricle from cardiac MR images, in which both endocardium and epicardium are simultaneously segmented. Our proposed method is assessed on 2017 ACDCA dataset. The experiment demonstrates that our new loss achieves the promising results in term of Dice coefficient and Jaccard index. This illuminates the efficiency of our method in multi-class segmentation for medical images.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
B. Jähne, H. Haußecker, Computer vision and applications (2000)
T. Zhou, S. Ruan, S. Canu, A review: deep learning for medical image segmentation using multi-modality fusion. Array 3, 100004 (2019)
D. Mumford, J. Shah, Optimal approximations by piecewise smoothfunctions and associated variational problems. Commun. Pure Appl. Math. 42(5), 577–685 (1989)
T. Chan, L. Vese, Active contours without edges. IEEE Trans. Image Process. 10(2), 266–277 (2001)
A. Chambolle, T. Pock, A first-order primal-dual algorithm for convex problems with applications to imaging. J. Math. Imaging Vis. 40(1), 120–145 (2011)
A. Sinha, J. Dolz, Multi-scale self-guided attention for medical image segmentation. IEEE J. Biomed. Health Inform. (2020)
Z. Zhou, M.M.R. Siddiquee, N. Tajbakhsh, J. Liang, Unet++: redesigning skip connections to exploit multiscale features in image segmentation. IEEE Trans. Med. Imaging 39(6), 1856–1867 (2019)
R. Azad, M. Asadi-Aghbolaghi, M. Fathy, S. Escalera, Bi-directional ConvLSTM U-net with Densley connected convolutions, in Proceedings of the IEEE International Conference on Computer Vision Workshops, 2019
O. Ronneberger, P. Fischer, T. Brox, U-net: Convolutional networks for biomedical image segmentation, in International Conference on Medical Image Computing and Computer-Assisted Intervention (Springer, 2015), pp. 234–241
S.S.M. Salehi, D. Erdogmus, A. Gholipour, Tversky loss function for image segmentation using 3D fully convolutional deep networks, in International Workshop on Machine Learning in Medical Imaging (Springer, 2017), pp. 379–387
T.T. Tran, T.-T. Tran, Q.C. Ninh, M.D. Bui, V.-T. Pham, Segmentation of left ventricle in short-axis MR images based on fully convolutional network and active contour model, in International Conference on Green Technology and Sustainable Development (Springer, 2020), pp. 49–59
S. Jégou, M. Drozdzal, D. Vazquez, A. Romero, Y. Bengio, The one hundred layers tiramisu: fully convolutional densenets for semantic segmentation, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2017, pp. 11–19
D. Jha, M. Riegler, D. Johansen, P. Halvorsen, H. Johansen, Doubleu-net: a deep convolutional neural network for medical image segmentation, in IEEE 33rd International Symposium on Computer-Based Medical Systems (CBMS), 2020, pp. 558–564
X. Chen, B.M. Williams, S.R. Vallabhaneni, G. Czanner, R. Williams, Y. Zheng, Learning active contour models for medical image segmentation, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019, pp. 11632–11640
S.R. Hashemi, S.S.M. Salehi, D. Erdogmus, S.P. Prabhu, S.K. Warfield, A. Gholipour, Asymmetric loss functions and deep densely-connected networks for highly-imbalanced medical image segmentation: Application to multiple sclerosis lesion detection. IEEE Access 7, 1721–1735 (2018)
V.T. Pham, T.T. Tran, P.C. Wang, M.T. Lo, Tympanic membrane segmentation in otoscopic images based on fully convolutional network with active contour loss. Signal Image Video Process. https://doi.org/10.1007/s11760-020-01772-7 (2020)
S. Gur, L. Wolf, L. Golgher, P. Blinder, Unsupervised microvascular image segmentation using an active contours mimicking neural network, in Proceedings of the IEEE International Conference on Computer Vision, 2019, pp. 10722–10731
B. Kim, J.C. Ye, Mumford-Shah loss functional for image segmentation with deep learning. IEEE Trans. Image Process. 29, 1856–1866 (2019)
T.F. Chan, L.A. Vese, Image segmentation using level sets and the piecewise-constant Mumford-Shah model, in Tech. Rep. 0014, Computational Applied Math Group 2000. Citeseer
V.-T. Pham, T.-T. Tran, Active contour model and nonlinear shape priors with application to left ventricle segmentation in cardiac MR images. Optik 127(3), 991–1002 (2016)
M. Tan, Q.V. Le, Efficientnet: rethinking model scaling for convolutional neural networks. arXiv:1905.11946 (2019)
B. Xu, N. Wang, T. Chen, M. Li, Empirical evaluation of rectified activations in convolutional network. arXiv:1505.00853 (2015)
K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770–778
A. Tato, R. Nkambou, Improving adam optimizer (2018)
O. Bernard, A. Lalande, C. Zotti, F. Cervenansky, X. Yang, P.-A. Heng, I. Cetin, K. Lekadir, O. Camara, M.A.G. Ballester, Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: is the problem solved? IEEE Trans. Med. Imaging 37(11), 2514–2525 (2018)
P.V. Tran, A fully convolutional neural network for cardiac segmentation in short-axis MRI. arXiv:1604.00494 (2016)
V. Badrinarayanan, A. Kendall, R. Cipolla, Segnet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(12), 2481–2495 (2017)
Acknowledgements
This research is funded by Vietnam National Foundation for Science and Technology Development (NAFOSTED) under grant number 102.05-2018.302.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Trinh, MN., Nguyen, NT., Tran, TT., Pham, VT. (2022). A Semi-supervised Deep Learning-Based Approach with Multiphase Active Contour Loss for Left Ventricle Segmentation from CMR Images. In: Poonia, R.C., Singh, V., Singh Jat, D., Diván, M.J., Khan, M.S. (eds) Proceedings of Third International Conference on Sustainable Computing. Advances in Intelligent Systems and Computing, vol 1404. Springer, Singapore. https://doi.org/10.1007/978-981-16-4538-9_2
Download citation
DOI: https://doi.org/10.1007/978-981-16-4538-9_2
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-4537-2
Online ISBN: 978-981-16-4538-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)