Abstract
Automatic and accurate myocardial scar segmentation from multiple-sequence cardiac MRI is essential for the diagnosis and prognosis of patients with myocardial infarction. However, this is difficult due to motion artifact, low contrast between scar and blood pool in late gadolinium enhancement (LGE) MRI, and poor contrast between edema and healthy myocardium in T2 cardiac MRI. In this paper, we proposed a fully-automatic scar segmentation method using a cascaded segmentation network of three Fully Convolutional Densenet (FC-Densenet) with Inception and Squeeze-Excitation module. It is called Cascaded FCDISE. The first FCDISE is used to extract the region of interest and the second FCDISE to segment myocardium and the last one to segment scar from the pre-segmented myocardial region. In the proposed segmentation network, the inception module is incorporated at the beginning of the network to extract multi-scale features from the input image, whereas the squeeze-excitation blocks are placed in the skip connections of the network to transfer recalibrated feature maps from the encoder to the decoder. To encourage higher order similarities between predicted image and ground truth, we adopted a dual loss function composed of logarithmic Dice loss and region mutual information (RMI) loss. Our method is evaluated on the Multi-sequence CMR based Myocardial Pathology Segmentation challenge (MyoPS 2020) dataset. On the test set, our fully-automatic approach achieved an average Dice score of 0.565 for scar and 0.664 for scar\(+\)edema. This is higher than the inter-observer variation of manual scar segmentation. The proposed method outperformed similar methods and showed that adding the two modules to FC-Densenet improves the segmentation result with little computational overhead.
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
Amado, L.C., et al.: Accurate and objective infarct sizing by contrast-enhanced magnetic resonance imaging in a canine myocardial infarction model. J. Am. Coll. Cardiol. 44(12), 2383–2389 (2004)
Belleza, M.: Myocardial infarction: Nursing management and study guide (2017). https://nurseslabs.com/myocardial-infarction/. Accessed 10 June 2020
Detsky, J.S., Paul, G., Dick, A.J., Wright, G.A.: Reproducible classification of infarct heterogeneity using fuzzy clustering on multicontrast delayed enhancement magnetic resonance images. IEEE Trans. Med. Imaging 28(10), 1606–1614 (2009)
He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1026–1034 (2015)
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132–7141 (2018)
Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708 (2017)
Jégou, S., Drozdzal, M., Vazquez, D., Romero, A., Bengio, Y.: The one hundred layers Tiramisu: fully convolutional DenseNets for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 11–19 (2017)
Khened, M., Kollerathu, V.A., Krishnamurthi, G.: Fully convolutional multi-scale residual DenseNets for cardiac segmentation and automated cardiac diagnosis using ensemble of classifiers. Med. Image Anal. 51, 21–45 (2019)
Kim, R.J., et al.: Relationship of MRI delayed contrast enhancement to irreversible injury, infarct age, and contractile function. Circulation 100(19), 1992–2002 (1999)
Moccia, S., et al.: Development and testing of a deep learning-based strategy for scar segmentation on CMR-LGE images. Magn. Reson. Mater. Phys. Biol. Med 32(2), 187–195 (2019)
Oktay, O., et al.: Attention U-Net: learning where to look for the pancreas. arXiv preprint arXiv:1804.03999 (2018)
Organization, W.H.: Cardiovascular diseases (CVDs) (2017). https://www.who.int/news-room/fact-sheets/detail/cardiovascular-diseases-(cvds). Accessed 04 June 2020
Positano, V., et al.: A fast and effective method to assess myocardial necrosis by means of contrast magnetic resonance imaging. J. Cardiovasc. Magn. Reson. 7(2), 487–494 (2005)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
de la Rosa, E., Sidibé, D., Decourselle, T., Leclercq, T., Cochet, A., Lalande, A.: Myocardial infarction quantification from late gadolinium enhancement MRI using top-hat transforms and neural networks. arXiv preprint arXiv:1901.02911 (2019)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826 (2016)
Wong, K.C.L., Moradi, M., Tang, H., Syeda-Mahmood, T.: 3D segmentation with exponential logarithmic loss for highly unbalanced object sizes. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11072, pp. 612–619. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00931-1_70
Zabihollahy, F., White, J.A., Ukwatta, E.: Myocardial scar segmentation from magnetic resonance images using convolutional neural network. In: Medical Imaging 2018: Computer-Aided Diagnosis, vol. 10575, p. 105752Z. International Society for Optics and Photonics (2018)
Zhao, S., Wang, Y., Yang, Z., Cai, D.: Region mutual information loss for semantic segmentation. In: Advances in Neural Information Processing Systems, pp. 11117–11127 (2019)
Zhuang, X.: Multivariate mixture model for cardiac segmentation from multi-sequence MRI. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 581–588. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46723-8_67
Zhuang, X.: Multivariate mixture model for myocardial segmentation combining multi-source images. IEEE Trans. Pattern Anal. Mach. Intell. 41(12), 2933–2946 (2019)
Acknowledgements
T.W. Arega received an Erasmus+ scholarship from the Erasmus Mundus Joint Master Degree in Medical Imaging and Applications (MAIA), a program funded by the Erasmus+ program of the European Union. This work was also supported by the French National Research Agency (ANR), with reference ANR-19-CE45-0001-01-ACCECIT.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Arega, T.W., Bricq, S. (2020). Automatic Myocardial Scar Segmentation from Multi-sequence Cardiac MRI Using Fully Convolutional Densenet with Inception and Squeeze-Excitation Module. In: Zhuang, X., Li, L. (eds) Myocardial Pathology Segmentation Combining Multi-Sequence Cardiac Magnetic Resonance Images. MyoPS 2020. Lecture Notes in Computer Science(), vol 12554. Springer, Cham. https://doi.org/10.1007/978-3-030-65651-5_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-65651-5_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-65650-8
Online ISBN: 978-3-030-65651-5
eBook Packages: Computer ScienceComputer Science (R0)