Abstract
Delayed enhancement (DE)-MRI plays an important role in the diagnosis of various myocardial damages (such as myocardial infarct and no-reflow phenomenon). This paper proposes a hybrid U-net network to achieve the simultaneous segmentation of the background, left ventricle, left myocardium, myocardial infarction, and no-reflow regions in DE-MRI. The hybrid U-net architecture introduces the squeeze-and-excitation residual (SE-Res) module and selective kernel (SK) block in the encoder and decoder parts, respectively. The SE-Res module can address the dependencies of all feature channels, and increase the weight value on the more informative channel. The SK block can adaptively adjust the receptive field size to obtain the multi-scale feature information. Two types of labels (category label and segmentation label) and hybrid branches are used to control the whole segmentation process, which produces robust segmentation performance. The experimental result shows that the proposed model achieves high segmentation performance with the Dice score of 0.8455 for myocardium, 0.6455 for infarction, and 0.6698 for no-reflow on the validation set.
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
References
Chaurasia, A., Culurciello, E.: Linknet: exploiting encoder representations for efficient semantic segmentation. In: 2017 IEEE Visual Communications and Image Processing (VCIP), pp. 1–4. IEEE (2017)
Ciofolo, C., Fradkin, M., Mory, B., Hautvast, G., Breeuwer, M.: Automatic myocardium segmentation in late-enhancement MRI. In: 2008 5th IEEE International Symposium on Biomedical Imaging: from nano to macro, pp. 225–228. IEEE (2008)
Dikici, E., O’Donnell, T., Setser, R., White, R.D.: Quantification of delayed enhancement MR images. In: Barillot, C., Haynor, D.R., Hellier, P. (eds.) MICCAI 2004. LNCS, vol. 3216, pp. 250–257. Springer, Heidelberg (2004). https://doi.org/10.1007/978-3-540-30135-6_31
El Berbari, R., Kachenoura, N., Frouin, F., Herment, A., Mousseaux, E., Bloch, I.: An automated quantification of the transmural myocardial infarct extent using cardiac DE-MR images. In: 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 4403–4406. IEEE (2009)
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)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Lalande, A., et al.: Emidec: a database usable for the automatic evaluation of myocardial infarction from delayed-enhancement cardiac mri. Data 5(4), 89 (2020)
Li, X., Wang, W., Hu, X., Yang, J.: Selective kernel networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 510–519 (2019)
Pineda, V., Merino, X., Gispert, S., MahÃa, P., Garcia, B., DomÃnguez-Oronoz, R.: No-reflow phenomenon in cardiac MRI: diagnosis and clinical implications. Am. J. Roentgenol. 191(1), 73–79 (2008)
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
Samet, H., Tamminen, M.: Efficient component labeling of images of arbitrary dimension represented by linear bintrees. IEEE Trans. Pattern Anal. Mach. Intell. 10(4), 579–586 (1988)
Tao, Q., et al.: Automated segmentation of myocardial scar in late enhancement MRI using combined intensity and spatial information. Magn. Reson. Med. 64(2), 586–594 (2010)
Vos, T., et al.: Global, regional, and national incidence, prevalence, and years lived with disability for 310 diseases and injuries, 1990–2015: a systematic analysis for the global burden of disease study 2015. lancet 388(10053), 1545–1602 (2016)
Wei, D., Sun, Y., Ong, S.H., Chai, P., Teo, L.L., Low, A.F.: Three-dimensional segmentation of the left ventricle in late gadolinium enhanced MR images of chronic infarction combining long-and short-axis information. Med. Image Anal. 17(6), 685–697 (2013)
Xu, C., Xu, L., Brahm, G., Zhang, H., Li, S.: MuTGAN: simultaneous segmentation and quantification of myocardial infarction without contrast agents via joint adversarial learning. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11071, pp. 525–534. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00934-2_59
Xu, C., et al.: Direct delineation of myocardial infarction without contrast agents using a joint motion feature learning architecture. Med. Image Anal. 50, 82–94 (2018)
Xu, R.S., Athavale, P., Lu, Y., Radau, P., Wright, G.A.: Myocardial segmentation in late-enhancement MR images via registration and propagation of cine contours. In: 2013 IEEE 10th International Symposium on Biomedical Imaging, pp. 856–859. IEEE (2013)
Zhuang, X.: Multivariate mixture model for myocardial segmentation combining multi-source images. IEEE Trans. Pattern Anal. Mach. Intell. 41(12), 2933–2946 (2018)
Acknowledgement
This research was funded by the National Natural Science Foundation of China, grant number 61571314.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Yang, S., Wang, X. (2021). A Hybrid Network for Automatic Myocardial Infarction Segmentation in Delayed Enhancement-MRI. In: Puyol Anton, E., et al. Statistical Atlases and Computational Models of the Heart. M&Ms and EMIDEC Challenges. STACOM 2020. Lecture Notes in Computer Science(), vol 12592. Springer, Cham. https://doi.org/10.1007/978-3-030-68107-4_36
Download citation
DOI: https://doi.org/10.1007/978-3-030-68107-4_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-68106-7
Online ISBN: 978-3-030-68107-4
eBook Packages: Computer ScienceComputer Science (R0)
