Abstract
Segmenting cardiac scars and edema from cardiac magnetic resonance (CMR) are essential for the early diagnosis and accurate prognostic assessment of ischemic heart disease. The pathological myocardium presents distinctive brightness in the late gadolinium enhancement (LGE) images, the T2-weighted CMR shows the acute injury and ischemic regions, and the balanced-Steady State Free Precession (bSSFP) can clearly reveal the boundaries of the myocardium. Given this fact, we proposed a novel fully-automatic two-stage method to extract different features of each modality as well as segment myocardium edema and scars. In the first stage, a U-net was trained on bSSFP images with full annotation of myocardium, which can locate the coarse position of the myocardium and obtain the mask of the myocardium as a constraint on the next stage. In the second stage, with the T2 images, LGE images and predicted myocardium masks concatenated as inputs, an M-shaped network based on attention mechanism was trained to segment the myocardial edema and scars accurately. In conclusion, the accuracy of the segmentation was improved by adopting prior constraints and attention mechanism, which achieved an average Dice score of 0.570 and 0.634 for the myocardial scars and myocardial scars+edema respectively on the test set of MyoPS 2020.
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
Change history
21 December 2020
The original version of this chapter was revised. The institute Shanghai United Imaging Intelligence, Co., Ltd., Shanghai, China of the author Dongdong Gu has been removed and the acknowledgement was changed to “This work was supported by the National Natural Science Foundation of China (61671204).”
References
Fahmy, A.S., et al.: Three-dimensional deep convolutional neural networks for automated myocardial scar quantification in hypertrophic cardiomyopathy: a multicenter multivendor study. Radiology 294(1), 52–60 (2020)
Fu, H., Cheng, J., Xu, Y., Wong, D.W.K., Liu, J., Cao, X.: Joint optic disc and cup segmentation based on multi-label deep network and polar transformation. IEEE Trans. Med. Imaging 37(7), 1597–1605 (2018)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Lin, A., Kolossváry, M., Išgum, I., Maurovich-Horvat, P., Slomka, P.J., Dey, D.: Artificial intelligence: improving the efficiency of cardiovascular imaging. Expert. Rev. Med. Devices 17(6), 565–577 (2020). https://doi.org/10.1080/17434440.2020.1777855
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)
Singh, G., et al.: Deep learning based automatic segmentation of cardiac computed tomography. J. Am. Coll. Cardiol. 73(9), 1643 (2019)
Tavakoli, V., Amini, A.A.: A survey of shaped-based registration and segmentation techniques for cardiac images. Comput. Vis. Image Underst. 117(9), 966–989 (2013)
Wang, P., Chung, A.C.S.: Focal dice loss and image dilation for brain tumor segmentation. In: Stoyanov, D., et al. (eds.) DLMIA/ML-CDS -2018. LNCS, vol. 11045, pp. 119–127. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00889-5_14
Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3–19. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_1
Xu, Z., Wu, Z., Feng, J.: CFUN: combining faster R-CNN and U-net network for efficient whole heart segmentation. arXiv preprint arXiv:1812.04914 (2018)
Zabihollahy, F., White, J.A., Ukwatta, E.: Fully automated segmentation of left ventricular myocardium from 3D late gadolinium enhancement magnetic resonance images using a U-net convolutional neural network-based model. In: Medical Imaging 2019: Computer-Aided Diagnosis, vol. 10950, p. 109503C. International Society for Optics and Photonics (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)
Acknowledgement
This work was supported by the National Natural Science Foundation of China (61671204).
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
Liu, Y., Zhang, M., Zhan, Q., Gu, D., Liu, G. (2020). Two-Stage Method for Segmentation of the Myocardial Scars and Edema on Multi-sequence Cardiac Magnetic Resonance. 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_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-65651-5_3
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)