Abstract
3D+t Transesophageal Echocardiography (TEE) performs 4D scans of mitral valve (MV) morphology at frame rate providing real-time guidance for catheter-based interventions for MV repair and replacement. A key anatomical structure is the MV annulus, and live quantification of the dynamic annulus at acquisition rates 15 fps or higher have proven to be technically challenging. In this paper, we propose a bottom-up approach inspired by clinicians’ manual workflow for MV annulus modeling on 3D+t TEE images in real time. Specifically, we first detect annulus landmarks with clear 3D anatomical features via agents trained using Deep Reinforcement Learning. Leveraging the circular structure of the annulus, cross-annular planes are extracted and additional landmarks are then detected through 2D image-to-image networks on the 2D cutting planes. The complete 3D annulus is finally fitted through all detected landmarks using Splines. We validate the proposed approach on 795 3D+t TEE sequences with 1906 annotated frames, and achieve a speed 20 fps with a median accuracy 2.74 mm curve-to-curve error. Furthermore, device simulation is utilized to augment the training data that results in promising accuracy improvement on challenging echos with visible devices and warrants further investigation.
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
Notes
- 1.
Each sequence or case refers to a TEE recording over time. It consists of 10 to 60 frames. Each frame is a 3D TEE image.
- 2.
Courtesy of Dr Mani Vannan, Piedmont Heart Institute, Atlanta, GA.
- 3.
[10] presents accuracy over 2D cutting-planes with weighted mean error as 2.0 mm, which the same metric in this work is 1.57 mm.
References
Benjamin, E.J., Muntner, P., Bittencourt, M.S.: Heart disease and stroke statistics-2019 update: a report from the american heart association. Circulation 139(10), e56–e528 (2019)
El Sabbagh, A., Reddy, Y.N., Nishimura, R.A.: Mitral valve regurgitation in the contemporary era. JACC: Cardiovasc. Imaging 11(4), 628–643 (2018)
Bax, J.J., et al.: Transcatheter interventions for mitral regurgitation. JACC: Cardiovasc. Imaging 12(10), 2029–2048 (2019)
Ionasec, R.I., et al.: Patient-specific modeling and quantification of the aortic and mitral valves from 4-d cardiac CT and tee. IEEE Trans. Med. Imaging 29(9), 1636–1651 (2010)
Voigt, I., et al.: Robust physically-constrained modeling of the mitral valve and subvalvular apparatus. In: Fichtinger, G., Martel, A., Peters, T. (eds.) MICCAI 2011. LNCS, vol. 6893, pp. 504–511. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-23626-6_62
Schneider, R.J., Perrin, D.P., Vasilyev, N.V., Marx, G.R., Pedro, J., Howe, R.D.: Mitral annulus segmentation from four-dimensional ultrasound using a valve state predictor and constrained optical flow. Med. Image Anal. 16(2), 497–504 (2012)
Pouch, A.M., et al.: Modeling the myxomatous mitral valve with three-dimensional echocardiography. Ann. Thorac. Surg. 102(3), 703–710 (2016)
Graser, B., et al.: Using a shape prior for robust modeling of the mitral annulus on 4D ultrasound data. Int. J. Comput. Assist. Radiol. Surg. 9(4), 635–644 (2014). https://doi.org/10.1007/s11548-013-0942-3
Voigt, I., et al.: Robust live tracking of mitral valve annulus for minimally-invasive intervention guidance. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9349, pp. 439–446. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24553-9_54
Andreassen, B.S., Veronesi, F., Gerard, O., Solberg, A.H.S., Samset, E.: Mitral annulus segmentation using deep learning in 3D transesophageal echocardiography. IEEE J. Biomed. Health Inform. 24, 994–1003 (2019)
Ghesu, F.C., et al.: Multi-scale deep reinforcement learning for real-time 3d-landmark detection in CT scans. IEEE Trans. Pattern Anal. Mach. Intell. 41(1), 176–189 (2017)
Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529 (2015)
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)
Abbott Laboratories: Mitraclip clip delivery system: instructions for use. https://www.accessdata.fda.gov/cdrh_docs/pdf10/P100009c.pdf (2013). Accessed 16 Mar 2020
Alessandrini, M., et al.: A pipeline for the generation of realistic 3D synthetic echocardiographic sequences: methodology and open-access database. IEEE Trans. Med. Imaging 34, 1436–1451 (2015)
Gao, H., et al.: A fast convolution-based methodology to simulate 2-d/3-d cardiac ultrasound images. IEEE Trans. Ultrasonics Ferroelectr. Freq. Control 56, 404–409 (2009)
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
Zhang, Y. et al. (2020). A Bottom-Up Approach for Real-Time Mitral Valve Annulus Modeling on 3D Echo Images. In: Martel, A.L., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2020. MICCAI 2020. Lecture Notes in Computer Science(), vol 12266. Springer, Cham. https://doi.org/10.1007/978-3-030-59725-2_44
Download citation
DOI: https://doi.org/10.1007/978-3-030-59725-2_44
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59724-5
Online ISBN: 978-3-030-59725-2
eBook Packages: Computer ScienceComputer Science (R0)
