Abstract
Segmentation of the right ventricle (RV) from 3D echocardiography (3DE) is a challenging task. In comparison to the left ventricle (LV), the complex geometry of the RV hinders accurate and reproducible volume quantification. While more accessible, 3DE falls short of gold-standard cardiac magnetic resonance (CMR) imaging for volume quantification due to its low spatial resolution and poor contrast-to-noise ratio. The use of machine learning can overcome these challenges to improve 3DE RV segmentation. This study assessed this approach by leveraging segmentations derived from CMR as ground truth labels, and including LV labels as contextual information. Forty subjects (20 females; 20 with cardiac diseases of mixed origin; 20 healthy controls) were imaged with transthoracic 3DE and cine CMR <1 h apart. Biventricular segmentations from CMR were spatially registered to corresponding end-diastolic and end-systolic 3DE images. Paired 3DE images and CMR labels from 32 subjects were used to train deep-learning models for RV segmentation from 3DE. One model was trained with RV labels only, and a second was trained with both RV and LV labels. Using the 8 test cases, the model trained with biventricular labels predicted an end-diastolic volume of 158 ± 36 ml, end-systolic volume of 105 ± 40 ml, and ejection fraction of 36 ± 11 %, which were not statistically significantly different to values measured using CMR (165 ± 30 ml, 115 ± 32 ml and 31 ± 8 %, respectively; P=NS). Inclusion of LV labels improved segmentation accuracy in cases with RV free wall signal dropout. These results indicate that leveraging CMR-derived labels for deep-learning can facilitate reliable clinical assessment of RV function from 3DE.
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
Notes
- 1.
Dice was calculated as the volume of overlap between the predicted segmentation and ground truth label, divided by the total number of voxels.
- 2.
MSD was calculated as the average Euclidian distance between the surface of the predicted segmentation and the ground truth label.
- 3.
HD was calculated as the maximum Euclidian distance between any subset of the predicted segmentation surface to the corresponding subset of the ground truth label surface.
References
Ahmad, A., et al.: Feasibility and accuracy of a fully automated right ventricular quantification software with three-dimensional echocardiography: comparison with cardiac magnetic resonance. Front. Cardiovasc. Med. 8, 732893 (2021)
Ahrens, J., Geveci, B., Law, C.: 36 - ParaView: an end-user tool for large-data visualization. In: Hansen, C.D., Johnson, C.R. (eds.) Visualization Handbook, pp. 717–731. Butterworth-Heinemann, Burlington (2005). https://doi.org/10.1016/B978-012387582-2/50038-1, https://www.sciencedirect.com/science/article/pii/B9780123875822500381
Bernard, O., et al.: 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)
Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834–848 (2018)
Danudibroto, A., Bersvendsen, J., Mirea, O., Gerard, O., D’hooge, J., Samset, E.: Image-based temporal alignment of echocardiographic sequences. In: Duric, N., Heyde, B. (eds.) Medical Imaging 2016: Ultrasonic Imaging and Tomography. vol. 9790, p. 97901G. International Society for Optics and Photonics, SPIE (2016). https://doi.org/10.1117/12.2216192
Genovese, D., et al.: Machine learning-based three-dimensional echocardiographic quantification of right ventricular size and function: Validation against cardiac magnetic resonance. J. Am. Soc. Echocardiogr. 32(8), 969–977 (2019)
Ghio, S., et al.: Independent and additive prognostic value of right ventricular systolic function and pulmonary artery pressure in patients with chronic heart failure. J. Am. Coll. Cardiol. 37(1), 183–188 (2001). https://doi.org/10.1016/S0735-1097(00)01102-5, https://www.sciencedirect.com/science/article/pii/S0735109700011025
Gilbert, K., et al.: An interactive tool for rapid biventricular analysis of congenital heart disease. Clin. Physiol. Funct. Imaging 37(4), 413–420 (2017)
Isensee, F., Jaeger, P.F., Kohl, S.A.A., Petersen, J., Maier-Hein, K.H.: nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods 18(2), 203–211 (2021)
Koo, T.K., Li, M.Y.: A guideline of selecting and reporting intraclass correlation coefficients for reliability research. J. Chiropractic Med. 15(2), 155–163 (2016). https://doi.org/10.1016/j.jcm.2016.02.012, https://www.sciencedirect.com/science/article/pii/S1556370716000158
Kramer, C.M., Barkhausen, J., Bucciarelli-Ducci, C., Flamm, S.D., Kim, R.J., Nagel, E.: Standardized cardiovascular magnetic resonance imaging (CMR) protocols: 2020 update. J. Cardiovasc. Magn. Reson. 22(1), 17 (2020)
Lang, R.M., et al.: Recommendations for cardiac chamber quantification by echocardiography in adults: an update from the American society of echocardiography and the European association of cardiovascular imaging. J. Am. Soc. Echocardiogr. 28(1), 1–39.e14 (2015). https://doi.org/10.1016/j.echo.2014.10.003, https://www.sciencedirect.com/science/article/pii/S0894731714007457
Medvedofsky, D., et al.: Novel approach to three-dimensional echocardiographic quantification of right ventricular volumes and function from focused views. J. Am. Soc. Echocardiogr. 28(10), 1222–1231 (2015)
Mosteller, R.D.: Simplified calculation of body-surface area. N. Engl. J. Med. 317(17), 1098 (1987)
Oktay, O., et al.: Attention U-Net: learning where to look for the pancreas. In: Medical Imaging with Deep Learning (2018). https://openreview.net/forum?id=Skft7cijM
Wu, V.C.C., Takeuchi, M.: Three-dimensional echocardiography: current status and real-life applications. Acta Cardiol. Sin. 33(2), 107–118 (2017)
Zhao, D., et al.: MITEA: a dataset for machine learning segmentation of the left ventricle in 3D echocardiography using subject-specific labels from cardiac magnetic resonance imaging. Front. Cardiovasc. Med. 9, 1016703 (2022)
Zhou, J., Du, M., Chang, S., Chen, Z.: Artificial intelligence in echocardiography: detection, functional evaluation, and disease diagnosis. Cardiovasc. Ultrasound 19(1), 29 (2021)
Zhu, Y., et al.: Quantitative assessment of right ventricular size and function with multiple parameters from artificial intelligence-based three-dimensional echocardiography: a comparative study with cardiac magnetic resonance. Echocardiography 39(2), 223–232 (2022)
Acknowledgements
We gratefully acknowledge the study participants, and the staff at the Centre for Advanced MRI at the University of Auckland for their expertise and assistance with the imaging components of this study.
Funding
This study was funded by the Health Research Council of New Zealand (programme grant 17/608).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Dillon, J.R. et al. (2024). Automated Segmentation of the Right Ventricle from 3D Echocardiography Using Labels from Cardiac Magnetic Resonance Imaging. In: Camara, O., et al. Statistical Atlases and Computational Models of the Heart. Regular and CMRxRecon Challenge Papers. STACOM 2023. Lecture Notes in Computer Science, vol 14507. Springer, Cham. https://doi.org/10.1007/978-3-031-52448-6_12
Download citation
DOI: https://doi.org/10.1007/978-3-031-52448-6_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-52447-9
Online ISBN: 978-3-031-52448-6
eBook Packages: Computer ScienceComputer Science (R0)