Abstract
Segmentation of echocardiograms plays an essential role in the quantitative analysis of the heart and helps diagnose cardiac diseases. In the recent decade, deep learning-based approaches have significantly improved the performance of echocardiogram segmentation. Most deep learning-based methods assume that the image to be processed is rectangular in shape. However, typically echocardiogram images are formed within a sector of a circle, with a significant region in the overall rectangular image where there is no data, a result of the ultrasound imaging methodology. This large non-imaging region can influence the training of deep neural networks. In this paper, we propose to use polar transformation to help train deep learning algorithms. Using the r-\(\theta \) transformation, a significant portion of the non-imaging background is removed, allowing the neural network to focus on the heart image. The segmentation model is trained on both x-y and r-\(\theta \) images. During inference, the predictions from the x-y and r-\(\theta \) images are combined using max-voting. We verify the efficacy of our method on the CAMUS dataset with a variety of segmentation networks, encoder networks, and loss functions. The experimental results demonstrate the effectiveness and versatility of our proposed method for improving the segmentation results.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Troy, B.L., et al.: Measurement of left ventricular wall thickness and mass by echocardiography. Circulation 45(3), 602–611 (1972)
Devereux, R.B., et al.: Echocardiographic assessment of left ventricular hypertrophy: comparison to necropsy findings. Am. J. Cardiol. 57(6), 450–458 (1986)
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. Euro. Heart J. Cardiovas. Imaging 16(3), 233–271 (2015)
Madani, A., et al.: Fast and accurate view classification of echocardiograms using deep learning. NPJ Digit. Med. 1(1), 1–8 (2018)
Østvik, A., et al.: Real-time standard view classification in transthoracic echocardiography using convolutional neural networks. Ultrasound Med. Biol. 45(2), 374–384 (2019)
Leclerc, S., et al.: Deep learning for segmentation using an open large-scale dataset in 2D echocardiography. IEEE TMI 38(9), 2198–2210 (2019)
Ouyang, D., et al.: Video-based AI for beat-to-beat assessment of cardiac function. Nature 580(7802), 252–256 (2020)
Liu, F., et al.: Deep pyramid local attention neural network for cardiac structure segmentation in two-dimensional echocardiography. Med. Image Anal. 67, 101873 (2021)
Wu, H., et al.: Semi-supervised segmentation of echocardiography videos via noise-resilient spatiotemporal semantic calibration and fusion. Med. Image Anal. 78, 102397 (2022)
Madani, A., et al.: Deep echocardiography: data-efficient supervised and semi-supervised deep learning towards automated diagnosis of cardiac disease. NPJ Digit. Med. 1(1), 1–11 (2018)
Zhang, J., et al.: Fully automated echocardiogram interpretation in clinical practice: feasibility and diagnostic accuracy. Circulation 138(16), 1623–1635 (2018)
Feng, Zi., et al.: Two-stream attention spatio-temporal network for classification of echocardiography videos. In: 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), pp. 1461–1465. IEEE (2021)
Tan, L.K., et al.: Fully automated segmentation of the left ventricle in cine cardiac MRI using neural network regression. J. Magn. Reson. Imaging 48(1), 140–152 (2018)
Chen, L.-C., et al. Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)
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
Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 833–851. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_49
He, K., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Acknowledgments
This work was funded by NSF Grant 1633295 BIGDATA: F: Collaborative Research: From Visual Data to Visual Understanding.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Feng, Z., Sivak, J.A., Krishnamurthy, A.K. (2022). Improving Echocardiography Segmentation by Polar Transformation. In: Camara, O., et al. Statistical Atlases and Computational Models of the Heart. Regular and CMRxMotion Challenge Papers. STACOM 2022. Lecture Notes in Computer Science, vol 13593. Springer, Cham. https://doi.org/10.1007/978-3-031-23443-9_13
Download citation
DOI: https://doi.org/10.1007/978-3-031-23443-9_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-23442-2
Online ISBN: 978-3-031-23443-9
eBook Packages: Computer ScienceComputer Science (R0)