Abstract
Rheumatic heart disease (RHD) is a common medical condition in children in which acute rheumatic fever causes permanent damage to the heart valves, thus impairing the heart’s ability to pump blood. Doppler echocardiography is a popular diagnostic tool used in the detection of RHD. However, the execution of this assessment requires the work of skilled physicians, which poses a problem of accessibility, especially in low-income countries with limited access to clinical experts. This paper presents a novel, automated, deep learning-based method to detect RHD using color Doppler echocardiography clips. We first homogenize the analysis of ungated echocardiograms by identifying two acquisition views (parasternal and apical), followed by extracting the left atrium regions during ventricular systole. Then, we apply a model ensemble of multi-view 3D convolutional neural networks and a multi-view Transformer to detect RHD. This model allows our analysis to benefit from the inclusion of spatiotemporal information and uses an attention mechanism to identify the relevant temporal frames for RHD detection, thus improving the ability to accurately detect RHD. The performance of this method was assessed using 2,136 color Doppler echocardiography clips acquired at the point of care of 591 children in low-resource settings, showing an average accuracy of 0.78, sensitivity of 0.81, and specificity of 0.74. These results are similar to RHD detection conducted by expert clinicians and superior to the state-of-the-art approach. Our novel model thus has the potential to improve RHD detection in patients with limited access to clinical experts.
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
Marijon, E., Mirabel, M., Celermajer, D.S., Jouven, X.: Rheumatic heart disease. Lancet 379(9819), 953–964 (2012). https://doi.org/10.1016/S0140-6736(11)61171-9
Liu, M., Lu, L., Sun, R., Zheng, Y., Zhang, P.: Rheumatic heart disease: Causes, symptoms, and treatments. Cell Biochem. Biophys. 72(3), 861–863 (2015). https://doi.org/10.1007/s12013-015-0552-5
Reményi, B., et al.: World heart federation criteria for echocardiographic diagnosis of rheumatic heart disease–an evidence-based guideline. Nat. Rev. Cardiol. 9(5), 297–309 (2012). https://doi.org/10.1038/nrcardio.2012.7
Beaton, A., et al.: The utility of handheld echocardiography for early rheumatic heart disease diagnosis: a field study. Eur. Hear. J. Cardiovasc. Imaging 16(5), 475–482 (2015). https://doi.org/10.1093/ehjci/jeu296
Scheel, A., et al.: The inter-rater reliability and individual reviewer performance of the 2012 world heart federation guidelines for the echocardiographic diagnosis of latent rheumatic heart disease. Int. J. Cardiol. 328, 146–151 (2021). https://doi.org/10.1016/j.ijcard.2020.11.013
Mirabel, M., et al.: Screening for rheumatic heart disease: Evaluation of a focused cardiac ultrasound approach. Circ. Cardiovasc. Imaging 8(1), 1–8 (2015). https://doi.org/10.1161/CIRCIMAGING.114.002324
Nunes, M.C.P., et al.: Simplified echocardiography screening criteria for diagnosing and predicting progression of latent rheumatic heart disease. Circ. Cardiovasc. Imaging 12(2), 1–13 (2019). https://doi.org/10.1161/CIRCIMAGING.118.007928
Diamantino, A., et al.: A focussed single-view hand-held echocardiography protocol for the detection of rheumatic heart disease. Cardiol. Young 28(1), 108–117 (2018). https://doi.org/10.1017/S1047951117001676
Balodi, A., Anand, R.S., Dewal, M.L., Rawat, A.: Computer-aided classification of the mitral regurgitation using multiresolution local binary pattern. Neural Comput. Appl. 32(7), 2205–2215 (2019). https://doi.org/10.1007/s00521-018-3935-x
Moghaddasi, H., Nourian, S.: Automatic assessment of mitral regurgitation severity based on extensive textural features on 2D echocardiography videos. Comput. Biol. Med. 73, 47–55 (2016). https://doi.org/10.1016/j.compbiomed.2016.03.026
Asmare, M.H., Filtjens, B., Woldehanna, F., Janssens, L., Vanrumste, B.: Rheumatic heart disease screening based on phonocardiogram. Sensors (Basel) 21(19), 1–17 (2021). https://doi.org/10.3390/s21196558
Asmare, M.H., Woldehanna, F., Janssens, L., Vanrumste, B.: Rheumatic heart disease detection using deep learning from spectro-temporal representation of un-segmented heart sounds. In: Proceedings of the Annual International Engineering in Medicine and Biology Society, pp. 168–71. IEEE, Montreal, QC, Canada (2020). https://doi.org/10.1109/EMBC44109.2020.9176544
Godown, J., et al.: Handheld echocardiography versus auscultation for detection of rheumatic heart disease. Pediatrics 135(4), e939–e944 (2015). https://doi.org/10.1542/PEDS.2014-2774
Zamzmi, G., Hsu, L.Y., Li, W., Sachdev, V., Antani, S.: Harnessing machine intelligence in automatic echocardiogram analysis: Current status, limitations, and future directions. IEEE Rev. Biomed. Eng. 14, 181–203 (2020). https://doi.org/10.1109/RBME.2020.2988295
Madani, A., Arnaout, R., Mofrad, M., Arnaout, R.: Fast and accurate view classification of echocardiograms using deep learning. NPJ Digit. Med. 1(6), 1–8 (2018). https://doi.org/10.1038/s41746-017-0013-1
Kusunose, K., Haga, A., Inoue, M., Fukuda, D., Yamada, H., Sata, M.: Clinically feasible and accurate view classification of echocardiographic images using deep learning. Biomolecules 10(5), 1–8 (2020). https://doi.org/10.3390/biom10050665
Chen, C., et al.: Deep learning for cardiac image segmentation: a review. Front. Cardiovasc. Med. 7(25), 1–33 (2020). https://doi.org/10.3389/fcvm.2020.00025
Ghorbani, A., et al.: Deep learning interpretation of echocardiograms. NPJ Digit. Med. 3(10), 1–10 (2020). https://doi.org/10.1038/s41746-019-0216-8
Martins, J.F.B.S., et al.: Towards automatic diagnosis of rheumatic heart disease on echocardiographic exams through video-based deep learning. J. Am. Med. Informatics Assoc. 28(9), 1834–1842 (2021). https://doi.org/10.1093/JAMIA/OCAB061
Seeland, M., Mäder, P.: Multi-view classification with convolutional neural networks. PLoS ONE 16(1), 1–17 (2021). https://doi.org/10.1371/journal.pone.0245230
Su, H., Maji, S., Kalogerakis, E., Learned-Miller, E.: Multi-view convolutional neural networks for 3D shape recognition. In: Proceedings of the International Conference on Computer Vision, pp. 1–12. IEEE, Santiago, Chile (2015). https://doi.org/10.48550/arxiv.1505.00880
Chen, S., Yu, T., Li, P.: MVT: Multi-view vision transformer for 3D object recognition. In: Proceedings of the 32nd British Machine Vision Conference, pp. 1–14. British Machine Vision Association, Online (2021)
Vaswani, A., et al.: Attention is all you need. In: Proceedings of the 31st Conference in Neural Information Processing Systems, pp. 1–11. Curran Associates Inc., Long Beach, CA, USA (2017). https://doi.org/10.48550/arxiv.1706.03762
Khan, S., Naseer, M., Hayat, M., Zamir, S.W., Khan, F.S., Shah, M.: Transformers in vision: A survey. ACM Comput. Surv., 1–38 (2021). https://doi.org/10.1145/3505244
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: Proceedings of the Conference on Computer Vision and Pattern Recognition, pp. 248–55. IEEE, Miami, Florida, USA (2009). https://doi.org/10.1109/CVPR.2009.5206848
Chaurasia, A., Culurciello, E.: LinkNet: Exploiting encoder representations for efficient semantic segmentation. In: Proceedings of the Visual Communications and Image Processing, pp. 1–5. IEEE, St. Petersburg, FL, USA (2017). https://doi.org/10.1109/VCIP.2017.8305148
Yakubovskiy, P.: Segmentation models. GitHub repository. GitHub (2019). https://github.com/qubvel/segmentation_models. Accessed 30 Jun 2022
Roshanitabrizi, P., et al.: Standardized analysis of kidney ultrasound images for the prediction of pediatric hydronephrosis severity. In: Lian, C., Cao, X., Rekik, I., Xu, X., Yan, P. (eds.) MLMI 2021. LNCS, vol. 12966, pp. 366–375. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87589-3_38
Hendrycks, D., Gimpel, K.: Gaussian error linear units (GELUs). arXiv: Learning, 1–9 (2016)
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
Roshanitabrizi, P. et al. (2022). Ensembled Prediction of Rheumatic Heart Disease from Ungated Doppler Echocardiography Acquired in Low-Resource Settings. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds) Medical Image Computing and Computer Assisted Intervention – MICCAI 2022. MICCAI 2022. Lecture Notes in Computer Science, vol 13431. Springer, Cham. https://doi.org/10.1007/978-3-031-16431-6_57
Download citation
DOI: https://doi.org/10.1007/978-3-031-16431-6_57
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-16430-9
Online ISBN: 978-3-031-16431-6
eBook Packages: Computer ScienceComputer Science (R0)
