Abstract
Automated quality assessment (AQA) in transoesophageal echocardiography (TEE) contributes to accurate diagnosis and echocardiographers’ training, providing direct feedback for the development of dexterous skills. However, prior works only perform AQA on simulated TEE data due to the scarcity of real data, which lacks applicability in the real world. Considering the cost and limitations of collecting TEE data from real cases, exploiting the readily available simulated data for AQA in real-world TEE is desired. In this paper, we construct the first simulation-to-real TEE dataset, and propose a novel Simulation-to-Real network (SR-AQA) with unsupervised domain adaptation for this problem. It is based on uncertainty-aware feature stylization (UFS), incorporating style consistency learning (SCL) and task-specific learning (TL), to achieve high generalizability. Concretely, UFS estimates the uncertainty of feature statistics in the real domain and diversifies simulated images with style variants extracted from the real images, alleviating the domain gap. We enforce SCL and TL across different real-stylized variants to learn domain-invariant and task-specific representations. Experimental results demonstrate that our SR-AQA outperforms state-of-the-art methods with 3.02% and 4.37% performance gain in two AQA regression tasks, by using only 10% unlabelled real data. Our code and dataset are available at https://doi.org/10.5522/04/23699736.
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.
Re-parameterization trick is applied here to make the sampling operation differentiable.
- 2.
Example GI and CP results are provided in the supplementary material
References
Abdi, A.H., et al.: Automatic quality assessment of echocardiograms using convolutional neural networks: feasibility on the apical four-chamber view. IEEE Trans. Med. Imaging 36(6), 1221–1230 (2017)
Chen, C., Li, Z., Ouyang, C., Sinclair, M., Bai, W., Rueckert, D.: MaxStyle: adversarial style composition for robust medical image segmentation. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds.) MICCAI 2022. LNCS, vol. 13435, pp. 151–161. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-16443-9_15
Chen, X., He, K.: Exploring simple Siamese representation learning. In: CVPR 2021, pp. 15745–15753 (2021)
Chen, X., Wang, S., Wang, J., Long, M.: Representation subspace distance for domain adaptation regression. In: ICML 2021, pp. 1749–1759 (2021)
Hahn, R.T., et al.: Guidelines for performing a comprehensive transesophageal echocardiographic examination: recommendations from the American society of echocardiography and the society of cardiovascular anesthesiologists. J. Am. Soc. Echocardiogr. 26(9), 921–964 (2013)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR 2016, pp. 770–778 (2016)
Hempel, C., et al.: Impact of simulator-based training on acquisition of transthoracic echocardiography skills in medical students. Ann. Card. Anaesth. 23(3), 293 (2020)
Huang, X., Belongie, S.: Arbitrary style transfer in real-time with adaptive instance normalization. In: ICCV 2017, pp. 1501–1510 (2017)
Labs, R.B., Vrettos, A., Loo, J., Zolgharni, M.: Automated assessment of transthoracic echocardiogram image quality using deep neural networks. Intell. Med. (2022)
Le, C.K., Lewis, J., Steinmetz, P., Dyachenko, A., Oleskevich, S.: The use of ultrasound simulators to strengthen scanning skills in medical students: a randomized controlled trial. J. Ultrasound Med. 38(5), 1249–1257 (2019)
Lee, S., Seong, H., Lee, S., Kim, E.: WildNet: learning domain generalized semantic segmentation from the wild. In: CVPR 2022, pp. 9926–9936 (2022)
Li, X., Dai, Y., Ge, Y., Liu, J., Shan, Y., Duan, L.: Uncertainty modeling for out-of-distribution generalization. In: ICLR 2022 (2022)
Liao, Z., et al.: On modelling label uncertainty in deep neural networks: automatic estimation of intra-observer variability in 2D echocardiography quality assessment. IEEE Trans. Med. Imaging 39(6), 1868–1883 (2019)
Lin, Z., et al.: Multi-task learning for quality assessment of fetal head ultrasound images. Med. Image Anal. 58, 101548 (2019)
Mazomenos, E.B., Bansal, K., Martin, B., Smith, A., Wright, S., Stoyanov, D.: Automated performance assessment in transoesophageal echocardiography with convolutional neural networks. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11073, pp. 256–264. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00937-3_30
Mazomenos, E.B., et al.: Motion-based technical skills assessment in transoesophageal echocardiography. In: Zheng, G., Liao, H., Jannin, P., Cattin, P., Lee, S.-L. (eds.) MIAR 2016. LNCS, vol. 9805, pp. 96–103. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-43775-0_9
Montealegre-Gallegos, M., et al.: Imaging skills for transthoracic echocardiography in cardiology fellows: the value of motion metrics. Ann. Card. Anaesth. 19(2), 245 (2016)
Rangwani, H., Aithal, S.K., Mishra, M., Jain, A., Radhakrishnan, V.B.: A closer look at smoothness in domain adversarial training. In: ICML 2022, pp. 18378–18399 (2022)
Shen, Y., Lu, Y., Jia, X., Bai, F., Meng, M.Q.H.: Task-relevant feature replenishment for cross-centre polyp segmentation. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds.) MICCAI 2022. LNCS, vol. 13434, pp. 599–608. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-16440-8_57
Song, H., Peng, Y.G., Liu, J.: Innovative transesophageal echocardiography training and competency assessment for Chinese anesthesiologists: role of transesophageal echocardiography simulation training. Curr. Opin. Anaesthesiol. 25(6), 686–691 (2012)
Wang, X., Long, M., Wang, J., Jordan, M.: Transferable calibration with lower bias and variance in domain adaptation. In: NeurIPS 2020, pp. 19212–19223 (2020)
Wheeler, R., et al.: A minimum dataset for a standard transoesphageal echocardiogram: a guideline protocol from the British society of echocardiography. Echo Res. Pract. 2(4), G29 (2015)
Zhang, Y., Liu, T., Long, M., Jordan, M.: Bridging theory and algorithm for domain adaptation. In: ICML 2019, pp. 7404–7413 (2019)
Zhou, K., Yang, Y., Qiao, Y., Xiang, T.: Domain generalization with mixstyle. In: ICLR 2021 (2021)
Acknowledgements
This work is supported by the Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS) [203145Z/16/Z and NS/A000050/1]; EPSRC-funded UCL Centre for Doctoral Training in Intelligent, Integrated Imaging in Healthcare (i4health) [EP/S021930/1]; Horizon 2020 FET [863146]; a UCL Graduate Research Scholarship; and Singapore MoE Tier 1 Start up grant (WBS: A-8001267-00-00). Danail Stoyanov is supported by a RAE Chair in Emerging Technologies [CiET1819/2/36] and an EPSRC Early Career Research Fellowship [EP/P012841/1].
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Xu, J. et al. (2023). Regressing Simulation to Real: Unsupervised Domain Adaptation for Automated Quality Assessment in Transoesophageal Echocardiography. In: Greenspan, H., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2023. MICCAI 2023. Lecture Notes in Computer Science, vol 14228. Springer, Cham. https://doi.org/10.1007/978-3-031-43996-4_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-43996-4_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43995-7
Online ISBN: 978-3-031-43996-4
eBook Packages: Computer ScienceComputer Science (R0)
