Abstract
Deep learning models with large learning capacities often overfit to medical imaging datasets. This is because training sets are often relatively small due to the significant time and financial costs incurred in medical data acquisition and labelling. Data augmentation is therefore routinely used to expand the availability of training data and to increase generalization. However, augmentation strategies are often chosen on an ad-hoc basis without justification. In this paper, we present an augmentation policy search method with the goal of improving model classification performance. We include in the augmentation policy search additional transformations that are commonly used in medical image analysis and evaluate their performance. In addition, we extend the augmentation policy search to include non-linear mixed-example data augmentation strategies. Using these learned policies, we show that principled data augmentation for medical image model training can lead to significant improvements in ultrasound standard plane detection, with an average F1-score improvement of 7.0% overall over naive data augmentation strategies in ultrasound fetal standard plane classification. We find that the learned representations of ultrasound images are better clustered and defined with optimized data augmentation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zaman, A., Park, S.H., Bang, H., Park, C., Park, I., Joung, S.: Generative approach for data augmentation for deep learning-based bone surface segmentation from ultrasound images. Int. J. Comput. Assist. Radiol. Surg. 15(6), 931–941 (2020). https://doi.org/10.1007/s11548-020-02192-1
Bargsten, L., Schlaefer, A.: Specklegan: a generative adversarial network with an adaptive speckle layer to augment limited training data for ultrasound image processing. In: ICARS (2020)
Baumgartner, C.F., et al.: SonoNet: real-time detection and localisation of fetal standard scan planes in freehand ultrasound. In: IEEE TMI (2017)
Buslaev, A., Iglovikov, V.I., et al.: Albumentations: Fast and flexible image augmentations. MDPI (2020)
Cubuk, E.D., Zoph, B., Mane, D., Vasudevan, V., Le, Q.V.: Autoaugment: learning augmentation strategies from data. In: CVPR (2019)
Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.V.: Randaugment: practical automated data augmentation with a reduced search space. In: CVPR (2020)
Droste, R., et al.: Ultrasound image representation learning by modeling sonographer visual attention. IPMI (2019)
Dubost, F., Bortsova, G., Adams, H., Ikram, M.A., Niessen, W., Vernooij, M., de Bruijne, M.: Hydranet: data augmentation for regression neural networks. In: Shen, D., Liu, T., Peters, T.M., Staib, L.H., Essert, C., Zhou, S., Yap, P.-T., Khan, A. (eds.) MICCAI 2019. LNCS, vol. 11767, pp. 438–446. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32251-9_48
Eaton-Rosen, Z., Bragman, F., et al.: Improving data augmentation for medical image segmentation. In: MIDL (2018)
Frid-Adar, M., Diamant, I., et al.: Gan-based synthetic medical image augmentation for increased cnn performance in liver lesion classification. Neurocomputing (2018)
Gan, Z., Henao, R., Carlson, D., Carin, L.: Learning deep sigmoid belief networks with data augmentation. In: Proceedings of Machine Learning Research (PMLR) (2015)
Gontijo-Lopes, R., Smullin, S.J., Cubuk, E.D., Dyer, E.: Affinity and diversity: quantifying mechanisms of data augmentation (2020)
Ho, D., Liang, E., et al.: Population based augmentation: efficient learning of augmentation policy schedules. In: ICML (2019)
Hu, J., et al.: Squeeze-and-excitation networks. In: IPAMI (2020)
Hussain, Z., Gimenez, F., Yi, D., Rubin, D.: Differential data augmentation techniques for medical imaging classification tasks. AMIA (2017)
Jiao, J., et al.: Self-supervised representation learning for ultrasound video. In: IEEE 17th International Symposium on Biomedical Imaging (2020)
Jin, D., Xu, Z., Tang, Y., Harrison, A.P., Mollura, D.J.: CT-realistic lung nodule simulation from 3D conditional generative adversarial networks for robust lung segmentation. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11071, pp. 732–740. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00934-2_81
Lim, S., Kim, I., Kim, T., Kim, C., Kim, S.: Fast autoaugment. In: Advances in Neural Information Processing Systems (NeurIPs) (2019)
Luke, T., Geoff, N.: Improving deep learning using generic data augmentation. In: IEEE Symposium Series on Computational Intelligence (2018)
Nalepa, J., et al.: Data augmentation via image registration. In: ICIP (2019)
Ohno, H.: Auto-encoder-based generative models for data augmentation on regression problems (2019)
Ryo, T., Takashi, M.: Data augmentation using random image cropping and patches for deep CNNs. In: IEEE TCSVT (2020)
Summers, C., Dinneen, M.J.: Improved mixed-example data augmentation. In: IEEE Winter Conference on Applications of Computer Vision (WACV) (2019)
Tokozume, Y., Ushiku, Y., Harada, T.: Between-class learning for image classification. In: CVPR (2018)
Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. In: ICLR (2018)
Zhao, A., Balakrishnan, G., et al.: Data augmentation using learned transformations for one-shot medical image segmentation. In: CVPR (2019)
Acknowledgements
We acknowledge the Croucher Foundation, ERC (ERC-ADG-2015 694 project PULSE), the EPSRC (EP/R013853/1, EP/T028572/1) and the MRC (MR/P027938/1).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Lee, L.H., Gao, Y., Noble, J.A. (2021). Principled Ultrasound Data Augmentation for Classification of Standard Planes. In: Feragen, A., Sommer, S., Schnabel, J., Nielsen, M. (eds) Information Processing in Medical Imaging. IPMI 2021. Lecture Notes in Computer Science(), vol 12729. Springer, Cham. https://doi.org/10.1007/978-3-030-78191-0_56
Download citation
DOI: https://doi.org/10.1007/978-3-030-78191-0_56
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-78190-3
Online ISBN: 978-3-030-78191-0
eBook Packages: Computer ScienceComputer Science (R0)