Abstract
Imaging in clinical routine is subject to changing scanner protocols, hardware, or policies in a typically heterogeneous set of acquisition hardware. Accuracy and reliability of deep learning models suffer from those changes as data and targets become inconsistent with their initial static training set. Continual learning can adapt to a continuous data stream of a changing imaging environment. Here, we propose a method for continual active learning on a data stream of medical images. It recognizes shifts or additions of new imaging sources - domains -, adapts training accordingly, and selects optimal examples for labelling. Model training has to cope with a limited labelling budget, resembling typical real world scenarios. We demonstrate our method on T1-weighted magnetic resonance images from three different scanners with the task of brain age estimation. Results demonstrate that the proposed method outperforms naive active learning while requiring less manual labelling.
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
Similar content being viewed by others
References
Bobu, A., Tzeng, E., Hoffman, J., Darrell, T.: Adapting to continously shifting domains. In: ICLR Workshop (2018)
Budd, S., Robinson, E.C., Kainz, B.: A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysis (2019)
Dinsdale, N.K., Jenkinson, M., Namburete, A.I.: Unlearning Scanner Bias for MRI Harmonisation in Medical Image Segmentation. Commun. Comput. Inf. Sci. CCIS 1248, 15–25 (2020)
Gatys, L., Ecker, A., Bethge, M.: A neural algorithm of artistic style. J. Vis. 16(12), 326 (2016)
Gonzalez, C., Sakas, G., Mukhopadhyay, A.: What is Wrong with Continual Learning in Medical Image Segmentation? (2020). http://arxiv.org/abs/2010.11008
Hofmanninger, J., Perkonigg, M., Brink, J.A., Pianykh, O., Herold, C., Langs, G.: Dynamic memory to alleviate catastrophic forgetting in continuous learning settings. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12262, pp. 359–368. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59713-9_35
LaMontagne, P.J., et al.: OASIS-3: Longitudinal Neuroimaging, Clinical, and Cognitive Dataset for Normal Aging and Alzheimer Disease. medRxiv p. 2019.12.13.19014902 (2019). https://doi.org/10.1101/2019.12.13.19014902
Lao, Q., Jiang, X., Havaei, M., Bengio, Y.: Continuous Domain Adaptation with Variational Domain-Agnostic Feature Replay (2020)
Lenga, M., Schulz, H., Saalbach, A.: Continual Learning for Domain Adaptation in Chest X-ray Classification. In: Conference on Medical Imaging with Deep Learning (MIDL) (2020)
Li, P., Hastie, T.J., Church, K.W.: Very sparse stable random projections for dimension reduction. In: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 440–449 (2007)
Li, Z., Hoiem, D.: Learning without forgetting. IEEE Trans. Pattern Anal. Mach. Intell. 40(12), 2935–2947 (2018)
Lopez-Paz, D., Ranzato, M.: Gradient episodic memory for continual learning. In: Advances in Neural Information Processing Systems, pp. 6468–6477 (2017)
Maaten, L.v.d., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579–2605 (2008)
McCloskey, M., Cohen, N.J.: Catastrophic interference in connectionist networks: the sequential learning problem. In: Psychology of Learning and Motivation - Advances in Research and Theory, vol. 24, pp. 109–165 (1989)
Ozdemir, F., Fuernstahl, P., Goksel, O.: Learn the new, keep the old: extending pretrained models with new anatomy and images. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11073, pp. 361–369. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00937-3_42
Pianykh, O.S., et al.: Continuous learning AI in radiology: implementation principles and early applications. Radiology 297(1), 6–14 (2020)
Tony Liu, F., Ming Ting, K., Zhou, Z.H.: Isolation Forest. In: International Conference on Data Mining (2008)
Venkataramani, R., Ravishankar, H., Anamandra, S.: Towards continuous domain adaptation for medical imaging. In: Proceedings - International Symposium on Biomedical Imaging, vol. 2019-April, pp. 443–446. IEEE Computer Society (4 2019)
Wu, Z., Wang, X., Gonzalez, J., Goldstein, T., Davis, L.: ACE: adapting to changing environments for semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2121–2130 (2019)
Zhou, Z., Sodha, V., Pang, J., Gotway, M.B., Liang, J.: Models Genesis. Medical Image Analysis p. 101840 (2020). https://doi.org/10.1016/j.media.2020.101840
Acknowledgments
This work was supported by Novartis Pharmaceuticals Corporation and received funding by the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No 765148.
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
Perkonigg, M., Hofmanninger, J., Langs, G. (2021). Continual Active Learning for Efficient Adaptation of Machine Learning Models to Changing Image Acquisition. 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_50
Download citation
DOI: https://doi.org/10.1007/978-3-030-78191-0_50
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)