Abstract
In medical imaging, technical progress or changes in diagnostic procedures lead to a continuous change in image appearance. Scanner manufacturer, reconstruction kernel, dose, other protocol specific settings or administering of contrast agents are examples that influence image content independent of the scanned biology. Such domain and task shifts limit the applicability of machine learning algorithms in the clinical routine by rendering models obsolete over time. Here, we address the problem of data shifts in a continuous learning scenario by adapting a model to unseen variations in the source domain while counteracting catastrophic forgetting effects. Our method uses a dynamic memory to facilitate rehearsal of a diverse training data subset to mitigate forgetting. We evaluated our approach on routine clinical CT data obtained with two different scanner protocols and synthetic classification tasks. Experiments show that dynamic memory counters catastrophic forgetting in a setting with multiple data shifts without the necessity for explicit knowledge about when these shifts occur.
J. Hofmanninger and M. Perkonigg—Authors contributed equally.
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
Notes
References
Baweja, C., Glocker, B., Kamnitsas, K.: Towards continual learning in medical imaging (2018). https://arxiv.org/abs/1811.02496
Gatys, L., Ecker, A., Bethge, M.: A neural algorithm of artistic style. J. Vis. 16(12), 326 (2016). https://doi.org/10.1167/16.12.326
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015). http://image-net.org/challenges/LSVRC/2015/
Hofmanninger, J., Prayer, F., Pan, J., Röhrich, S., Prosch, H., Langs, G.: Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem. Eur. Radiol. Exp. 4(50), 1–13 (2020). https://doi.org/10.1186/s41747-020-00173-2
Karani, N., Chaitanya, K., Baumgartner, C., Konukoglu, E.: A lifelong learning approach to brain MR segmentation across scanners and protocols. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11070, pp. 476–484. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00928-1_54
Kingma, D.P., Ba, J.L.: Adam: a method for stochastic optimization. In: 3rd International Conference on Learning Representations. (ICLR 2015) (2015)
Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. Proc. Natl. Acad. Sci. U.S.A. 114(13), 3521–3526 (2017). https://doi.org/10.1073/pnas.1611835114
Lopez-Paz, D., Ranzato, M.: Gradient episodic memory for continual learning. In: Advances in Neural Information Processing Systems, pp. 6468–6477 (2017)
McCloskey, M., Cohen, N.J.: Catastrophic Interference in Connectionist Networks: The Sequential Learning Problem. Psychol. Learn. Motiv. Adv. Res. Theory 24(C), 109–165 (1989). https://doi.org/10.1016/S0079-7421(08)60536-8
Ravishankar, H., Venkataramani, R., Anamandra, S., Sudhakar, P., Annangi, P.: Feature transformers: privacy preserving lifelong learners for medical imaging. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11767, pp. 347–355. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32251-9_38
Robins, A.: Catastrophic forgetting, rehearsal and pseudorehearsal. Connection Sci. 7(2), 123–146 (1995). https://doi.org/10.1080/09540099550039318
Acknowledgments
This work was supported by Austrian Science Fund (FWF) I 2714B31 and Novartis Pharmaceuticals Corporation.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Hofmanninger, J., Perkonigg, M., Brink, J.A., Pianykh, O., Herold, C., Langs, G. (2020). Dynamic Memory to Alleviate Catastrophic Forgetting in Continuous Learning Settings. In: Martel, A.L., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2020. MICCAI 2020. Lecture Notes in Computer Science(), vol 12262. Springer, Cham. https://doi.org/10.1007/978-3-030-59713-9_35
Download citation
DOI: https://doi.org/10.1007/978-3-030-59713-9_35
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59712-2
Online ISBN: 978-3-030-59713-9
eBook Packages: Computer ScienceComputer Science (R0)
