Abstract
Designing deep learning (DL) models that adapt to new data without forgetting previously acquired knowledge is important in the medical field where data is generated daily, posing a challenge for model adaptation and knowledge retention. Continual learning (CL) enables models to learn continuously without forgetting, typically on a sequence of domains with known domain identities (e.g. source of data). In this work, we address a more challenging and practical CL scenario where information about the domain identity during training and inference is unavailable. We propose Continual-GEN, a novel forget-free, replay-free, and domain-agnostic subnetwork-based CL method for medical imaging with a focus on skin lesion classification. Continual-GEN proposes an ensemble of groups approach that decomposes the training data for each domain into groups of semantically similar clusters. Given two domains, Continual-GEN assesses the similarity between them based on the distance between their ensembles and assigns a separate subnetwork if the similarity score is low, otherwise updating the same subnetwork to learn both domains. At inference, Continual-GEN selects the best subnetwork using a distance-based metric for each test data, which is directly used for classification. Our quantitative experiments on four skin lesion datasets demonstrate the superiority of Continual-GEN over state-of-the-art CL methods, highlighting its potential for practical applications in medical imaging. Our code: https://github.com/nourhanb/Continual-GEN.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ballerini, L., Fisher, R.B., Aldridge, B., Rees, J.: A color and texture based hierarchical K-NN approach to the classification of non-melanoma skin lesions. In: Celebi, M.E., Schaefer, G. (eds.) Color Medical Image Analysis, pp. 63–86. Springer, Dordrecht (2013). https://doi.org/10.1007/978-94-007-5389-1_4
Baweja, C., Glocker, B., Kamnitsas, K.: Towards continual learning in medical imaging. arXiv preprint arXiv:1811.02496 (2018)
Bayasi, N., Hamarneh, G., Garbi, R.: Culprit-Prune-Net: efficient continual sequential multi-domain learning with application to skin lesion classification. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12907, pp. 165–175. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87234-2_16
Bojchevski, A., Matkovic, Y., Günnemann, S.: Robust spectral clustering for noisy data: Modeling sparse corruptions improves latent embeddings. In: Proceedings of International Conference on Knowledge Discovery and Data Mining, pp. 737–746 (2017)
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597–1607 (2020)
Dekhovich, A., Tax, D.M.J., Sluiter, M.H.F., Bessa, M.A.: Continual prune-and-select: class-incremental learning with specialized subnetworks. Appl. Intell. 53(14), 17849–17864 (2023). https://doi.org/10.1007/s10489-022-04441-z
Esteva, A., et al.: Dermatologist-level classification of skin cancer with deep neural networks. Nature 542(7639), 115–118 (2017)
Fogelberg, K., Chamarthi, S., Maron, R.C., Niebling, J., Brinker, T.J.: Domain shifts in dermoscopic skin cancer datasets: Evaluation of essential limitations for clinical translation. New Biotechnol. 76, 106–117 (2023)
González, C., Ranem, A., Othman, A., Mukhopadhyay, A.: Task-agnostic continual hippocampus segmentation for smooth population shifts. In: Kamnitsas, K., et al. (eds.) Domain Adaptation and Representation Transfer: 4th MICCAI Workshop, DART 2022, Held in Conjunction with MICCAI 2022, Singapore, September 22, 2022, Proceedings, pp. 108–118. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-16852-9_11
Gutman, D., et al.: Skin lesion analysis toward melanoma detection: a challenge at the international symposium on biomedical imaging (ISBI) 2016, hosted by the international skin imaging collaboration (ISIC). arXiv:1605.01397 (2016)
Kawahara, J., Daneshvar, S., Argenziano, G., Hamarneh, G.: Seven-point checklist and skin lesion classification using multitask multimodal neural nets. IEEE J. Biomed. Health Inform. 23(2), 538–546 (2018)
Khosla, P., et al.: Supervised contrastive learning. In: Advances in Neural Information Processing Systems, vol. 33, pp. 18661–18673 (2020)
Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. Proc. Natl. Acad. Sci. 114(13), 3521–3526 (2017)
Li, Z., Hoiem, D.: Learning without forgetting. IEEE Trans. Pattern Anal. Mach. Intell. TPAMI 40(12), 2935–2947 (2017)
Mallya, A., Lazebnik, S.: PackNet: Adding multiple tasks to a single network by iterative pruning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7765–7773 (2018)
Özgün, S., Rickmann, A.-M., Roy, A.G., Wachinger, C.: Importance driven continual learning for segmentation across domains. In: Liu, M., Yan, P., Lian, C., Cao, X. (eds.) Machine Learning in Medical Imaging: 11th International Workshop, MLMI 2020, Held in Conjunction with MICCAI 2020, Lima, Peru, October 4, 2020, Proceedings, pp. 423–433. Springer International Publishing, Cham (2020). https://doi.org/10.1007/978-3-030-59861-7_43
Perkonigg, M., et al.: Dynamic memory to alleviate catastrophic forgetting in continual learning with medical imaging. Nat. Commun. 12(1), 5678 (2021)
Perkonigg, M., Hofmanninger, J., Langs, G.: Continual active learning for efficient adaptation of machine learning models to changing image acquisition. In: Feragen, A., Sommer, S., Schnabel, J., Nielsen, M. (eds.) IPMI 2021. LNCS, vol. 12729, pp. 649–660. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-78191-0_50
Prabhu, A., Torr, P.H.S., Dokania, P.K.: GDumb: a simple approach that questions our progress in continual learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 524–540. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58536-5_31
Sehwag, V., Chiang, M., Mittal, P.: SSD: a unified framework for self-supervised outlier detection. arXiv preprint arXiv:2103.12051 (2021)
Tschandl, P., Rosendahl, C., Kittler, H.: The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Sci. Data 5(1), 1–9 (2018)
Wang, L., Zhang, X., Su, H., Zhu, J.: A comprehensive survey of continual learning: theory, method and application. arXiv preprint arXiv:2302.00487 (2023)
Wen, D., et al.: Characteristics of publicly available skin cancer image datasets: a systematic review. Lancet Digit. Health 4(1), e64–e74 (2022)
Yoon, J., Jeong, W., Lee, G., Yang, E., Hwang, S.J.: Federated continual learning with weighted inter-client transfer. In: International Conference on Machine Learning, pp. 12073–12086 (2021)
Author information
Authors and Affiliations
Corresponding author
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
Bayasi, N., Du, S., Hamarneh, G., Garbi, R. (2023). Continual-GEN: Continual Group Ensembling for Domain-agnostic Skin Lesion Classification. In: Celebi, M.E., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2023 Workshops . MICCAI 2023. Lecture Notes in Computer Science, vol 14393. Springer, Cham. https://doi.org/10.1007/978-3-031-47401-9_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-47401-9_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-47400-2
Online ISBN: 978-3-031-47401-9
eBook Packages: Computer ScienceComputer Science (R0)