Abstract
Medical image segmentation is a critical task in medical image analysis. In recent years, deep learning based approaches have shown exceptional performance when trained on a fully-annotated dataset. However, data annotation is often a significant bottleneck, especially for 3D medical images. Active learning (AL) is a promising solution for efficient annotation but requires an initial set of labeled samples to start active selection. When the entire data pool is unlabeled, how do we select the samples to annotate as our initial set? This is also known as the cold-start AL, which permits only one chance to request annotations from experts without access to previously annotated data. Cold-start AL is highly relevant in many practical scenarios but has been under-explored, especially for 3D medical segmentation tasks requiring substantial annotation effort. In this paper, we present a benchmark named COLosSAL by evaluating six cold-start AL strategies on five 3D medical image segmentation tasks from the public Medical Segmentation Decathlon collection. We perform a thorough performance analysis and explore important open questions for cold-start AL, such as the impact of budget on different strategies. Our results show that cold-start AL is still an unsolved problem for 3D segmentation tasks but some important trends have been observed. The code repository, data partitions, and baseline results for the complete benchmark are publicly available at https://github.com/MedICL-VU/COLosSAL.
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
Change history
31 October 2023
A correction has been published.
References
Antonelli, M.: The medical segmentation decathlon. Nat. Commun. 13(1), 4128 (2022)
Cardoso, M.J., et al.: Monai: an open-source framework for deep learning in healthcare. arXiv preprint arXiv:2211.02701 (2022)
Chandra, A.L., Desai, S.V., Devaguptapu, C., Balasubramanian, V.N.: On initial pools for deep active learning. In: NeurIPS 2020 Workshop on Pre-registration in Machine Learning, pp. 14–32. PMLR (2021)
Chen, L., et al.: Making your first choice: to address cold start problem in medical active learning. In: Medical Imaging with Deep Learning (2023)
Gaillochet, M., Desrosiers, C., Lombaert, H.: TAAL: test-time augmentation for active learning in medical image segmentation. In: Nguyen, H.V., Huang, S.X., Xue, Y. (eds.) DALI 2022. LNCS, vol. 13567, pp. 43–53. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-17027-0_5
Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: International Conference on Machine Learning, pp. 1050–1059. PMLR (2016)
Hacohen, G., Dekel, A., Weinshall, D.: Active learning on a budget: opposite strategies suit high and low budgets. arXiv preprint arXiv:2202.02794 (2022)
Hesamian, M.H., Jia, W., He, X., Kennedy, P.: Deep learning techniques for medical image segmentation: achievements and challenges. J. Digit. Imaging 32, 582–596 (2019)
Isensee, F., Jaeger, P.F., Kohl, S.A., Petersen, J., Maier-Hein, K.H.: nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods 18(2), 203–211 (2021)
Jin, Q., Yuan, M., Li, S., Wang, H., Wang, M., Song, Z.: Cold-start active learning for image classification. Inf. Sci. 616, 16–36 (2022)
Lewis, D.D., Catlett, J.: Heterogeneous uncertainty sampling for supervised learning. In: Machine Learning Proceedings 1994, pp. 148–156. Elsevier (1994)
Mittal, S., Tatarchenko, M., Çiçek, Ö., Brox, T.: Parting with illusions about deep active learning. arXiv preprint arXiv:1912.05361 (2019)
Nath, V., Yang, D., Landman, B.A., Xu, D., Roth, H.R.: Diminishing uncertainty within the training pool: active learning for medical image segmentation. IEEE Trans. Med. Imaging 40(10), 2534–2547 (2020)
Nath, V., Yang, D., Roth, H.R., Xu, D.: Warm start active learning with proxy labels and selection via semi-supervised fine-tuning. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds.) MICCAI 2022. LNCS, vol. 13438, pp. 297–308. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-16452-1_29
Nguyen, V.L., Shaker, M.H., Hüllermeier, E.: How to measure uncertainty in uncertainty sampling for active learning. Mach. Learn. 111(1), 89–122 (2022)
Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9(1), 62–66 (1979)
Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, vol. 32 (2019)
Ranganathan, H., Venkateswara, H., Chakraborty, S., Panchanathan, S.: Deep active learning for image classification. In: 2017 IEEE International Conference on Image Processing (ICIP), pp. 3934–3938. IEEE (2017)
Sener, O., Savarese, S.: Active learning for convolutional neural networks: a core-set approach. arXiv preprint arXiv:1708.00489 (2017)
Siméoni, O., Budnik, M., Avrithis, Y., Gravier, G.: Rethinking deep active learning: using unlabeled data at model training. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 1220–1227. IEEE (2021)
Yang, L., Zhang, Y., Chen, J., Zhang, S., Chen, D.Z.: Suggestive annotation: a deep active learning framework for biomedical image segmentation. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10435, pp. 399–407. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-66179-7_46
Yuan, M., Lin, H.T., Boyd-Graber, J.: Cold-start active learning through self-supervised language modeling. arXiv preprint arXiv:2010.09535 (2020)
Zhang, T., Ramakrishnan, R., Livny, M.: Birch: an efficient data clustering method for very large databases. ACM SIGMOD Rec. 25(2), 103–114 (1996)
Zhao, Z., Lu, W., Zeng, Z., Xu, K., Veeravalli, B., Guan, C.: Self-supervised assisted active learning for skin lesion segmentation. In: 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), pp. 5043–5046. IEEE (2022)
Zheng, H., et al.: Biomedical image segmentation via representative annotation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 5901–5908 (2019)
Zhu, Y., et al.: Addressing the item cold-start problem by attribute-driven active learning. IEEE Trans. Knowl. Data Eng. 32(4), 631–644 (2019)
Acknowledgements
This work was supported in part by the National Institutes of Health grants R01HD109739 and T32EB021937, as well as National Science Foundation grant 2220401. This work was also supported by the Advanced Computing Center for Research and Education (ACCRE) of Vanderbilt University.
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
Liu, H. et al. (2023). COLosSAL: A Benchmark for Cold-Start Active Learning for 3D Medical Image Segmentation. In: Greenspan, H., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2023. MICCAI 2023. Lecture Notes in Computer Science, vol 14221. Springer, Cham. https://doi.org/10.1007/978-3-031-43895-0_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-43895-0_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43894-3
Online ISBN: 978-3-031-43895-0
eBook Packages: Computer ScienceComputer Science (R0)
