Active Learning Technique for Multimodal Brain Tumor Segmentation Using Limited Labeled Images
- 1 Citations
- 1.9k Downloads
Abstract
Image segmentation is an essential step in biomedical image analysis. In recent years, deep learning models have achieved significant success in segmentation. However, deep learning requires the availability of large annotated data to train these models, which can be challenging in biomedical imaging domain. In this paper, we aim to accomplish biomedical image segmentation with limited labeled data using active learning. We present a deep active learning framework that selects additional data points to be annotated by combining U-Net with an efficient and effective query strategy to capture the most uncertain and representative points. This algorithm decouples the representative part by first finding the core points in the unlabeled pool and then selecting the most uncertain points from the reduced pool, which are different from the labeled pool. In our experiment, only 13% of the dataset was required with active learning to outperform the model trained on the entire 2018 MICCAI Brain Tumor Segmentation (BraTS) dataset. Thus, active learning reduced the amount of labeled data required for image segmentation without a significant loss in the accuracy.
Keywords
Deep learning Active learning SegmentationReferences
- 1.Zaitoun, N., et al.: Survey on image segmentation techniques. Procedia Comput. Sci. 65, 797–806 (2015)CrossRefGoogle Scholar
- 2.Long, J., et al.: Fully convolutional networks for semantic segmentation. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)Google Scholar
- 3.Girshick, R.B. et al.: Rich feature hierarchies for accurate object detection and semantic segmentation. CoRR. abs/1311.2524 (2013)Google Scholar
- 4.Chen, H., Qi, X., Cheng, J.Z., Heng, P.A.: Deep contextual networks for neuronal structure segmentation. In: AAAI, pp. 1167–1173 (2016)Google Scholar
- 5.Chen, H., Qi, X., Yu, L., Heng, P.A.: DCAN: deep contour-aware networks for accurate gland segmentation. In: CVPR, pp. 2487–2496 (2016)Google Scholar
- 6.Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28 CrossRefGoogle Scholar
- 7.Settles, B.: Active Learning Literature Survey. University of Wisconsin-Madison (2009)Google Scholar
- 8.Yin, C., et al.: Deep similarity-based batch mode active learning with exploration-exploitation. In: Raghavan, V. et al. (ed.) ICDM, pp. 575–584. IEEE Computer Society (2017)Google Scholar
- 9.Yang, L., et al.: Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentation. CoRR. abs/1706.04737 (2017)Google Scholar
- 10.Zheng, H., et al.: Biomedical Image Segmentation via Representative Annotation (2019)Google Scholar
- 11.Multimodal Brain Tumor Segmentation Challenge (2018). https://www.med.upenn.edu/sbia/brats2018/data.html
- 12.Isensee, F., Kickingereder, P., Wick, W., Bendszus, M., Maier-Hein, K.H.: Brain tumor segmentation and radiomics survival prediction: contribution to the BRATS 2017 challenge. In: Crimi, A., Bakas, S., Kuijf, H., Menze, B., Reyes, M. (eds.) BrainLes 2017. LNCS, vol. 10670, pp. 287–297. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-75238-9_25CrossRefGoogle Scholar
- 13.Loy, C.C., et al.: Stream-based joint exploration-exploitation active learning. In: CVPR, pp. 1560–1567. IEEE Computer Society (2012)Google Scholar
- 14.Guo, Y., Schuurmans, D.: Discriminative batch mode active learning. In: Platt, J.C. et al. (ed.) NIPS, pp. 593–600. Curran Associates, Inc. (2007)Google Scholar
- 15.Xu, H., Wang, X., Liao, Y., Zheng, C.: An uncertainty sampling-based active learning approach for support vector machines. In: International Conference on Artificial Intelligence and Computational Intelligence, Shanghai 2009, pp. 208–213 (2009)Google Scholar
- 16.Cardoso, T.N.C., et al.: Ranked batch-mode active learning. Inf. Sci. 379, 313–337 (2017)CrossRefGoogle Scholar
- 17.Gal, Y. et al.: Deep Bayesian Active Learning with Image Data. CoRR. abs/1703.02910 (2017)Google Scholar