Active Learning for Segmentation by Optimizing Content Information for Maximal Entropy
Segmentation is essential for medical image analysis tasks such as intervention planning, therapy guidance, diagnosis, treatment decisions. Deep learning is becoming increasingly prominent for segmentation, where the lack of annotations, however, often becomes the main limitation. Due to privacy concerns and ethical considerations, most medical datasets are created, curated, and allow access only locally. Furthermore, current deep learning methods are often suboptimal in translating anatomical knowledge between different medical imaging modalities. Active learning can be used to select an informed set of image samples to request for manual annotation, in order to best utilize the limited annotation time of clinical experts for optimal outcomes, which we focus on in this work. Our contributions herein are two fold: (1) we enforce domain-representativeness of selected samples using a proposed penalization scheme to maximize information at the network abstraction layer, and (2) we propose a Borda-count based sample querying scheme for selecting samples for segmentation. Comparative experiments with baseline approaches show that the samples queried with our proposed method, where both above contributions are combined, result in significantly improved segmentation performance for this active learning task.
This work was funded by the Swiss National Science Foundation (SNSF), a Highly Specialized Medicine (HSM2) grant of the Canton of Zurich, and the EU’s 7th Framework Program (Agreement No. 611889, TRANS-FUSIMO). We acknowledge NVIDIA GPU Grant support.
- 1.Baumgartner, C.F., Koch, L.M., Pollefeys, M., Konukoglu, E.: An Exploration of 2D and 3D Deep Learning Techniques for Cardiac MR Image Segmentation. In: Pop, M., et al. (eds.) STACOM 2017. LNCS, vol. 10663, pp. 111–119. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-75541-0_12CrossRefGoogle Scholar
- 3.Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: International Conference on Machine Learning (ICML), pp. 1050–1059 (2016)Google Scholar
- 4.Gal, Y., Islam, R., Ghahramani, Z.: Deep Bayesian active learning with image data. In: Proceedings of the 34th International Conference on Machine Learning (ICML) (2017)Google Scholar
- 6.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_46CrossRefGoogle Scholar
- 8.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.) Medical Image Computing and Computer Assisted Intervention (MICCAI), pp. 361–369. Springer International Publishing, Cham (2018). https://doi.org/10.1007/978-3-030-00937-3_42. ISBN: 978-3-030-00937-3CrossRefGoogle Scholar
- 9.Gatys, L.A., Ecker, A.S., Bethge, M.: Image style transfer using convolutional neural networks. In: IEEE CVPR, pp. 2414–2423 (2016)Google Scholar
- 11.Abadi, M., Agarwal, A., Barham, P., Brevdo, E., et al.: TensorFlow: large-scale machine learning on heterogeneous systems (2015). www.tensorflow.org