Abstract
The recent success of deep learning approaches relies partly on large amounts of well annotated training data. For natural images object annotation is easy and cheap. For biomedical images however, annotation crucially depends on the availability of a trained expert whose time is typically expensive and scarce. To ensure efficient annotation, only the most relevant objects should be presented to the expert. Currently, no approach exists that allows to select those for a multiclass detection problem. Here, we present an active learning framework that identifies the most relevant samples from a large set of not annotated data for further expert annotation. Applied to brightfield images of red blood cells with seven subtypes, we train a faster R-CNN for single cell identification and classification, calculate a novel confidence score using dropout variational inference and select relevant images for annotation based on (i) the confidence of the single cell detection and (ii) the rareness of the classes contained in the image. We show that our approach leads to a drastic increase of prediction accuracy with already few annotated images. Our original approach improves classification of red blood cell subtypes and speeds up the annotation. This important step in diagnosing blood diseases will profit from our framework as well as many other clinical challenges that suffer from the lack of annotated training data.
This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 675115 – RELEVANCE – H2020-MSCA-ITN-2015/H2020-MSCA-ITN-2015. CM acknowledges support from the BMBF (Project MicMode).
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Andolfo, I., et al.: Multiple clinical forms of dehydrated hereditary stomatocytosis arise from mutations in piezo1. Blood 121(19), 3925–3935 (2013)
Coudray, N., et al.: Classification and mutation prediction from non-small cell lung cancer histopathology images using deep learning. Nat. Med. 24(10), 1559 (2018)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR09 (2009)
Esteva, A., et al.: Dermatologist-level classification of skin cancer with deep neural networks. Nature 542(7639), 115 (2017)
Gal, Y., Islam, R., Ghahramani, Z.: Deep bayesian active learning with image data. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 1183–1192. JMLR. org (2017)
Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440–1448 (2015)
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587 (2014)
Hw, G.L., Wortis, M., Mukhopadhyay, R.: Stomatocyte-discocyte-echinocyte sequence of the human red blood cell: evidence for the bilayer-couple hypothesis from membrane mechanics. Proc. Natl. Acad. Sci. 99(26), 16766–16769 (2002)
Ilhan, H.O., Amasyali, M.F.: Active learning as a way of increasing accuracy. Int. J. Comput. Theory Eng. 6(6), 460 (2014)
Kendall, A., Gal, Y.: What uncertainties do we need in bayesian deep learning for computer vision? In: Advances in Neural Information Processing Systems, pp. 5574–5584 (2017)
Minetti, G., et al.: Red cell investigations: art and artefacts. Blood Rev. 27(2), 91–101 (2013)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99 (2015)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Xu, M., Papageorgiou, D.P., Abidi, S.Z., Dao, M., Zhao, H., Karniadakis, G.E.: A deep convolutional neural network for classification of red blood cells in sickle cell anemia. PLoS Comput. Biol. 13(10), e1005746 (2017)
Acknowledgements
CM acknowledges support from the DFG funded SFB1243 (A09) and the “MicMode-I2T” project (FKZ#017x1710D) funded by the Federal Ministry of Education and Research of Germany (BMBF), DLR project management, in the “e:Med” framework program.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Sadafi, A. et al. (2019). Multiclass Deep Active Learning for Detecting Red Blood Cell Subtypes in Brightfield Microscopy. In: Shen, D., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2019. MICCAI 2019. Lecture Notes in Computer Science(), vol 11764. Springer, Cham. https://doi.org/10.1007/978-3-030-32239-7_76
Download citation
DOI: https://doi.org/10.1007/978-3-030-32239-7_76
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32238-0
Online ISBN: 978-3-030-32239-7
eBook Packages: Computer ScienceComputer Science (R0)