Abstract
Annotating image data is one of the most time-consuming parts of the training of machine learning algorithms. With this contribution, we are looking for a solution that decreases the time needed for annotating images of the human retina created by Optical coherence tomography (OCT). As a first step, we use a simple annotation tool to test whether the sorting of images by their predicted amount of parts that contain anomalies decreases the time needed for annotation without increasing the number of annotation mistakes. The predictions are made by a convolutional neural network (CNN) that was trained on a previously annotated image set. We investigated the annotation behaviour in two groups of five subjects each. The first group received the (OCT) images in the order of recording, the second group sorted by the number of predicted anomalies. We observed a significant increase in annotation speed in the subjects of the second group while the quality of annotation remained at least stable.
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
Notes
References
Acuna, D., Ling, H., Kar, A., Fidler, S.: Efficient interactive annotation of segmentation datasets with polygon-RNN++. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 859–868 (2018)
Culotta, A., McCallum, A.: Reducing labeling effort for structured prediction tasks. In: AAAI, vol. 5, pp. 746–751 (2005)
Dias, P.A., Shen, Z., Tabb, A., Medeiros, H.: Freelabel: a publicly available annotation tool based on freehand traces. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 21–30. IEEE (2019)
Dutta, A., Zisserman, A.: The via annotation software for images, audio and video. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 2276–2279 (2019)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016). http://www.deeplearningbook.org
Hasan, R., Langner, H., Ritter, M., Eibl, M.: Investigating the robustness of pre-trained networks on OCT-dataset. In: Actual Problems of System and Software Engineering, November 2019
Karpathy, A.: Convnetjs. https://cs.stanford.edu/people/karpathy/convnetjs/index.html. Accessed 14 Feb 2020
Podoleanu, A.G.: Optical coherence tomography. J. Microscopy 247(3), 209–219 (2012). https://doi.org/10.1111/j.1365-2818.2012.03619.x. https://onlinelibrary.wiley.com/doi/abs/10.1111/j.1365-2818.2012.03619.x
Qin, X., He, S., Zhang, Z., Dehghan, M., Jagersand, M.: ByLabel: a boundary based semi-automatic image annotation tool. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1804–1813. IEEE (2018)
Resnikoff, S., et al.: Global data on visual impairment in the year 2002. Bull. World Health Organ. 82(11), 844–851 (2004)
Schindelin, J., et al.: Fiji: an open-source platform for biological-image analysis. Nat. Methods 9(7), 676–682 (2012)
Schmidt-Erfurth, U.M., et al.: Guidance for the treatment of neovascular age-related macular degeneration. Acta Ophthalmol. Scand. 85(5), 486–494 (2007)
Schrader, W.F.: Altersbedingte makuladegeneration. Der Ophthalmol. 103(9), 742–748 (2006)
Simeone, O.: A very brief introduction to machine learning with applications to communication systems. IEEE Trans. Cogn. Commun. Netw. 4(4), 648–664 (2018)
Specht, D.F., et al.: A general regression neural network. IEEE Trans. Neural Netw. 2(6), 568–576 (1991)
Swanson, E.A., et al.: In vivo retinal imaging by optical coherence tomography. Opt. Lett. 18(21), 1864–6 (1993)
Tseng, Q., et al.: Spatial organization of the extracellular matrix regulates cell–cell junction positioning. Proc. Natl. Acad. Sci. (2012). https://doi.org/10.1073/pnas.1106377109. https://www.pnas.org/content/early/2012/01/09/1106377109
Zysk, A.M., Nguyen, F.T., Oldenburg, A.L., Marks, D.L., Boppart, S.A.: Optical coherence tomography: a review of clinical development from bench to bedside. J. Biomed. Opt. 12(5), 051403 (2007)
Acknowledgement
We like to acknowledge that Prof. Dr. Andreas Stahl and the collaborators of the TOPOs project provided the OCT image data that was used in this study, as well as the ophthalmological background. TOPOs (“Therapievorhersage durch Analyse von Patientendaten in der Ophthalmologie”) is a collaborative project that is funded by BMBF (“Bundesministerium für Bildung und Forschung”, “Federal Ministry of Education & Resarch”) (FKZ: 13GW0170B) from March 2017 to January 2020.
The SMWK (“Sächsisches Staatsministerium für Wissenschaft, Kultur und Tourismus”) supported this work by funding the project “Digitale Produkt- und Prozessinnovationen 2020”, which contains a work package named “Entwicklung und Implementierung eines begehbaren Auges zur computergestützten Annotation von Augenkrankheiten in der virtuellen Realität”. This work describes findings that were made while working on this work package.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Schleier, S., Stolz, N., Langner, H., Hasan, R., Roschke, C., Ritter, M. (2020). Semi-automatic Annotation of OCT Images for CNN Training. In: Kurosu, M. (eds) Human-Computer Interaction. Design and User Experience. HCII 2020. Lecture Notes in Computer Science(), vol 12181. Springer, Cham. https://doi.org/10.1007/978-3-030-49059-1_49
Download citation
DOI: https://doi.org/10.1007/978-3-030-49059-1_49
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-49058-4
Online ISBN: 978-3-030-49059-1
eBook Packages: Computer ScienceComputer Science (R0)