Abstract
Ulcerative Colitis (UC) is an inflammatory bowel disease that causes inflammation, ulcers and bleeding of the colon affecting more than 500,000 people in the United States. To achieve the therapeutic objectives for UC, which are to first induce and then maintain disease remission, physicians need to evaluate the severity of UC. However, objective assessment of US is difficult because of the non-uniform nature of symptoms and large variations in disease presentation. To address this, in our previous work, we developed two different approaches in which one uses the image textures, and the other uses CNN (Convolutional Neural Network) to measure and objectively classify the severity of UC as seen on optical colonoscopy video frames. However, we found that the image texture based approach could not handle large numbers of variations in patterns, and the CNN based approach could not achieve very high accuracy. In this paper, we improve our CNN based approach in two ways to provide better accuracy for UC severity classification. We add more thorough and essential preprocessing, subdivide each class of UC severity and generate more classes for the classification to accommodate large variations in patterns. The experimental results show that the proposed preprocessing and generation of more classes can improve the overall accuracy of automated classification of the severity of UC.
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
References
Kappelman, M.D., Rifas-Shiman, S.L., Kleinman, K., Ollendorf, D., Bousvaros, A., Grand, R.J., et al.: The prevalence and geographic distribution of Crohn’s disease and ulcerative colitis in the United State. Clin. Gastroenterol. Hepatol. 5, 1424–1429 (2007)
Nosato, H., Sakanashi, H., Takahashi, E., Murakawa, M.: An objective evaluation method of ulcerative colitis with optical colonoscopy images based on higher order local auto-correlation features. In: IEEE 11th International Symposium on Biomedical Imaging ISBI, pp. 89–92 (2014)
Dahal, A., Oh, J., Tavanapong, W., Wong, J., de Groen, P.C.: Detection of ulcerative colitis severity in colonoscopy video frames. In: IEEE/ACM International Workshop on Content-Based Multimedia Indexing - CBMI 2015, Prague, Czech Republic, 10–12 June 2015, pp. 1–6 (2015). http://doi.org/10.1109/CBMI.2015.7153617
Alammari, A., Rezbaul Islam, A.B.M., Oh, J., Tavanapong, W., Wong, J., De Groen, P.C.: Classification of ulcerative colitis severity in colonoscopy videos using CNN. In: 9th International Conference on Information Management and Engineering (ICIME 2017), Barcelona, Spain, 9–11 October 2017, pp. 232–237 (2017)
De Chambrun, G.I.P., Peyrin-Biroulet, L., Lémann, M., Colombel, J.F.: Clinical implications of mucosal healing for the management of IBD. Nat. Rev. Gastroenterol. Hepatol. 7(1), 15–29 (2010)
Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks. In: Proceedings of Neural Information Processing Systems 2012 (NIPS), pp. 1106–1114 (2012)
Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)
Abadi, M., Agarwal, A., Barham, P., et al.: TensorFlow: large-scale machine learning on heterogeneous distributed systems (2016). https://arxiv.org/abs/1603.04467
Alammari, A., Rezbaul Islam, A.B.M., Oh, J., Tavanapong, W., Wong, J., de Groen, P.C.: Non-informative frame classification in colonoscopy videos using CNNs. In: 3rd International Conference on Biomedical Imaging, Signal Processing (ICBSP 2018), Bari, Italy, 11–13 October 2018, pp. 35–42, (2018)
Wang, Y., Tavanapong, W., Wong, J., Oh, J., de Groen P.C.: Light reflection detection for colonoscopy images. Technical report, Department of Computer Science, Iowa State University (2009)
Tajbakhsh, N., et al.: Convolutional neural networks for medical image analysis: full training or fine tuning? IEEE Trans. Med. Imaging 35(5), 1299–1312 (2016)
Acknowledgements
This research was supported in part by a grant from the NIH (Grant #1R01DK106130-01A1). Tavanapong, Wong, and Oh have an equity interest and management role in EndoMetric Corporation, Ames, IA50014, USA, a for profit company that markets endoscopy-related software. De Groen has a financial interest in EndoMetric. The terms of this arrangement have been reviewed and approved by Iowa State University and University of Minnesota in accordance with its conflict of interest policies.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Tejaswini, S.V.L.L., Mittal, B., Oh, J., Tavanapong, W., Wong, J., de Groen, P.C. (2019). Enhanced Approach for Classification of Ulcerative Colitis Severity in Colonoscopy Videos Using CNN. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2019. Lecture Notes in Computer Science(), vol 11845. Springer, Cham. https://doi.org/10.1007/978-3-030-33723-0_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-33723-0_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-33722-3
Online ISBN: 978-3-030-33723-0
eBook Packages: Computer ScienceComputer Science (R0)