Abstract
An important feature of medical images is high variability, which makes it difficult to use traditional models of machine learning and tightens the requirements for the database size for training of Convolutional Neural Networks (CNN). Neural network approaches to segmentation are relevant and effective, which leads to their widespread use. However, the limited amount of training facilities available, which is typical for medical image processing, requires the search for additional solutions. In this chapter, we propose method to improve the quality of segmentation of polyps in endoscopic images using CNN introducing a preliminary stage of binary classification based on the use of global features extracted from the image. Our research show: using the binary classification as a preliminary segmentation stage increases Dice score more than 10% in conditionals of small database in CNN training.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Hong, J.H., Rho, S.-Y., Hong, Y.S.: Trends in the aggressiveness of end-of-life care for advanced stomach cancer patients. Cancer Res Treat 45(4), 270–275 (2013)
Pogorelov, K., Riegler, M., Eskeland, S.L., de Lange, T., Johansen, D., Griwodz, C., Schmidt, P.T., Halvorsen, P.: Efficient disease detection in gastrointestinal videos–global features versus neural networks. J. Multimedia Tools Appl 76(21), 22493–22525 (2017)
Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995)
Ho, T.K.: Random decision forests. In: 3rd International Conference Document Analysis and Recognition, pp. 278–282 (1995)
Li, B., Meng, M.Q., Xu, L.: A comparative study of shape features for polyp detection in wireless capsule endoscopy images. In: 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 3731–3734 (2009)
Karargyris, A., Bourbakis, N.: Identification of polyps in wireless capsule endoscopy videos using log Gabor filters. In: 2009 IEEE/NIH Life Science Systems and Applications Workshop, pp. 143–147 (2009)
Smith, S.M., Brady, J.M.: SUSAN—a new approach to low level image processing. Int. J. Comput. Vis. 23(1), 45–78 (1997)
Karargyris, A., Bourbakis, N.: Detection of small bowel polyps and ulcers in wireless capsule endoscopy videos. IEEE Trans. Biomed. Eng. 58, 2777–2786 (2011)
Nawarathna, R.D., Oh, J., Yuan, X., Lee, J., Tang, S.J.: Abnormal image detection using texton method in wireless capsule endoscopy videos. In: Zhang, D., Sonka, M. (eds.) Medical Biometrics, LNCS, vol. 6165, pp. 153–162. Springer, Berlin, Heidelberg (2010)
Park, S., Lee, M., Kwak, N.: Polyp detection in colonoscopy videos using deeply-learned hierarchical features. Seoul Nat. Univ., pp. 1–4 (2015)
Tajbakhsh, N., Gurudu, S.R., Liang, J.: Automatic polyp detection in colonoscopy videos using an ensemble of convolutional neural networks. In; IEEE 12th International Symposium Biomedical Imaging, pp. 79–83 (2015)
Akbari, M., Mohrekesh, M., Esfahani, E.N., Soroushmehr, S.M.R., Karimi, N., Samavi, S., Najarian, K.: Polyp segmentation in colonoscopy images using fully convolutional network. In: 40th Annual International Conference on IEEE Engineering in Medicine and Biology Society, pp. 1–10 (2018)
Chatzichristofis, S.A., Boutalis, Y.S., Lux, M.: Selection of the proper compact composite descriptor for improving content-based image retrieval. In: 6th IASTED International Conference Signal Processing, Pattern Recognition and Applications, pp. 134–140 (2009)
Tamura, H., Mori, S., Yamawaki, T.: Textural features corresponding to visual perception. IEEE Trans. Syst., Man, and Cybern 8(6), 460–473 (1978)
Rosenfeld, A., Troy, E.: Visual Texture Analysis. Technical report, pp. 70–116 (1970)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE Computer Society Conference Computer Vision and Pattern Recognition, vol. 1, pp. 886–893 (2005)
Pogorelov, K., Randel, K.R., Griwodz, C., Eskeland, S.L., de Lange, T., Johansen, D., Spampinato, C., Dang-Nguyen, D., Lux, M., Schmidt, P.T., Riegler, M., Halvorsen, P.: Kvasir: A multi-class image dataset for computer aided gastrointestinal disease detection. In: 8th ACM Conference Multimedia Systems, pp. 164–169 (2017)
Bernal, J., Sánchez, F. J., Fernández-Esparrach, G., Gil, D., Rodríguez, C., Vilariño, F.: WM-DOVA maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physicians. Comput. Med. Imaging Graph. 43, 99–111 (2015)
Bernal, J., Sanchez, J., Vilariño, F.: Towards automatic polyp detection with a polyp appearance model. Pattern Recogn. 45(9), 3166–3182 (2012)
Silva, J.S., Histace, A., Romain, O., Dray, X., Granado, B., Towards embedded detection of polyps in WCE images for early diagnosis of colorectal cancer. Int. J. Comput. Assist. Radiol. Surg. 9(2), 283–293 (2014)
Manjunath, B.S., Salembier, P., Sikora, T.: Introduction to MPEG-7: Multimedia Content Description Interface. Wiley, N.Y. (2002)
Huang, J., Kumar, S.R., Mitra, M., Zhu, W.-J., Zabih, R.: Image indexing using color correlograms. IEEE Conf. Comput. Vis. Pattern Recognit. 762–768 (1997)
Bosch, A., Zisserman, A., Munoz, X.: Representing shape with a spatial pyramid kernel. In: 6th ACM International Conference Image and Video Retrieval, pp. 401–408 (2007)
van der Maaten, L.J.P., Hinton, G.E.: Visualizing high-dimensional data using t-SNE. J. Mach. Learn. Res. 9, 2579–2605 (2008)
Fisher, R.A.: The use of multiple measurements in taxonomic problems. Ann Eugenics 7(2), 179–188 (1936)
Freund, Y., Schapire, R.E.: A decision-theoretic generalization of on-line learning and an application to boosting. J. Comput. Syst. Sci. 55(1), 119–139 (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Obukhova, N.A., Motyko, A.A., Pozdeev, A.A. (2020). Two-Stage Method for Polyps Segmentation in Endoscopic Images. In: Favorskaya, M., Jain, L. (eds) Computer Vision in Control Systems—6. Intelligent Systems Reference Library, vol 182. Springer, Cham. https://doi.org/10.1007/978-3-030-39177-5_8
Download citation
DOI: https://doi.org/10.1007/978-3-030-39177-5_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-39176-8
Online ISBN: 978-3-030-39177-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)