A Robust Method for Blood Vessel Extraction in Endoscopic Images with SVM-based Scene Classification

Mayank Golhar, Yuji Iwahori, M. K. Bhuyan, Kenji Funahashi, Kunio Kasugai

2017

Abstract

This paper proposes a model for blood vessel detection in endoscopic images. A novel SVM-based scene classification of endoscopic images is used. This SVM-based model classifies images into four classes on the basis of dye content and blood vessel presence in the scene, using various colour, edge and texture based features. After classification, a vessel extraction method is proposed which is based on the Frangi vesselness approach. In original Frangi Vesselness results, it is observed that many non-blood vessel edges are inaccurately detected as blood vessels. So, two additions are proposed, background subtraction and a novel dissimilarity-detecting filtering procedure, which are able to discriminate between blood vessel and non-blood vessel edges by exploiting the symmetric nature property of blood vessels. It was found that the proposed approach gave better accuracy of blood vessel extraction when compared with the vanilla Frangi Vesselness approach and BCOSFIRE filter, another state-of-art vessel delineation approach.

References

  1. Azzopardi, G., Strisciuglio, N., Vento, M., and Petkov, N. (2015). Trainable cosfire filters for vessel delineation with application to retinal images. Medical image analysis, 19(1):46-57.
  2. Frangi, A. F., Niessen, W. J., Vincken, K. L., and Viergever, M. A. (1998). Multiscale vessel enhancement filtering. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 130-137. Springer.
  3. Fraz, M. M., Remagnino, P., Hoppe, A., Uyyanonvara, B., Rudnicka, A. R., Owen, C. G., and Barman, S. A. (2012). Blood vessel segmentation methodologies in retinal images-a survey. In Computer methods and programs in biomedicine, Vol. 108(1), pp. 407-433. Elsevier.
  4. Hafner, M., Gangl, A., Wrba, F., Thonhauser, K., Schmidt, H.-P., Kastinger, C., Uhl, A., and Vecsei, A. (2007). Comparison of k-nn, svm, and nn in pit pattern classification of zoom-endoscopic colon images using cooccurrence histograms. In Image and Signal Processing and Analysis, 2007. ISPA 2007. 5th International Symposium on, pp. 516-521. IEEE.
  5. Ikeda, N., Usami, H., Iwahori, Y., Bhuyan, M., and Kasugai, K. (2016). Generating lambertian image by removing specular reflection component and difference of reflectance factor using hsv. In Proc. of ITC-CSCC 2016, T2-5, Computer Vision (2), pp.547-550.
  6. Kumar, V., Abbas, A. K., Fausto, N., and Aster, J. C. (2014). Robbins and Cotran pathologic basis of disease. Elsevier Health Sciences, 9th edition.
  7. Lin, B., Sun, Y., Sanchez, J. E., and Qian, X. (2015). Efficient vessel feature detection for endoscopic image analysis. IEEE Transactions on Biomedical Engineering, 62(4):1141-1150.
  8. Mohanty, A. A., Vaibhav, B., and Sethi, A. (2013). A framebased decision pooling method for video classification. In 2013 Annual IEEE India Conference (INDICON), pages 1-5. IEEE.
  9. Zhang, D., Wong, A., Indrawan, M., and Lu, G. (2000). Content-based image retrieval using gabor texture features. In IEEE Pacific-Rim Conference on Multimedia, University of Sydney, Australia, pages 392-395.
Download


Paper Citation


in Harvard Style

Golhar M., Iwahori Y., K. Bhuyan M., Funahashi K. and Kasugai K. (2017). A Robust Method for Blood Vessel Extraction in Endoscopic Images with SVM-based Scene Classification . In Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-222-6, pages 148-156. DOI: 10.5220/0006192601480156


in Bibtex Style

@conference{icpram17,
author={Mayank Golhar and Yuji Iwahori and M. K. Bhuyan and Kenji Funahashi and Kunio Kasugai},
title={A Robust Method for Blood Vessel Extraction in Endoscopic Images with SVM-based Scene Classification},
booktitle={Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2017},
pages={148-156},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006192601480156},
isbn={978-989-758-222-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - A Robust Method for Blood Vessel Extraction in Endoscopic Images with SVM-based Scene Classification
SN - 978-989-758-222-6
AU - Golhar M.
AU - Iwahori Y.
AU - K. Bhuyan M.
AU - Funahashi K.
AU - Kasugai K.
PY - 2017
SP - 148
EP - 156
DO - 10.5220/0006192601480156