COMBINED MACHINE LEARNING WITH MULTI-VIEW MODELING FOR ROBUST WOUND TISSUE ASSESSMENT

Hazem Wannous, Yves Lucas, Sylvie Treuillet

2010

Abstract

From colour images acquired with a hand held digital camera, an innovative tool for assessing chronic wounds has been developed. It combines both types of assessment, colour analysis and dimensional measurement of injured tissues in a user-friendly system. Colour and texture descriptors have been extracted and selected from a sample database of wound tissues, before the learning stage of a support vector machine classifier with perceptron kernel on four categories of tissues. Relying on a triangulated 3D model captured using uncalibrated vision techniques applied on a stereoscopic image pair, a fusion algorithm elaborates new tissue labels on each model triangle from each view. The results of 2D classification are merged and directly mapped on the mesh surface of the 3D wound model. The result is a significative improvement in the robustness of the classification. Real tissue areas can be computed by retro projection of identified regions on the 3D model.

References

  1. Albouy, B., Koenig, E., Treuillet, S., and Y.Lucas: (2006). Accurate 3d structure measurements from two uncalibrated views. In ACIVS, pages 1111-1121,.
  2. Callieri, M., Cignoni, P., Coluccia, M., Gaggio, G., Pingi, P., Romanelli, M., and Scopigno, R. (2003). Derma : monitoring the evolution of skin lesions with a 3d system. In 8th Int. Work. on Vis. Mod. and Visualization, pages 167-174.
  3. Carson, C., Belongie, S., Greenspan, H., and Malik, J. (2002). Blobworld: image segmentation using expectation-maximization and its application to image querying. IEEE Trans. PAMI, 24(8):1026-1038.
  4. Chapelle, O., Vapnik, V., Bousquet, O., and Mukherjee, S. (2001). Choosing kernel parameters for support vector machines. Machine Learning, pages 131-160.
  5. Comaniciu, D. and Meer, P. (2002). Mean shift: a robust approach toward feature space analysis. IEEE Trans. PAMI, 24(5):603-619.
  6. Deng, Y., Kenney, S., Moore, M., and Manjunath, B. S. (1999). Peer group filtering and perceptual color image quantization. In IEEE Inter. Symp. on Circ. and Sys. VLSI (ISCAS'99), volume 4, pages 21-24, Orlando, FL.
  7. Deng, Y. and Manjunath, B. S. (2001). Unsupervised segmentation of colour-texture regions in images and video. IEEE Trans. PAMI 7801, 23:800-810.
  8. Huang, T., Weng, R. C., and Lin, C.-J. (2006). Generalized bradley-terry models and multi-class probability estimates. Journal of Machine Learning Research, 7:85- 115.
  9. Jones, C. D., Plassmann, P., Stevens, R. F., Pointer, M. R., and McCarthy, M. B. (2006). Good practice guide to the use of mavis ii. Technical report, Medical Imaging Research Unit TR-07-06, Univ. of Glamorgan.
  10. Kolesnik, M. and Fexa, A. (2004). Segmentation of wounds in the combined color-texture feature space. SPIE Medical Imaging, 5370:549-556.
  11. Krouskop, T. A., Baker, R., and Wilson, M. S. (2002). A noncontact wound measurement system. J Rehabil Res Dev, 39(3):337-345.
  12. Landis, J. and Koch, G. (1977). The measurement of observer agreement for categorical data. Biometrics, 33:159-174.
  13. Lin, H.-T. and Li., L. (2005). Infinite ensemble learning with support vector machines. J. Gama et al., eds., Machine Learning: ECML 7805, Lecture Notes in Artificial Intelligence, 3720:242-254, Springer-Verlag.
  14. Malian, A., Heuvel van den, F., and Azizi, A. (2002). A robust photogrammetric system for wound measurement. In International Archives of Photogrammetry and Remote Sensing, volume 34, pages 264 -269, Corfu, Greece.
  15. Oduncu, H., Hoppe, H., Clark, M., Williams, R., and Harding, K. (2004). Analysis of skin wound images using digital color image processing: a preliminary communication. Int J Low Extrem Wounds, 3(3):151-156.
  16. Ojala, T., Pietikainen, M., and Maenpaa, T. (2002). Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans. PAMI, 24(7):971-987.
  17. Treuillet, S., Albouy, B., and Lucas, Y. (2009). Threedimensional assessment of skin wounds using a standard digital camera. IEEE Trans. on Medical Imaging, 28:752-762.
  18. Wannous, H., Treuillet, S., and Lucas, Y. (2007). Supervised tissue classification from color images for a complete wound assessment tool. In 29th Inter. Conf. of the IEEE Eng. in Med. and Bio. Soc. EMBS'07, pages 6031-6034.
  19. Wannous, H., Treuillet, S., and Lucas, Y. (2010). Robust tissue classification for reproducible wound assessment in telemedicine environments. to appear in the Journal of Electronic Imaging.
  20. Zheng, H., Bradley, L., Patterson, D., Galushka, M., and Winder, J. (2004). New protocol for leg ulcer tissue classification from colour images. In 26th Inter. Conf. of the IEEE Eng. in Med. and Bio. Soc. EMBS'04, volume 1, pages 1389-1392.
Download


Paper Citation


in Harvard Style

Wannous H., Lucas Y. and Treuillet S. (2010). COMBINED MACHINE LEARNING WITH MULTI-VIEW MODELING FOR ROBUST WOUND TISSUE ASSESSMENT . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2010) ISBN 978-989-674-028-3, pages 98-104. DOI: 10.5220/0002833300980104


in Bibtex Style

@conference{visapp10,
author={Hazem Wannous and Yves Lucas and Sylvie Treuillet},
title={COMBINED MACHINE LEARNING WITH MULTI-VIEW MODELING FOR ROBUST WOUND TISSUE ASSESSMENT},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2010)},
year={2010},
pages={98-104},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002833300980104},
isbn={978-989-674-028-3},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2010)
TI - COMBINED MACHINE LEARNING WITH MULTI-VIEW MODELING FOR ROBUST WOUND TISSUE ASSESSMENT
SN - 978-989-674-028-3
AU - Wannous H.
AU - Lucas Y.
AU - Treuillet S.
PY - 2010
SP - 98
EP - 104
DO - 10.5220/0002833300980104