Testing an Image Mining Approach to Obtain Pressure Ulcers Stage and Texture

Renato V. Guadagnin, Levy Aniceto Santana, Rinaldo de Souza Neves

2015

Abstract

Improvement of pressure ulcers (PU) images analysis through computerized techniques is advantageous both to medical assistance institutions and to patients’ life quality. The scientific challenge is to improve assistance to patients with PU by means of reliable image analysis procedures. Diagnosis of stage and predominant texture in a PU is essentially an image colour classification problem that can use existing knowledge. This study performs a classification of pressure ulcers images through an algorithm based on ID3 to construct a decision tree that has RGB statistics as input features and PU stage and texture as target features. A decision tree is constructed first by classification of 18 images of a training set. Then this tree is tested in a set of 45 PU images. Acceptable classification accuracy for training sets was not confirmed in test set.

References

  1. Bouchaert, R. R. et al. Weka Manual for Version 3-7-12, Hamilton, New Zealand: University of Waikato, 2014.
  2. Ferreira, T., Rasband, W. ImageJ User Guide. IJ1.46r, October 2012. http://imagej.nih.gov/ij/docs/guide/ user-guide.pdf [access 04/Aug/2014]
  3. Guadagnin, R. V., Neves, R. S., Santana, L. A. Preliminary results from an image mining approach to support pressure ulcers analysis. In: Proceedings of the 9th Open German-Russian Workshop on Pattern Recognition and Image Understanding, Koblenz (Germany): Dec/2014.
  4. Luger, GF. Inteligência Artificial. Estrutura e estratégias para a solução de problemas complexos, 4. Ed, \Porto Alegre (Brazil): Bookman, 2004.
  5. Scharma, AK, Sahni, S. A Comparative Study of Classification Algorithms for Spam Email Data Analysis, in: International Journal on Computer Science and Engineering (IJCSE), Vol. 3 No. 5 May 2011, p. 1890-1895.
  6. Soukup, T., Davidson, I. Visual Data Mining, USA: Wiley, 2002.
  7. Squire, DMcG, CSE5230 Tutorial: The ID3 Decision Tree Algorithm: Monash University, 2004.
  8. Veredas, F, Mesa, H, Morente, L, Binary Tissue Classification on Wound Images with Neural Networks and Bayesian Classifiers, in: IEEE Transactions on Medical Images, Vol. 29, No. 2, February 2010.
  9. Witten, IH, Frank, E. Data mining: practical machine learning tools and techniques with Java Implementation. USA: Morgan Kaufmann, 1999.
Download


Paper Citation


in Harvard Style

V. Guadagnin R., Aniceto Santana L. and de Souza Neves R. (2015). Testing an Image Mining Approach to Obtain Pressure Ulcers Stage and Texture . In Proceedings of the 5th International Workshop on Image Mining. Theory and Applications - Volume 1: IMTA-5, (VISIGRAPP 2015) ISBN 978-989-758-094-9, pages 22-28. DOI: 10.5220/0005457500220028


in Bibtex Style

@conference{imta-515,
author={Renato V. Guadagnin and Levy Aniceto Santana and Rinaldo de Souza Neves},
title={Testing an Image Mining Approach to Obtain Pressure Ulcers Stage and Texture},
booktitle={Proceedings of the 5th International Workshop on Image Mining. Theory and Applications - Volume 1: IMTA-5, (VISIGRAPP 2015)},
year={2015},
pages={22-28},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005457500220028},
isbn={978-989-758-094-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 5th International Workshop on Image Mining. Theory and Applications - Volume 1: IMTA-5, (VISIGRAPP 2015)
TI - Testing an Image Mining Approach to Obtain Pressure Ulcers Stage and Texture
SN - 978-989-758-094-9
AU - V. Guadagnin R.
AU - Aniceto Santana L.
AU - de Souza Neves R.
PY - 2015
SP - 22
EP - 28
DO - 10.5220/0005457500220028