Comparing Machine Learning Techniques in a Hyperemia Grading Framework

L. S. Brea, N. Barreira, A. Mosquera, H. Pena-Verdeal, E. Yebra-Pimentel

Abstract

Hyperemia is the occurrence of redness in a certain tissue. When it takes place on the bulbar conjunctiva, it can be an early symptom of different pathologies, hence, the importance of its quick evaluation. Experts grade hyperemia as a value in a continuous scale, according to the severity level. As it is a subjective and time consuming task, its automatisation is a priority for the optometrists. To this end, several image features are computed from a video frame that shows the patient’s eye. Then, these features are transformed to the grading scale by means of machine learning techniques. In previous works, we have analysed the performance of several regression algorithms. However, since the experts only use a finite number of values in each grading scale, in this paper we analyse how classifiers perform the task in comparison to regression methods. The results show that the classification techniques usually achieve a lower training error value, but the regression approaches classify correctly a larger number of samples.

References

  1. Aha, D. W., Kibler, D., and Albert, M. K. (1991). Instance-based learning algorithms. Machine Learning, 6(1):37-66.
  2. Baum, E. B. (1988). On the capabilities of multilayer perceptrons. Journal of complexity, 4(3):193-215.
  3. Breiman, L. (2001). Random forests. Machine Learning, 45(1):5-32.
  4. Buhmann, M. D. (2000). Radial basis functions. Acta Numerica 2000, 9:1-38.
  5. Canny, J. (1986). A computational approach to edge detection. Pattern Analysis and Machine Intelligence, IEEE Transactions on, (6):679-698.
  6. Chang, C.-C. and Lin, C.-J. (2011). LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2:27:1-27:27.
  7. Cooper, G. F. and Herskovits, E. (1991). A bayesian method for constructing bayesian belief networks from databases. In Proceedings of the Seventh conference on Uncertainty in Artificial Intelligence, pages 86-94. Morgan Kaufmann Publishers Inc.
  8. Efron, N., Morgan, P. B., and Katsara, S. S. (2001). Validation of grading scales for contact lens complications. Ophthalmic and Physiological Optics, 21(1):17-29.
  9. Fieguth, P. and Simpson, T. (2002). Automated measurement of bulbar redness. Investigative Ophthalmology and Visual Science, 43(2):340-347.
  10. Friedman, N., Geiger, D., and Goldszmidt, M. (1997). Bayesian network classifiers. Machine learning, 29(2- 3):131-163.
  11. Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., and Witten, I. H. (2009). The WEKA data mining software: An update. ACM SIGKDD Explorations Newsletter, 11(1):10-18.
  12. Hastie, T., Tibshirani, R., et al. (1998). Classification by pairwise coupling. The annals of statistics, 26(2):451- 471.
  13. Holte, R. C. (1993). Very simple classification rules perform well on most commonly used datasets. Machine learning, 11(1):63-90.
  14. Jensen, F. V. (1996). An introduction to Bayesian networks, volume 210. UCL press London.
  15. John, G. H. and Langley, P. (1995). Estimating continuous distributions in bayesian classifiers. In Proceedings of the Eleventh conference on Uncertainty in artificial intelligence, pages 338-345. Morgan Kaufmann Publishers Inc.
  16. Keerthi, S. S., Shevade, S. K., Bhattacharyya, C., and Murthy, K. R. K. (2001). Improvements to platt's SMO algorithm for SVM classifier design. Neural Computation, 13(3):637-649.
  17. Kohavi, R. (1995). The power of decision tables. In Machine Learning: ECML-95, pages 174-189. Springer.
  18. Papas, E. B. (2000). Key factors in the subjective and objective assessment of conjunctival erythema. Investigative Ophthalmology and Visual Science, 41(3):687- 691.
  19. Platt, J. et al. (1999). Fast training of support vector machines using sequential minimal optimization. Advances in kernel methodssupport vector learning, 3.
  20. Quinlan, J. R. (2014). C4. 5: programs for machine learning. Elsevier.
  21. Quinlan, J. R. et al. (1992). Learning with continuous classes. In 5th Australian joint conference on artificial intelligence, volume 92, pages 343-348. Singapore.
  22. Rodriguez, J. D., Johnston, P. R., Ousler III, G. W., Smith, L. M., and Abelson, M. B. (2013). Automated grading system for evaluation of ocular redness associated with dry eye. Clinical ophthalmology (Auckland, NZ), 7:1197.
  23. Rolando, M. and Zierhut, M. (2001). The ocular surface and tear film and their dysfunction in dry eye disease. Survey of Ophthalmology, 45, Supplement 2(0):S203 - S210.
  24. Sánchez, L., Barreira, N., García-Resúa, C., and YebraPimentel, E. (2015a). Automatic selection of video frames for hyperemia grading. Eurocast 2015, pages 165-166.
  25. Sánchez, L., Barreira, N., Pena-Verdeal, H., and YebraPimentel, E. (2015b). A novel framework for hyperemia grading based on artificial neural networks. In Advances in Computational Intelligence, pages 263- 275. Springer.
  26. Schulze, M. M., Jones, D. A., and Simpson, T. L. (2007). The development of validated bulbar redness grading scales. Optometry & Vision Science, 84(10):976-983.
  27. Smola, A. J. and Schölkopf, B. (2004). A tutorial on support vector regression. Statistics and Computing, 14(3):199-222.
  28. Vázquez, S. G., Barreira, N., Penedo, M. G., Pena-Seijo, M., and Gómez-Ulla, F. (2013). Evaluation of SIRIUS retinal vessel width measurement in REVIEW dataset. In Proceedings of the 26th IEEE International Symposium on Computer-Based Medical Systems, Porto, Portugal, June 20-22, 2013, pages 71-76.
  29. Wang, Y. and Witten, I. H. (1996). Induction of model trees for predicting continuous classes.
  30. Wolffsohn, J. S. and Purslow, C. (2003). Clinical monitoring of ocular physiology using digital image analysis. Contact Lens and Anterior Eye, 26(1):27-35.
  31. Yoneda, T., Sumi, T., Takahashi, A., Hoshikawa, Y., Kobayashi, M., and Fukushima, A. (2012). Automated hyperemia analysis software: reliability and reproducibility in healthy subjects. Japanese journal of ophthalmology, 56(1):1-7.
Download


Paper Citation


in Harvard Style

S. Brea L., Barreira N., Mosquera A., Pena-Verdeal H. and Yebra-Pimentel E. (2016). Comparing Machine Learning Techniques in a Hyperemia Grading Framework . In Proceedings of the 8th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-172-4, pages 423-429. DOI: 10.5220/0005756004230429


in Bibtex Style

@conference{icaart16,
author={L. S. Brea and N. Barreira and A. Mosquera and H. Pena-Verdeal and E. Yebra-Pimentel},
title={Comparing Machine Learning Techniques in a Hyperemia Grading Framework},
booktitle={Proceedings of the 8th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2016},
pages={423-429},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005756004230429},
isbn={978-989-758-172-4},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 8th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Comparing Machine Learning Techniques in a Hyperemia Grading Framework
SN - 978-989-758-172-4
AU - S. Brea L.
AU - Barreira N.
AU - Mosquera A.
AU - Pena-Verdeal H.
AU - Yebra-Pimentel E.
PY - 2016
SP - 423
EP - 429
DO - 10.5220/0005756004230429