Interpretação e reconhecimento de padrões para avaliação de dor em imagens faciais de recém-nascidos

• Pedro Orona FEI
• Davi Fabbro FEI
• Tatiany Heiderich UNIFESP
• Marina Barros UNIFESP
• Rita Balda UNIFESP
• Ruth Guinsburg UNIFESP
• Carlos Thomaz FEI

DOI: https://doi.org/10.5753/sbcas.2020.11521

Abstract

Pain analysis in newborns has become a relevant study subject over the last few decades, given the inability to objectively identify the source and intensity of the pain in newborn babies. Considering this context, this work’s main objective is to develop a computer framework capable of recognizing and interpreting patterns in facial expressions for an automated evaluation of pain levels on term babies. Being that, the framework developed here, get an accuracy (upper limit) of approximately 96% for the COPE base and 77% for the UNIFESP base.

References

Brahnam, S., Chuang, C.-F., Shih, F. Y., and Slack, M. R. (2006). Machine recognition and representation of neonatal facial displays of acute pain. Artificial intelligence in medicine, 36(3):211–222.

Fukunaga, K. (2013). Introduction to statistical pattern recognition. Elsevier.

Gibson, S. J. (2006). Eigenfit: A statistical learning approach to facial composites. PhD thesis, University of Kent.

Heiderich, T. M., Leslie, A. T. F. S., and Guinsburg (2015). Neonatal procedural pain can be assessed by computer software that has good sensitivity and specificity to detect facial movements. Acta Paediatrica, 104(2):e63–e69.

Johnson, R. A. and Wichern, D. W. (2006). Applied Multivariate Statistical Analysis. Prentice-Hall, Inc., Upper Saddle River, NJ, USA, 6 edition.

Luda, Nackley, A. G., Tchivileva, I. E., Shabalina, S. A., and Maixner, W. (2007). Genetic architecture of human pain perception. TRENDS in Genetics, 23(12):605–613.

Mansor, M. N. and Rejab, M. N. (2013). A computational model of the infant pain impressions with gaussian and nearest mean classifier. In Control System, Computing and Engineering (ICCSCE), 2013 IEEE International Conference on, pages 249–253. IEEE.

Nanni, L., Brahnam, S., and Lumini, A. (2010). A local approach based on a local binary patterns variant texture descriptor for classifying pain states. Expert Systems with Applications, 37(12):7888–7894.

Orona, P. A., Fabbro, D. A., Heiderich, T. M., Barros, M. C., Balda, R. C., Guinsburg, R., and Thomaz, C. E. (2019). Atlas of neonatal face images using triangular meshes. In Anais do XV Workshop de Visão Computacional , pages 19–24. SBC.

Taddio, A., Katz, J., Ilersich, A. L., and Koren, G. (1997). Effect of neonatal circumcision on pain response during subsequent routine vaccination. The lancet, 349(9052):599– 603.

Teruel, G. F., Heiderich, T. M., Guinsburg, R., and Thomaz, C. E. (2019). Analise e reconhecimento de dor em imagens 2d frontais de recem-nascidos a termo e saudáveis. In Anais Estendidos do XIX Simposio Brasileiro de Computacão Aplicada a Saude , pages 97–102. SBC.

Thomaz, C. E., Kitani, E. C., and Gillies, D. F. (2006). A maximum uncertainty lda-based approach for limited sample size problems—with application to face recognition. Journal of the Brazilian Computer Society, 12(2):7–18.

Zamzmi, G., Goldgof, D., Kasturi, R., and Sun, Y. (2018). Neonatal pain expression recognition using transfer learning. arXiv preprint arXiv:1807.01631.

Zhi, R., Zamzmi, G., Goldgof, D., Ashmeade, T., and Sun, Y. (2018). Automatic infants’ pain assessment by dynamic facial representation: Effects of profile view, gestational age, gender, and race. Journal of clinical medicine, 7(7):173.