Human vs Machine Towards Neonatal Pain Assessment: A Comparison of the Facial Features Extracted by Adults and Convolutional Neural Networks
Resumo
Recém-nascidos (RNs) em estado crítico ou prematuros passam diariamente por inúmeros procedimentos dolorosos, necessitando avaliação contínua da dor. No entanto, resultados recentes evidenciaram a subjetividade dos métodos aplicados por profissionais de saúde. Neste contexto, este trabalho aplica modelos computacionais para compreender de maneira específica a dor expressa por RNs, comparando as características faciais relevantes para a máquina com as regiões observadas por Médicos e Pais de RN durante avaliação da dor. Os resultados obtidos mostraram que as regiões relevantes para os modelos computacionais são clinicamente importantes e, em partes, concordam com a percepção facial humana.
Referências
Barros, M. C. d. M., Thomaz, C. E., da Silva, G. V. T., do Carmo Azevedo Soares, J., Carlini, L. P., Heiderich, T. M., Orsi, R. N., Balda, R. d. C. X., Silva, P. A. S. O., Sanudo, A., et al. (2021). Identification of pain in neonates: the adults’ visual perception of neonatal facial features. Journal of Perinatology, 41(9):2304–2308.
Brahnam, S., Chuang, C.-F., Shih, F. Y., and Slack, M. R. (2005). Svm classification of neonatal facial images of pain. International Workshop on Fuzzy Logic and Applications, pages 121–128.
Carlini, L. P., Ferreira, L. A., Coutrin, G. A., Varoto, V. V., Heiderich, T. M., Balda, R. C., Barros, M. C., Guinsburg, R., and Thomaz, C. E. (2021). A convolutional neural network-based mobile application to bedside neonatal pain assessment. In 2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), pages 394–401. IEEE Computer Society.
Carlini, L. P., Soares, J. C. A., Silva, G. V. T., Heideirich, T. M., Balda, R. C. X., Barros, M. C. M., Guinsburg, R., and Thomaz, C. E. (2020). A visual perception framework to analyse neonatal pain in face images. In Campilho, A., Karray, F., and Wang, Z., editors, Image Analysis and Recognition, volume 12131 of Lecture Notes in Computer Science, pages 233–243, Cham. Springer International Publishing.
Coutrin, G. A., Carlini, L. P., Ferreira, L. A., Heiderich, T. M., Balda, R. C., Barros, M. C., Guinsburg, R., and Thomaz, C. E. (2022). Convolutional neural networks for newborn pain assessment using face images: A quantitative and qualitative comparison. In Proceedings of the 3rd International Conference on Medical Imaging and Computer-Aided Diagnosis, MICAD 2022. Springer LNEE.
Cruz, M., Fernandes, A., and Oliveira, C. (2016). Epidemiology of painful procedures performed in neonates: a systematic review of observational studies. European Journal of Pain, 20(4):489–498.
Darmstadt, G. L., Shiffman, J., and Lawn, J. E. (2015). Advancing the newborn and stillbirth global agenda: priorities for the next decade. Archives of disease in childhood, 100(Suppl 1):S13–S18.
Gkikas, S. and Tsiknakis, M. (2023). Automatic assessment of pain based on deep learning methods: A systematic review. Computer Methods and Programs in Biomedicine, 231:107365.
Grunau, R. E. (2020). Personal perspectives: Infant pain—a multidisciplinary journey. Paediatric and Neonatal Pain, 2(2):50–57.
Guinsburg, R. (1999). Avaliação e tratamento da dor no recém-nascido. J Pediatr (Rio J), 75(3):149–60.
Heiderich, T. M., Leslie, A. T. F. S., and Guinsburg, R. (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.
Parkhi, O. M., Vedaldi, A., and Zisserman, A. (2015). Deep face recognition. In British Machine Vision Conference.
Schiller, D., Huber, T., Dietz, M., and André, E. (2020). Relevance-based data masking: a model-agnostic transfer learning approach for facial expression recognition. Frontiers in Computer Science, 2:6.
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017). Grad-cam: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE international conference on computer vision, pages 618–626.
Sundararajan, M., Taly, A., and Yan, Q. (2017). Axiomatic attribution for deep networks. arXiv preprint arXiv:1703.01365.
Zamzmi, G., Paul, R., Goldgof, D., Kasturi, R., and Sun, Y. (2019). Pain assessment from facial expression: Neonatal convolutional neural network (n-cnn). In 2019 International Joint Conference on Neural Networks (IJCNN), pages 1–7. IEEE.
Brahnam, S., Chuang, C.-F., Shih, F. Y., and Slack, M. R. (2005). Svm classification of neonatal facial images of pain. International Workshop on Fuzzy Logic and Applications, pages 121–128.
Carlini, L. P., Ferreira, L. A., Coutrin, G. A., Varoto, V. V., Heiderich, T. M., Balda, R. C., Barros, M. C., Guinsburg, R., and Thomaz, C. E. (2021). A convolutional neural network-based mobile application to bedside neonatal pain assessment. In 2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), pages 394–401. IEEE Computer Society.
Carlini, L. P., Soares, J. C. A., Silva, G. V. T., Heideirich, T. M., Balda, R. C. X., Barros, M. C. M., Guinsburg, R., and Thomaz, C. E. (2020). A visual perception framework to analyse neonatal pain in face images. In Campilho, A., Karray, F., and Wang, Z., editors, Image Analysis and Recognition, volume 12131 of Lecture Notes in Computer Science, pages 233–243, Cham. Springer International Publishing.
Coutrin, G. A., Carlini, L. P., Ferreira, L. A., Heiderich, T. M., Balda, R. C., Barros, M. C., Guinsburg, R., and Thomaz, C. E. (2022). Convolutional neural networks for newborn pain assessment using face images: A quantitative and qualitative comparison. In Proceedings of the 3rd International Conference on Medical Imaging and Computer-Aided Diagnosis, MICAD 2022. Springer LNEE.
Cruz, M., Fernandes, A., and Oliveira, C. (2016). Epidemiology of painful procedures performed in neonates: a systematic review of observational studies. European Journal of Pain, 20(4):489–498.
Darmstadt, G. L., Shiffman, J., and Lawn, J. E. (2015). Advancing the newborn and stillbirth global agenda: priorities for the next decade. Archives of disease in childhood, 100(Suppl 1):S13–S18.
Gkikas, S. and Tsiknakis, M. (2023). Automatic assessment of pain based on deep learning methods: A systematic review. Computer Methods and Programs in Biomedicine, 231:107365.
Grunau, R. E. (2020). Personal perspectives: Infant pain—a multidisciplinary journey. Paediatric and Neonatal Pain, 2(2):50–57.
Guinsburg, R. (1999). Avaliação e tratamento da dor no recém-nascido. J Pediatr (Rio J), 75(3):149–60.
Heiderich, T. M., Leslie, A. T. F. S., and Guinsburg, R. (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.
Parkhi, O. M., Vedaldi, A., and Zisserman, A. (2015). Deep face recognition. In British Machine Vision Conference.
Schiller, D., Huber, T., Dietz, M., and André, E. (2020). Relevance-based data masking: a model-agnostic transfer learning approach for facial expression recognition. Frontiers in Computer Science, 2:6.
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017). Grad-cam: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE international conference on computer vision, pages 618–626.
Sundararajan, M., Taly, A., and Yan, Q. (2017). Axiomatic attribution for deep networks. arXiv preprint arXiv:1703.01365.
Zamzmi, G., Paul, R., Goldgof, D., Kasturi, R., and Sun, Y. (2019). Pain assessment from facial expression: Neonatal convolutional neural network (n-cnn). In 2019 International Joint Conference on Neural Networks (IJCNN), pages 1–7. IEEE.
Publicado
27/06/2023
Como Citar
CARLINI, Lucas Pereira; THOMAZ, Carlos Eduardo.
Human vs Machine Towards Neonatal Pain Assessment: A Comparison of the Facial Features Extracted by Adults and Convolutional Neural Networks. In: PRÊMIO ARTUR ZIVIANI - CONCURSO DE TESES E DISSERTAÇÕES (MESTRADO) - SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO APLICADA À SAÚDE (SBCAS), 23. , 2023, São Paulo/SP.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2023
.
p. 78-83.
ISSN 2763-8987.
DOI: https://doi.org/10.5753/sbcas_estendido.2023.229341.
