Classificações Explicáveis para Imagens de Células Infectadas por Malária

  • Iam Sousa PUC-Rio
  • Marley Vellasco PUC-Rio
  • Eduardo Silva PUC-Rio

Resumo


Este trabalho apresenta o desenvolvimento de um classificador explicável de imagens, treinado para a tarefa de determinar se uma célula foi infectada por malária. O classificador consiste em uma rede neural residual, com acurácia de classificação de 96%, treinada com o dataset de Malária do National Health Institute. Técnicas de Inteligência Artificial Explicável foram aplicadas para tornar as classificações mais interpretáveis. Estas explicações são geradas usando duas metodologias: Local Interpretable Model Agnostic Explanations (LIME) e SquareGrid. As explicações fornecem perspectivas novas e importantes para os padrões de decisão de modelos como este, de alto desempenho para tarefas médicas.

Palavras-chave: Inteligência Artificial Explicável, Classificação, Malária, Redes Neurais Convolucionais

Referências

Adadi, A. and Berrada, M. (2018). Peeking inside the black-box: A survey on explainable artificial intelligence (xai). IEEE Access, 6:52138–52160.

Felzenszwalb, P. F. and Huttenlocher, D. P. (2004). Efficient graph-based image segmentation. International journal of computer vision, 59:167–181.

He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition.

Kermany, D. S., Goldbaum, M., Cai, W., Valentim, C. C. S., Liang, H., Baxter, S. L., McKeown, A., Yang, G., Wu, X., Yan, F., et al. (2018). Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell, 172:1122–1131.

Keskar, N. S. and Socher, R. (2017). Improving generalization performance by switching from adam to sgd.

Miotto, R., Wang, F., Wang, S., Jiang, X., and Dudley, J. T. (2017). Deep learning for healthcare: review, opportunities and challenges. Briefings in bioinformatics, 19:1236– 1246.

OPAS (2019). Folha informativa - malária.

Palatnik de Sousa, I., Maria Bernardes Rebuzzi Vellasco, M., and Costa da Silva, E. (2019). Local interpretable model-agnostic explanations for classification of lymph node metastases. Sensors, 19(13):2969.

Rajaraman, S., Antani, S. K., Poostchi, M., Silamut, K., Hossain, M. A., Maude, R. J., Jaeger, S., and Thoma, G. R. (2018). Pre-trained convolutional neural networks as feature extractors toward improved malaria parasite detection in thin blood smear images.

Ribeiro, M. T., Singh, S., and Guestrin, C. (2016). Why should i trust you?: Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pages 1135–1144. Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining.

Sayyed, A. Q. M. S., Saha, D., Hossain, A. R., and Shahnaz, C. (2019). Effectiveness of convolutional and capsule network in malaria parasite detection. IEEE International Conference on Signal Processing, Information, Communication & Systems(SPICSCON).

Veeling, B. S., Linmans, J., Winkens, J., Cohen, T., and Welling, M. (2018). Rotation equivariant cnns for digital pathology. In International Conference on Medical image computing and computer-assisted intervention, pages 210–218. International Conference on Medical image computing and computer-assisted intervention.

WHO (2019). World malaria report 2019. Technical report.

Adadi, A. and Berrada, M. (2018). Peeking inside the black-box: A survey on explainable artificial intelligence (xai). IEEE Access, 6:52138–52160.

Felzenszwalb, P. F. and Huttenlocher, D. P. (2004). Efficient graph-based image segmentation. International journal of computer vision, 59:167–181.

He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition.

Kermany, D. S., Goldbaum, M., Cai, W., Valentim, C. C. S., Liang, H., Baxter, S. L., McKeown, A., Yang, G., Wu, X., Yan, F., et al. (2018). Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell, 172:1122–1131.

Keskar, N. S. and Socher, R. (2017). Improving generalization performance by switching from adam to sgd.

Miotto, R., Wang, F., Wang, S., Jiang, X., and Dudley, J. T. (2017). Deep learning for healthcare: review, opportunities and challenges. Briefings in bioinformatics, 19:1236– 1246.

OPAS (2019). Folha informativa - malária.

Palatnik de Sousa, I., Maria Bernardes Rebuzzi Vellasco, M., and Costa da Silva, E. (2019). Local interpretable model-agnostic explanations for classification of lymph node metastases. Sensors, 19(13):2969.

Rajaraman, S., Antani, S. K., Poostchi, M., Silamut, K., Hossain, M. A., Maude, R. J., Jaeger, S., and Thoma, G. R. (2018). Pre-trained convolutional neural networks as feature extractors toward improved malaria parasite detection in thin blood smear images.

Ribeiro, M. T., Singh, S., and Guestrin, C. (2016). Why should i trust you?: Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pages 1135–1144. Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining.

Sayyed, A. Q. M. S., Saha, D., Hossain, A. R., and Shahnaz, C. (2019). Effectiveness of convolutional and capsule network in malaria parasite detection. IEEE International Conference on Signal Processing, Information, Communication & Systems(SPICSCON).

Veeling, B. S., Linmans, J., Winkens, J., Cohen, T., and Welling, M. (2018). Rotation equivariant cnns for digital pathology. In International Conference on Medical image computing and computer-assisted intervention, pages 210–218. International Conference on Medical image computing and computer-assisted intervention.

WHO (2019). World malaria report 2019. Technical report.
Publicado
20/10/2020
Como Citar

Selecione um Formato
SOUSA, Iam; VELLASCO, Marley; SILVA, Eduardo. Classificações Explicáveis para Imagens de Células Infectadas por Malária. In: ENCONTRO NACIONAL DE INTELIGÊNCIA ARTIFICIAL E COMPUTACIONAL (ENIAC), 17. , 2020, Evento Online. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2020 . p. 47-57. DOI: https://doi.org/10.5753/eniac.2020.12116.