Classificação automática de glóbulos brancos usando descritores de forma e textura e eXtreme Gradient Boosting

• Domingos A. Dias Júnior UFMA
• Luana B. da Cruz UFMA
• João O. B. Diniz UFMA / IFMA
• Geraldo Braz Júnior UFMA
• Aristófanes C. Silva UFMA

DOI: https://doi.org/10.5753/sbcas.2021.16056

Resumo

O diagnóstico de doenças sanguíneas envolve a identificação e caracterização de amostras de sangue de pacientes pela contagem e classificação de glóbulos brancos. Métodos automatizados têm importantes aplicações para auxiliar médicos. O objetivo deste trabalho é desenvolver um método para classificação automática de glóbulos brancos utilizando técnicas de realce, Threshold Adjacency Statistics (TAS) para extração de características e eXtreme Gradient Boosting (XGBoost) para classificação. Os resultados são promissores comparados a outras técnicas e trabalhos da literatura, alcançado 93,27% de acurácia e 90% de F-Measure. Com isto, acredita-se que o método possa auxiliar especialista nesta tarefa importante.

Referências

Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., et al. (2015). Tensorow: Large-scale machine learning on heterogeneous systems. Software available from tensorow.org.

ACS (2018). About chronic lymphocytic leukemia. https://cancer.org/cancer/chronic-lymphocytic-leukemia/about/normal-tissue.html. Acesso em: 2020-06-07.

BCCD, D. (2018). Bccd dataset. https://www.kaggle.com/surajiiitm/bccd-dataset.

Carvalho, E. D., Antônio Filho, O., Silva, R. R., Araújo, F. H., Diniz, J. O., Silva, A. C., Paiva, A. C., and Gattass, M. (2020). Breast cancer diagnosis from histopathological images using textural features and cbir. Articial Intelligence in Medicine, 105:101845.

Chen, T., He, T., Benesty, M., Khotilovich, V., and Tang, Y. (2015). Xgboost: extreme gradient boosting. R package version 0.4-2, pages 1–4.

Chollet, F. et al. (2015). Keras. https://keras.io.

da Cruz, L. B., Araújo, J. D. L., Ferreira, J. L., Diniz, J. O. B., Silva, A. C., de Almeida, J. D. S., de Paiva, A. C., and Gattass, M. (2020). Kidney segmentation from computed tomography images using deep neural network. Computers in Biology and Medicine, page 103906.

Diniz, J. O. B., Ferreira, J. L., Diniz, P. H. B., Silva, A. C., and de Paiva, A. C. (2020). Esophagus segmentation from planning ct images using an atlas-based deep learning approach. Computer Methods and Programs in Biomedicine, 197:105685.

Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. The Annals of Statistics, 29(5):1189–1232.

Gonzalez, R. C. and Woods, R. E. (2010). Digital Image Processing. Pearson Prentice Hall.

Guyon, I., Weston, J., Barnhill, S., and Vapnik, V. (2002). Gene selection for cancer classication using support vector machines. Machine learning, 46(1-3):389–422.

H Mohamed, E., H El-Behaidy, W., Khoriba, G., and Li, J. (2020). Improved white blood cells classification based on pre-trained deep learning models. Journal of Communications Software and Systems, 16(1):37–45.

Hamilton, N. A., Pantelic, R. S., Hanson, K., and Teasdale, R. D. (2007). Fast automated cell phenotype image classication. BMC bioinformatics, 8(1):1–8.

Ko, B., Gim, J., and Nam, J. (2011). Cell image classication based on ensemble features and random forest. Electronics Letters, 47(11):638–639.

Macawile, M. J., Qui˜nones, V. V., Ballado, A., Cruz, J. D., and Caya, M. V. (2018). White blood cell classication and counting using convolutional neural network. In 2018 3rd International conference on control and robotics engineering (ICCRE), pages 259– 263. IEEE.

Meyer-Baese, A. and Schmid, V. (2014). Chapter 2 - feature selection and extraction. In Meyer-Baese, A. and Schmid, V., editors, Pattern Recognition and Signal Analysis in Medical Imaging (Second Edition), pages 21 – 69. Academic Press, Oxford, second edition edition.

Mohamed, E., El-Behaidy, W., Khoriba, G., and Li, J. (2020). Improved white blood cells classication based on pre-trained deep learning models. Journal of Communications Software and Systems, 16.

NCI (2020). White blood cell. https://cancer.gov/publications/dictionaries/cancer-terms/def/white-blood-cell. Acesso em: 2020-06-07.

Rezatoghi, S. H. and Soltanian-Zadeh, H. (2011). Automatic recognition of ve types of white blood cells in peripheral blood. Computerized Medical Imaging and Graphics, 35(4):333–343.

Sezgin, M. and Sankur, B. (2004). Survey over image thresholding techniques and quantitative performance evaluation. Journal of Electronic imaging, 13(1):146–165.

Tai, W.-L., Hu, R.-M., Hsiao, H. C., Chen, R.-M., and Tsai, J. J. (2011). Blood cell image classication based on hierarchical svm. In 2011 IEEE International Symposium on Multimedia, pages 129–136. IEEE.

Vatathanavaro, S., Tungjitnob, S., and Pasupa, K. (2018). White blood cell classication: A comparison between vgg-16 and resnet-50 models. In Thailand-CIS, page 3.

Vogado, L. H., Veras, R. M., Araujo, F. H., Silva, R. R., and Aires, K. R. (2019). Rede neural convolucional para o diagnóstico de leucemia. In Anais do XIX Simpósio Brasileiro de Computação Aplicada à Saúde, pages 46–57. SBC.

Wu, Y.-T., Wei, J., Hadjiiski, L. M., Sahiner, B., Zhou, C., Ge, J., Shi, J., Zhang, Y., and Chan, H.-P. (2007). Bilateral analysis based false positive reduction for computer-aided mass detection. Medical physics, 34(8):3334–3344.

Zhao, J., Zhang, M., Zhou, Z., Chu, J., and Cao, F. (2017). Automatic detection and classication of leukocytes using convolutional neural networks. Medical & biological engineering & computing, 55(8):1287–1301.