Algoritmos de Aprendizado de Máquina para Classificação de Células Nucleadas do Sangue Periférico - Uma Experiência do Projeto Hemovision

  • Mariana Dourado X. S. Santos UFG
  • William Laus Bertemes UFG
  • Iaan Mesquita de Souza UFG
  • Mateus Henrique B. Andrades UFG
  • David Antonio T. M. Barros UFG
  • Vinicius Sebba Patto UFG

Resumo


Este trabalho trata do uso de algoritmos de aprendizado de máquina para classificação de células nucleadas do sangue periférico. Foi utilizada a rede neural convolucional ResNet18 para o pré-processamento das imagens e em substituição às camadas densas; e para a saída foi escolhido o classificador Support Vector Machine (SVM). Foram usadas imagens disponibilizadas por um estudo de classificação de imagem do Hospital das Clínicas de Barcelona, contendo oito classes. O modelo desenvolvido obteve uma acurácia média de 97.2%, e o F1-Score médio de 97%, sendo que algumas classes obtiveram médias próximas de 100%, enquanto outras, de 95%. Diante dos resultados encontrados, constatou-se que os algoritmos de aprendizado de máquina podem ser integrados de forma satisfatória aos processos educacionais e de apoio ao diagnóstico.

Referências

Acevedo, A, Alférez, S., Merino, A., Puigví, L., and Rodellar, J. (2019). A dataset of microscopic peripheral blood cell images for development of automatic recognition systems. page 1191–1214. Computer Methods and Programs in Biomedicine.

Acevedo, A., Merino, A., Alférez, S., Molina, A., Boldúand, L., and Rodellar, J. (2019). Recognition of peripheral blood cell images using Convolutional Neural Networks. page 1191–1214. Computer Methods and Programs in Biomedicine.

Almezhghwi, K. and Serte, S. (2020). Improved classification of white blood cells with the Generative Adversarial Network and Deep Convolutional Neural Network.

Alreza, Z. K. K. and Karimian, A. (2016). Design a new algorithm to count white blood cells for classification leukemic blood image using machine vision system, pages 251–256. In Computer and Knowledge Engineering (ICCKE).

Altaf, K., Amber, E., Alexander, C., and Hasan, D. (2021). White blood cell type identification using multi-layer convolutional features with an Extreme-Learning Machine.

Bain, B. J. (2005). Diagnosis from the blood smear. page 498–507. New England Journal of Medicine.

Bo, B., Li, Y., Li, W., Wang, Y., and Tong, S. (2018). Optogenetic excitation of ipsilesional sensorimotor neurons is protective in acute ischemic stroke: a laser speckle imaging study. page 1372–1379. IEEE Trans.Biomed. Eng. 66(5).

Chabot-Richards, D. S. and Foucar, K. (2017). Does morphology matter in 2017? an approach to morphologic clues in non-neoplastic blood and bone marrow disorders. pages 23–30. Int J Lab Hem. 39(Suppl. 1).

Chen, S., Billings, S. A., and Grant, P. M. (1990). Non-linear system identification using neural networks. page 1191–1214. International Journal of Control.

Duan, Y., Wang, J., Hu, M., Zhou, M., Li, Q., Sun, L., Qiu, S., and Wang, Y. (2019). Leukocyte classification based on spatial and spectral features of microscopic hypers-pectral images. page 530–538. Optics LaserTechnology 112.

Failace, R. and Fernandes, F. (2015). Hemograma: manual de interpretação. Artmed, 6th edition.

Gautam, A. and Bhadauria, H. (2014). White blood nucleus extraction using k-mean clustering and mathematical morphing. page 549–554. Confluence The Next Generation Information Technology Summit (Confluence).

He, J., Baxter, S., Xu, J., Zhou, X., and Zhang, K. (2019). The practical implementation of artificial intelligence technologies in medicine. Nature Medicine.

Irvin, J., Rajpurkar, P., Ko, M., Yu, Y., Ciurea-Ilcus, S., Chute, C., Marklund, H., Hagh-goo, B., Ball, R., and Shpanskaya, K. (2019). Chexpert: a large chest radiograph dataset with uncertainty labels and expert comparison. arXiv:1901.07031.

Isensee, F., Kickingereder, P., Wick, W., Bendszus, M., and Maier-Hein, K. H. (2018). No new-net. page 234–244. International MICCAI Brain lesion Workshop. Springer.

Jordan, M. and Mitchell, T. (2015). Machine learning: trends, perspectives, and prospects. page 255–260. Science 349(6245).

Jun, G., Qian, J., Bo, Z., and Daozheng, C. (2019). Convolutional neural networks for computer-aided detection or diagnosis in medical image analysis: an overview. pages 6536–6561. Mathematical Biosciences and Engineering.

Kononenko, I. (1994). Estimating attributes: Analysis and extensions of relief. In Machine Learning: ECML-94, pages 171–182.

Liang, G., Hong, H., Xie, W., and Zheng, L. (2018). Combining Convolutional Neural Network with recursive neural network for blood cell image classification. pages 36188–36197. IEEE Access.

Liu, Q., Chen, S., Soetikno, B., Liu, W., Tong, S., and Zhang, H. (2017). Monitoring acute stroke in mouse model using laser speckle imaging-guided visible-light optical coherence tomography. page 2136–2142. IEEE Trans. Biomed. Eng. 65(10).

Ma, L., Shuai, R., and Ran, X. E. A. (2020). Combining DC-GAN with resnet for blood cell image classification. page 1251–1264. Med Biol Eng Comput 58.

Perez, L. and Wang, J. (2017). The effectiveness of data augmentation in image classification using deep learning.

Puttamadegowda, J. and Prasannakumar, S. (2016). White Blood cell segmentation using Fuzzy C means and snake. page 47–52. Computation System and Information Technology for Sustainable Solutions (CSITSS).

Rawat, W. and Wang, Z. (2017). Deep Convolutional Neural Networks for image classification: A comprehensive review. page 2352–2449. Neural computation, v. 29, n. 9.

Universidade de Toronto (2019). The cifar dataset. https://www.cs.toronto.edu/~kriz/cifar.html

Weber, E. U. and Coskunoglu, O. (1990). Descriptive and prescriptive models of decision making: implications for the development of decision aids. pages 310–317. IEEE transactions on Systems, Man, and Cybernetics.

Wibawa and S., M. (2018). A comparison study between deep learning and conventional machine learning on white blood cells classification. International Conference on Orange Technologies.

Yao, X. (2021). Classification of white blood cells using weighted optimized deformable convolutional neural networks.

Özgün, Ç., Abdulkadir, A., Lienkamp, S., Brox, T., and Ronneberger, O. (2016). 3D U-net: learning dense volumetric segmentation from sparse annotation. page 424–4329. International conference on medical image computing and computer-assisted intervention. Springer.
Publicado
25/10/2022
SANTOS, Mariana Dourado X. S.; BERTEMES, William Laus; DE SOUZA, Iaan Mesquita; ANDRADES, Mateus Henrique B.; BARROS, David Antonio T. M.; PATTO, Vinicius Sebba. Algoritmos de Aprendizado de Máquina para Classificação de Células Nucleadas do Sangue Periférico - Uma Experiência do Projeto Hemovision. In: ESCOLA REGIONAL DE INFORMÁTICA DE GOIÁS (ERI-GO), 10. , 2022, Goiás. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2022 . p. 130-140. DOI: https://doi.org/10.5753/erigo.2022.227698.