Machine Learning Algorithms for Peripheral Blood Cell Classification - A Hemovision Project Experience

Authors

  • Mariana Dourado X. S. Santos Universidade Federal de Goiás https://orcid.org/0009-0005-3732-5989
  • William Laus Bertemes Universidade Federal de Goias
  • Iaan Mesquita de Souza Universidade Federal de Goiás
  • Mateus Henrique B. Andrades Universidade Federal de Goiás
  • Vinicius Sebba Patto Universidade Federal de Goiás https://orcid.org/0000-0003-2134-0234

DOI:

https://doi.org/10.22456/2175-2745.130669

Keywords:

Support Vector Machine, Convolutional Neural Networks, White Blood Cells, Machine Learning

Abstract

This research explores the use of machine learning algorithms to classify nucleated peripheral blood cells. The ResNet18 convolutional neural network was used to pre-process the images and replace the dense layers; and for the output, the Support Vector Machine (SVM) classifier was chosen. Images from different datasets were used for training and testing the model. Thus, the developed model achieved an accuracy and F1-Score of 99.96%. In face of the obtained results, it was found that machine learning algorithms can be satisfactorily integrated into educational and diagnostic support processes.

Downloads

Download data is not yet available.

References

FAILACE, R.; FERNANDES, F. Hemograma: manual de interpretac ̧ ̃ao. 6. ed. Porto Alegre: Artmed, 2015.

BAIN, B. J. Diagnosis from the blood smear. New England Journal of Medicine, Oxford, v. 353, p. 498–507, aug. 2005.

CHABOT-RICHARDS, D. S.; FOUCAR, K. Does morphology matter in 2017? an approach to morphologic clues in non-neoplastic blood and bone marrow disorders. International Journal of Laboratory Hematology, Oxford, v. 39, n. S1, p. 23–30, may 2017.

JUN, G. et al. Convolutional neural networks for computer-aided detection or diagnosis in medical image analysis: an overview. Mathematical Biosciences and Engineering, Springfield, v. 16, n. 6, p. 6536–6561, jul. 2019.

CHEN, S.; BILLINGS, S. A.; GRANT, P. M. Non-linear system identification using neural networks. International Journal of Control, Amsterdam, v. 51, n. 6, p. 1191–1214, mar. 1990.

HE, J. et al. The practical implementation of artificial intelligence technologies in medicine. Nature Medicine, New York, v. 25, p. 30–36, jan 2019.

JORDAN, M.; MITCHELL, T. Machine learning: trends, perspectives, and prospects. Science, New York, v. 349, n. 6245, p. 255–260, jul. 2015.

LIANG, G. et al. Combining convolutional neural network with recursive neural network for blood cell image classification. IEEE, New York, v. 6, p. 36188–36197, jul. 2018.

BO, B. et al. Optogenetic excitation of ipsilesional sensorimotor neurons is protective in acute ischemic stroke: a laser speckle imaging study. IEEE Trans.Biomed. Eng., New York, v. 66, n. 5, p. 1372–1379, may 2018.

LIU, Q. et al. Monitoring acute stroke in mouse model using laser speckle imaging-guided visible-light optical coherence tomography. IEEE Trans. Biomed. Eng., New York, v. 65, n. 10, p. 2136–2142, may 2017.

IRVIN, J. et al. Chexpert: a large chest radiograph dataset with uncertainty labels and expert comparison. Arxiv preprint arXiv:1901.07031, [S. l.], p. 1–9, jan 2019.

ISENSEE, F. et al. No new-net. In: 4th International MICCAI Brain lesion Workshop. Cham, Switzerland: Springer, 2018. p. 234–244.

ÇIÇEK, Ö. et al. 3d u-net: Learning dense volumetric segmentation from sparse annotation. Arxiv preprint arXiv: 1606.06650, [S. l.], p. 1–8, jun. 2016.

DUAN, Y. et al. Leukocyte classification based on spatial and spectral features of microscopic hypers-pectral images. Optics LaserTechnology 112, Amsterdam, v. 112, p. 530–538, apr. 2019.

ACEVEDO, A. et al. Recognition of peripheral blood cell images using convolutional neural networks. Computer Methods and Programs in Biomedicine, Amsterdam, v. 180, p. 1–16, oct. 2019.

WIBAWA; S., M. A comparison study between deep learning and conventional machine learning on white blood cells classification. In: International Conference on Orange Technologies (ICOT). New York: IEEE, 2018. p. 1–6.

WEBER, E. U.; COSKUNOGLU, O. Descriptive and prescriptive models of decision- making: implications for the development of decision aids. IEEE transactions on Systems, Man, and Cybernetics, New York, v. 20, n. 2, p. 310–317, mar. 1990.

PUTTAMADEGOWDA, J.; PRASANNAKUMAR, S. White blood cell segmentation using fuzzy c means and snake. In: Computation System and Information Technology for Sustainable Solutions (CSITSS). New York: IEEE, 2016. p. 47–52.

GAUTAM, A.; BHADAURIA, H. White blood nucleus extraction using k-mean clustering and mathematical morphing. In: Proceedings of the 5th International Conference on Confluence 2014: The Next Generation Information Technology Summit. New York: IEEE, 2014. p. 549–554.

ALREZA, Z. K. K.; KARIMIAN, A. Design a new algorithm to count white blood cells for classification leukemic blood image using machine vision system. In: 6th International Conference on Computer and Knowledge Engineering (ICCKE). New York: IEEE, 2016. p. 251–256.

PEREZ, L.; WANG, J. The effectiveness of data augmentation in image classification using deep learning. Arxiv preprint arXiv:1712.04621, [S. l.], p. 1–8, dec. 2017.

YAO, X. Classification of white blood cells using weighted optimized deformable convolutional neural networks. Artificial Cells, Nanomedicine, and Biotechnology, London, v. 49, n. 1, p. 147–155, feb. 2021.

MA, L.; SHUAI, R.; RAN, X. E. A. Combining dc-gan with resnet for blood cell image classification. Medical & Biological Engineering & Computing, New York, v. 58, p. 1251–1264, mar. 2020.

ALMEZHGHWI, K.; SERTE, S. Improved classification of white blood cells with the generative adversarial network and deep convolutional neural network. Computational Intelligence and Neuroscience, New York, v. 2020, p. 1–12, jul. 2020.

KRIZHEVSKY, A. The cifar dataset. Universidade de Toronto, 2019. Disponível em: ⟨https://www.cs.toronto.edu/∼kriz/cifar.html⟩. Acesso em:22 junho 2023.

KHAN, A. et al. White blood cell type identification using multi-layer convolutional features with an extreme-learning machine. Biomedical Signal Processing and Control, Oxford, v. 69, p. 102932, aug. 2021.

RAWAT, W.; WANG, Z. Deep convolutional neural networks for image classification: A comprehensive review. Neural computation, Cambridge, v. 29, n. 9, p. 2352–2449, sep. 2017.

KONONENKO, I. Estimating attributes: Analysis and extensions of relief. In: Machine Learning: ECML-94. Cham, Switzerland: Springer, 1994. p. 171–182.

KATAR, O.; KILINCER, I. F. Automatic classification of white blood cells using pre-trained deep models. Sakarya University Journal of Computer and Information Sciences, Turkey, v. 5, n. 3, p. 462–476, dec. 2022.

DENG, J. et al. Imagenet: A large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2009. p. 248–255.

WANG, Y.; CAO, Y. Human peripheral blood leukocyte classification method based on convolutional neural network and data augmentation. Medical Physics, Woodbury, v. 47, n. 1, p. 142–151, jan. 2019.

LONG, F. et al. Bloodcaps: A capsule network based model for the multiclassification of human peripheral blood cells. Computer Methods and Programs in Biomedicine, Amsterdam, v. 202, p. 105972, apr. 2021.

ACEVEDO, A. et al. A dataset of microscopic peripheral blood cell images for development of automatic recognition systems. Computer Methods and Programs in Biomedicine, Amsterdam, v. 30, p. 1–5, jun. 2019.

CENGIL, E.; C ̧ INAR, A.; YILDIRIM, M. A hybrid approach for efficient multi-classification of white blood cells based on transfer learning techniques and traditional machine learning methods. Concurrency and Computation: Practice and Experience, Chichester, v. 34, n. 6, p. e6756, mar. 2021.

MANOHAR, N. et al. Convolutional neural network with svm for classification of animal images. In: SRIDHAR, V.; PADMA, M.; RAO, K. R. (Ed.). Emerging Research in Electronics, Computer Science and Technology. Singapore: Springer Singapore, 2019. p. 527–537.

AGARAP, A. F. An architecture combining convolutional neural network (CNN) and support vector machine (SVM) for image classification. Arxiv preprint arXiv: 1712.03541, [S. l.], p. 1–4, dec. 2017.

MOONEY., P. Blood cell images. Kaggle, 2020. Disponível em: ⟨https://www.kaggle.com/paultimothymooney/blood-cells⟩. Acesso em: 22 junho 2023.

KOUZEHKANAN, Z. M. et al. Raabin-wbc: a large free access dataset of white blood cells from normal peripheral blood. bioRxiv, Cold Spring Harbor Laboratory, p. 1–24, 2021. (No prelo). Disponível em: ⟨https://www.biorxiv.org/content/early/2021/05/29/2021.05.02.442287⟩.

REINHARD, E. et al. Color transfer between images. IEEE Computer Graphics and Applications, New York, v. 21, n. 5, p. 34–41, jul. 2001.

Downloads

Published

2023-10-05

How to Cite

Santos, M. D. X. S., Bertemes, W. L., Mesquita de Souza, I., Andrades, M. H. B., & Patto, V. S. (2023). Machine Learning Algorithms for Peripheral Blood Cell Classification - A Hemovision Project Experience. Revista De Informática Teórica E Aplicada, 30(2), 89–100. https://doi.org/10.22456/2175-2745.130669

Issue

Section

Selected Papers ERI-GO 2022