Solving the Problem of Leukocyte Segmentation and Classification in Images Using Transfer Learning and an Ensemble of Convolutional Neural Networks
DOI:
https://doi.org/10.52575/2687-0932-2024-51-4-873-886Keywords:
images processing, computer vision, blood microscopic images, machine learning, segmentation, leukocytes classificationAbstract
This article presents a study aimed at developing an innovative method for automated counting and classification of leukocytes in digital microscopic blood images. The proposed approach is designed to overcome key limitations of existing methods, ensuring high accuracy, versatility, and robustness to input data variability. The novelty of the method lies in leveraging the advantages of transfer learning and combining convolutional neural networks into an ensemble, which significantly enhances the accuracy of recognizing various leukocyte types. The developed algorithm implements a three-stage image processing procedure: leukocyte segmentation using an ensemble of models, post-processing of segmented images to improve their quality, and final classification. The computational experiment data demonstrate a significant effectiveness of the proposed approach and confirm its versatility. The results of this work can serve as a foundation for developing new automated diagnostic systems for clinical practice capable of increasing the speed and accuracy of blood analysis, which represents an important step towards improving the quality of medical care.
Downloads
References
Список литературы
Батищев Д.С., Михелев В.М., Утянский А.А. 2020. Метод сегментации перекрывающихся форменных элементов крови на микроскопических медицинских изображениях. Экономика. Информатика. 47(4): 803–815.
Волкова С.А. Боровков Н.Н. 2013. Основы клинической гематологии: учебное пособие. Н. Новгород. Издательство Нижегородской гос. медицинской академии, 400 с.
Черных Е.М., Михелев В.М., Петров Д.В. 2023. Безэталонные метрики качества изображений клеток крови. Экономика. Информатика. 50(2): 380–388.
Acevedo A., Merino González A., Alférez Baquero E.S., Molina Borrás Á., Boldú Nebot L., Rodellar Benedé J. 2020. A dataset of microscopic peripheral blood cell images for development of automatic recognition systems. Data in brief, 30(article 105474).
Almezhghwi K., Serte S. 2020. Improved classification of white blood cells with the generative adversarial network and deep convolutional neural network. Computational Intelligence and Neuroscience, 2020(1), 6490479.
Chernykh E.M., Mikhelev V.M. 2021. A computer system for the leukocytes classification in medical images. In Journal of Physics: Conference Series. 1715(1): 012007.
Chow L.S., Paramesran R. 2016. Review of medical image quality assessment. Biomedical signal processing and control. 27: 145–154.
Clunie D., Hosseinzadeh D., Wintell M., De Mena D., Lajara N., Garcia-Rojo M., Bueno G., Saligrama K., Stearrett A., Toomey D., Abels E., Apeldoorn F.V., Langevin S., Nichols S., Schmid J., Horchner U., Beckwith B., Parwani A., Pantanowitz L. 2018. Digital Imaging and Communications in Medicine Whole Slide Imaging Connectathon at Digital Pathology Association Pathology Visions 2017. Journal of pathology informatics, 9(1).
Di Ruberto C., Putzu L. 2014. Accurate blood cells segmentation through intuitionistic fuzzy set threshold. Tenth international conference on signal-image technology and internet-based systems (pp. 57–64). IEEE.
Ganaie M.A., Hu M., Malik A.K., Tanveer M., Suganthan P.N. 2022. Ensemble deep learning: A review. Engineering Applications of Artificial Intelligence, 115, 105151.
Ibrahim S., Rozan M.H.C., Sabri N. 2019. Comparative analysis of support vector machine (SVM) and convolutional neural network (CNN) for white blood cells’ classification. International Journal of Advanced Trends in Computer Science and Engineering, 8(1.3): 394–399.
Lin L., Wang W. 2018. A robust leukocyte recognition method based on multi-scale regional growth and mean-shift clustering. Journal of Algorithms & Computational Technology, 12(3), 208–216.
Ma J.J., Nakarmi U., Kin C.Y.S., Sandino C.M., Cheng J.Y., Syed A.B., Wei P., Pauly J.M., Vasanawala S. S. 2020. Diagnostic image quality assessment and classification in medical imaging: opportunities and challenges. Proceedings. IEEE International Symposium on Biomedical Imaging: 337–340.
Ronneberger O., Fischer P., Brox T. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention–MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18: 234–241. Springer International Publishing.
Rosyadi T., Arif A., Achmad B. 2016. Classification of leukocyte images using k-means clustering based on geometry features. In 2016 6th international annual engineering seminar. 245–249).
Tamang T., Baral S., Paing M.P. 2022. Classification of white blood cells: A comprehensive study using transfer learning based on convolutional neural networks. Diagnostics, 12(12), 2903.
Wang W., Su P.Y. 2012. Blood cell image segmentation on color and GVF snake for Leukocyte classification on SVM. Guangxue Jingmi Gongcheng/Optics and Precision Engineering, 20(12): 2781–2790.
Zhang C., Wu S., Lu Z., Shen Y., Wang J., Huang P., Li D. 2020. Hybrid adversarial‐discriminative network for leukocyte classification in leukemia. Medical physics, 47(8): 3732–3744.
Zheng X., Wang Y., Wang G., Liu J. 2018. Fast and robust segmentation of white blood cell images by self-supervised learning. Micron, 107: 55–71.
Zheng Z., Wang P., Liu W., Li J., Ye R., Ren D. (2020, April). Distance-IoU loss: Faster and better learning for bounding box regression. In Proceedings of the AAAI conference on artificial intelligence. 34(07): 12993–13000.
Abstract views: 7
Share
Published
How to Cite
Issue
Section
Copyright (c) 2024 Economics. Information Technologies
This work is licensed under a Creative Commons Attribution 4.0 International License.
