CNN-Based Approach for Overlapping Erythrocyte Counting and Cell Type Classification in Peripheral Blood Images

Year 2022, Volume: 4 Issue: 2, 82 - 87, 30.07.2022

Muhammed Ali Pala Murat Erhan Çimen Mustafa Zahid Yıldız Gökçen Çetinel Emir Avcıoğlu Yusuf Alaca

https://doi.org/10.51537/chaos.1114878

Cited By: 3

Abstract

Classification and counting of cells in the blood is crucial for diagnosing and treating diseases in the clinic. A peripheral blood smear method is a fast, reliable, robust diagnostic tool for examining blood samples. However, cell overlap during the peripheral smear process may cause incorrectly predicted results in counting blood cells and classifying cell types. The overlapping problem can occur in automated systems and manual inspections by experts. Convolutional neural networks (CNN) provide reliable results for the segmentation and classification of many problems in the medical field. However, creating ground truth labels in the data during the segmentation process is time-consuming and error-prone. This study proposes a new CNN-based strategy to eliminate the overlap-induced counting problem in peripheral smear blood samples and accurately determine the blood cell type. In the proposed method, images of the peripheral blood were divided into sub-images, block by block, using adaptive image processing techniques to identify the overlapping cells and cell types. CNN was used to classify cell types and overlapping cell numbers in sub-images. The proposed method successfully counts overlapping erythrocytes and determines the cell type with an accuracy rate of 99.73\%. The results of the proposed method have shown that it can be used efficiently in various fields.

Keywords

Blood cells, deep learning, microscopy, machine learning, classification

Supporting Institution

Sakarya University of Applied Science Scientific Research Projects Coordination Unit

Project Number

2020-01-01-011

Thanks

This work was supported by Sakarya University of Applied Science Scientific Research Projects Coordination Unit (SUBU BAPK, Project Number: 2020-01-01-011). The author, Muhammed Ali PALA, is grateful to The Scientific and Technological Research Council of Turkey for granting a scholarship (TUBITAK, 2211C) for him Ph.D. studies.

References

• Ahn, D., J. Lee, S. Moon, and T. Park, 2018 Human-level blood cell counting on lens-free shadow images exploiting deep neural networks. Analyst 143: 5380–5387.
• Alimadadi, A., S. Aryal, I. Manandhar, P. B. Munroe, B. Joe, et al., 2020 Artificial intelligence and machine learning to fight covid- 19.
• Aliyu, H. A., 2017 Detection of accurate segmentation in blood cells count–a review. International Journal of Science & Engineering Development Research 2: 28–32.
• Bain, B. J., 2005 Diagnosis from the blood smear. New England Journal of Medicine 353: 498–507.
• Barbastathis, G., A. Ozcan, and G. Situ, 2019 On the use of deep learning for computational imaging. Optica 6: 921–943.
• Bayat, F. M., M. Prezioso, B. Chakrabarti, H. Nili, I. Kataeva, et al., 2018 Implementation of multilayer perceptron network with highly uniform passive memristive crossbar circuits. Nature communications 9: 1–7.
• Beydoun, M., H. Beydoun, G. Dore, J. Canas, M. Fanelli- Kuczmarski, et al., 2016 White blood cell inflammatory markers are associated with depressive symptoms in a longitudinal study of urban adults. Translational psychiatry 6: e895–e895.
• Chiroma, H., A. Y. Gital, N. Rana, S. M. Abdulhamid, A. N. Muhammad, et al., 2019 Nature inspired meta-heuristic algorithms for deep learning: recent progress and novel perspective. In Science and Information Conference, pp. 59–70, Springer.
• Choi, J. W., Y. Ku, B. W. Yoo, J.-A. Kim, D. S. Lee, et al., 2017 White blood cell differential count of maturation stages in bone marrow smear using dual-stage convolutional neural networks. PloS one 12: e0189259.
• Çimen, M. E., Z. GAR˙IP, M. A. PALA, A. F. BOZ, and A. AKGÜL, 2019 Modelling of a chaotic system motion in video with artificial neural networks. Chaos Theory and Applications 1: 38–50.
• Dodge, S. and L. Karam, 2016 Understanding how image quality affects deep neural networks. In 2016 eighth international conference on quality of multimedia experience (QoMEX), pp. 1–6, IEEE.
• Gonzalez, R. C., S. L. Eddins, and R. E.Woods, 2004 Digital image publishing using MATLAB. Prentice Hall.
• Gould, S., T. Gao, and D. Koller, 2009 Region-based segmentation and object detection. Advances in neural information processing systems 22.
• Huang, X., Q. Zhang, G. Wang, X. Guo, and Z. Li, 2019 Medical image super-resolution based on the generative adversarial network. In Chinese Intelligent Systems Conference, pp. 243–253, Springer.
• Jang, H.-J. and K.-O. Cho, 2019 Applications of deep learning for the analysis of medical data. Archives of pharmacal research 42: 492–504.
• Kibunja, K. P., 2021 A Duplicate number plate detection system using fixed location cameras. Ph.D. thesis, Strathmore University.
• Li, X.-W., Y.-X. Kang, Y.-L. Zhu, G. Zheng, and J.-D. Wang, 2017 An improved medical image segmentation algorithm based on clustering techniques. In 2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI), pp. 1–5, IEEE.
• Liu, T., K. De Haan, Y. Rivenson, Z. Wei, X. Zeng, et al., 2019 Deep learning-based super-resolution in coherent imaging systems. Scientific reports 9: 1–13.
• McLeod, E. and A. Ozcan, 2016 Unconventional methods of imaging: computational microscopy and compact implementations. Reports on Progress in Physics 79: 076001.
• Mohammed, E. A., M. M. Mohamed, B. H. Far, and C. Naugler, 2014 Peripheral blood smear image analysis: A comprehensive review. Journal of pathology informatics 5: 9.
• Nixon, M. and A. Aguado, 2019 Feature extraction and image processing for computer vision. Academic press.
• Otsu, N., 1979 A threshold selection method from gray-level histograms. IEEE transactions on systems, man, and cybernetics 9: 62–66.
• Pala, M. A., M. E. Çimen, A. Akgül, M. Z. Yıldız, and A. F. Boz, 2022 Fractal dimension-based viability analysis of cancer cell lines in lens-free holographic microscopy via machine learning. The European Physical Journal Special Topics 231: 1023–1034.
• Rere, L., M. I. Fanany, and A. M. Arymurthy, 2016 Metaheuristic algorithms for convolution neural network. Computational intelligence and neuroscience 2016.
• Rezatofighi, S. H. and H. Soltanian-Zadeh, 2011 Automatic recognition of five types of white blood cells in peripheral blood. Computerized Medical Imaging and Graphics 35: 333–343.
• Strumberger, I., E. Tuba, N. Bacanin, R. Jovanovic, and M. Tuba, 2019 Convolutional neural network architecture design by the tree growth algorithm framework. In 2019 International Joint Conference on Neural Networks (IJCNN), pp. 1–8, IEEE.
• Sun, Y., B. Xue, M. Zhang, and G. G. Yen, 2019 Completely automated cnn architecture design based on blocks. IEEE transactions on neural networks and learning systems 31: 1242–1254.
• Wang, H., K. Sun, and S. He, 2015 Characteristic analysis and dsp realization of fractional-order simplified lorenz system based on adomian decomposition method. International Journal of Bifurcation and Chaos 25: 1550085.
• Xue, Y., N. Ray, J. Hugh, and G. Bigras, 2016 Cell counting by regression using convolutional neural network. In European Conference on Computer Vision, pp. 274–290, Springer.
• Ye, J., R. Janardan, and Q. Li, 2004 Two-dimensional linear discriminant analysis. Advances in neural information processing systems 17.
• Zhang, Y., T.-C. Poon, P. W. Tsang, R. Wang, and L. Wang, 2019 Review on feature extraction for 3-d incoherent image processing using optical scanning holography. IEEE Transactions on Industrial Informatics 15: 6146–6154.