Machine learning system for automated blood smear analysis

• Autorzy: Grochowski Michał , Wąsowicz Michał , Mikołajczyk Agnieszka , Ficek Mateusz , Kulka Marek , Wróbel Maciej S. , Jędrzejewska-Szczerska Małgorzata

Identyfikatory

DOI

10.24425/mms.2019.126323

• Języki publikacji: EN

Abstrakty

EN

In this paper the authors propose a decision support system for automatic blood smear analysis based onmicroscopic images. The images are pre-processed in order to remove irrelevant elements and to enhancethe most important ones – the healthy blood cells (erythrocytes) and the pathologic ones (echinocytes). The separated blood cells are analysed in terms of their most important features by the eigenfaces method. The features are the basis for designing the neural network classifier, learned to distinguish between erythrocytes and echinocytes. As the result, the proposed system is able to analyse the smear blood images in a fully automatic way and to deliver information on the number and statistics of the red blood cells, both healthy and pathologic. The system was examined in two case studies, involving the canine and human blood, and then consulted with the experienced medicine specialists. The accuracy of classification of red blood cells into erythrocytes and echinocytes reaches 96%.

Słowa kluczowe

EN

optical microscopy; blood cells; biophotonics; image analysis; classification; eigenfaces; neural networks; decision support; nanodiamonds; bioimaging

• Wydawca: Komitet Metrologii i Aparatury Naukowej PAN
• Czasopismo: Metrology and Measurement Systems
• Rocznik: 2019
• Tom: Vol. 26, nr 1
• Strony: 81--93
• Opis fizyczny: Bibliogr. 28 poz., rys., tab., wykr.

Twórcy

autor

Grochowski Michał

• Gdańsk University of Technology, Faculty of Electrical and Control Engineering, G. Narutowicza 11/12, 80-233 Gdańsk, Poland

autor

Wąsowicz Michał

• Warsaw University of Life Sciences, Faculty of Veterinary Medicine, Nowoursynowska 159, 02-776 Warsaw, Poland

autor

Mikołajczyk Agnieszka

• Gdańsk University of Technology, Faculty of Electrical and Control Engineering, G. Narutowicza 11/12, 80-233 Gdańsk, Poland

autor

Ficek Mateusz

• Gdańsk University of Technology, Faculty of Electronics, Telecommunications and Informatics, G. Narutowicza 11/12, 80-233 Gdańsk, Poland

autor

Kulka Marek

• Warsaw University of Life Sciences, Faculty of Veterinary Medicine, Nowoursynowska 159, 02-776 Warsaw, Poland

autor

Wróbel Maciej S.

• Gdańsk University of Technology, Faculty of Electronics, Telecommunications and Informatics, G. Narutowicza 11/12, 80-233 Gdańsk, Poland

autor

Jędrzejewska-Szczerska Małgorzata

• Gdańsk University of Technology, Faculty of Electronics, Telecommunications and Informatics, G. Narutowicza 11/12, 80-233 Gdańsk, Poland

Bibliografia

• [1] Provan, D. (2018). ABC of Clinical Haematology 4ed. Wiley Blackwell.
• [2] Moritz, A., Fickenscher, Y., Meyer, K., Failing, K., Weiss, D.J. (2004). Canine and feline hematology reference values for the Advia 120 hematology system. Vet Clin. Pathol.,33, 32-38.
• [3] Walker, H.K., Hall, W.D., Hurst, J.W. (1990). Peripheral blood smear, Clinical Methods: The History, Physical, and Laboratory Examinations. Butterworths, Boston.
• [4] Bhagavathi, S.L., Thomas Niba, S. (2016). An Automatic System for Detecting and Counting RBC and WBC using Fuzzy Logic. ARPN Journal of Engineering and Applied Sciences, 11(11), 6891-6894.
• [5] Alomari, Y.M., Abdullah, S., Huda S.N., Zaharatul Azma, R., Omar, K. (2014). Automatic detection and quantification of WBCs and RBCs using iterative structured circle detection algorithm. Computational and mathematical methods in medicine, 1-17.
• [6] Savkare, S.S., Narote S.P., (2015). Blood cell segmentation from microscopic blood images. Information Processing (ICIP), International Conference on IEEE, 502-505.
• [7] Liu, Z., Liu, J., Xiao, X., Yuan, H., Li, X., Chang, J., Zheng, C., (2015). Segmentation of white blood cells through nucleus mark watershed operations and mean shift clustering. Sensors, 15(9), 22561-22586.
• [8] Khajehpour, H., Dehnavi, A.M., Taghizad, H., Khajehpour, E., Naeemabadi, M. (2013). Detection and Segmentation of Erythrocytes in Blood Smear Images Using a Line Operator and Watershed Algorithm. Journal of Medical Signals and Sensors, 3(3), 164-171.
• [9] Rawat, J., Singh, A., Bhadauria, H.S., Virmani, J. (2015). Computer aided diagnostic system for detection of leukemia using microscopic images. Procedia Computer Science, 70, 748-756.
• [10] Zhang, C., Xiao, X., Li, X., Chen, Y.-J., Zhen, W., Chang, J., Zheng, C., Liu, Z. (2014). White Blood Cell Segmentation by Color-Space-Based K-Means Clustering. Sensors, 14, 16128-16147.
• [11] Rosado, L., da Costa, J.M.C., Elias, D., Cardoso, J.S. (2017). Mobile-Based Analysis of Malaria-Infected Thin Blood Smears: Automated Species and Life Cycle Stage Determination. Sensors, 17, 2167.
• [12] Spigulis, J. (2017). Multispectral, Fluorescent and Photoplethysmographic Imaging for Remote Skin Assessment. Sensors, 17, 1165.
• [13] Kharbach, A., Bellach, B., Rahmoune, M., Rahmoun, M., Kacem, H.H. (2017). Towards a Novel Approach for Tumor Volume Quantification. J. Imaging, 3, 41.
• [14] Hill, J. Matlock, K., Nutter, B., Mitra, S. (2015). Automated Segmentation of MS Lesions in MR Images Based on an Information Theoretic Clustering and Contrast Transformations. Technologies, 3, 142-161.
• [15] Jędrzejewska-Szczerska, M. (2014). Response of a New Low-Coherence Fabry-Perot Sensor to Hematocrit Levels in Human Blood. Sensors, 14, 6965-6976.
• [16] Jędrzejewska-Szczerska, M., Gnyba, M. (2011). Optical investigation of hematocrit level in humanblood. Acta Physica Polonica A, 4, 642-646.
• [17] Wierzba, P., Jędrzejewska-Szczerska, M. (2013). Optimization of a Fabry-Perot Sensing Interferometer Design for an Optical Fiber Sensor of Hematocrit Level. Acta Physica Polonica, A, 124(3), 586-588.
• [18] Turk, M., Pentland, A. (1991) Eigenfaces for recognition. Journal of Cognitive Neuroscience, 3(1), 71-86.
• [19] Kwasigroch, A., Mikołajczyk, A., Grochowski, M. (2017). Deep convolutional neural networks as a decision support tool in medical problems - malignant melanoma case study. Advances in Intelligent Systems and Computing, Springer International Publishing AG, Cham (ZG), 577, 848-856.
• [20] Mikołajczyk, A., Kwasigroch, A., Grochowski, M. (2017). Intelligent system supporting diagnosis of malignant melanoma. Advances in Intelligent Systems and Computing, Springer International Publishing AG, Cham (ZG), 577, 828-837.
• [21] Kwasigroch, A., Mikołajczyk, A., Grochowski, M. (2017). Deep neural networks approach to skin lesions classification - A comparative analysis. 22nd International Conference on Methods and Models in Automation and Robotics (MMAR), Międzyzdroje, Poland, 1069-1074.
• [22] Swędrowski L., Duzinkiewicz, K., Grochowski, M., Rutkowski, T. (2014). Use of neural networks in diagnostics of rolling-element bearing of the induction motor. Key Engineering Materials, 588, 333-342.
• [23] Wąsowicz, M., Ficek, M., Wróbel, M.S., Chakraborty, R., Fixler, D., Wierzba, P., Jędrzejewska-Szczerska, M. (2017). Haemocompatibility of Modified Nanodiamonds. Materials, 10(4), 352.
• [24] Bain, B.J., Lewis, S.M., (2012) Preparation and staining methods for blood and bone marrow films. Dacie and Lewis, Practical Hematology, Elsevier: Edinburgh, UK, 57-68.
• [25] Hübl, W., Andert, S., Erath, A., Lapin, A., Bayer, P.M. (1995). Peripheral blood monocyte counting: towards a new reference method. Eur. J. Clin. Chem. Clin. Biochem., 33(11), 839-845.
• [26] Walker, H.K., Hall, W.D., Hurst, J.W. (1990). Peripheral blood smear, Clinical Methods: The History, Physical, and Laboratory Examinations. Butterworths, Boston, 155.
• [27] Jackson, J.E. (1991). A User’s Guide to Principal Components. Wiley.
• [28] Nowicki A., Grochowski, M. (2011). Kernel PCA in Application to Leakage Detection in Drinking Water Distribution System, Computational Collective Intelligence. Technologies and Applications, Springer Berlin Heidelberg, 497-506.

Uwagi

EN

1. Authors MF, MSW, and MJSZ acknowledge the DS funds of Department of Metrology and Optoelectronics, Faculty of Electronics, Telecommunications and Informatics, Gdańsk University of Technology. MSW acknowledges the support of National Science Centre under grant no. 2016/20/T/ST7/00380, and Foundation for Polish Science (FNP) START 95.2017. This study was partly supported by the Leading National Research Centre Scientific Consortium “Healthy Animal-Safe Food” Faculty of Veterinary Medicine, Warsaw University of Life Sciences, Poland. MG and AM acknowledge the DS funds of Department of Electrical Engineering, Control Systems and Informatics, Faculty of Electrical and Control Engineering, Gdańsk University of Technology. Furthermore, the authors would like to thank Mrs Magdalena Cymerman, Laboratory of Veterinary Analysis, ALAB Plus, for quality control of Good Laboratory Practices according to SO17025 during the research work.

PL

2. Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2019).