Optical identification of hemolysis and lipemia in blood serum samples: computer vision and diffuse reflectance spectroscopy
Denisenko G.M.1,2, Fitagdinov R.R.3,4,5, Yakimov B.P.2,6,7, Biryukov A.A.7,8, Shitova Y.A.5, Keruntu E.N.7, Shkoda A.S.7, Shirshin E.A.2,6
1 Institute for Regenerative Medicine, Sechenov First Moscow State Medical University, Sechenov University, Moscow, Russia
2Laboratory of Clinical Biophotonics, Scientific and Technical Park of Biomedicine, First Moscow State Medical University (Sechenov University), Moscow, Russia
3Center for Photonics and 2D Materials, Moscow Institute of Physics and Technology, Dolgoprudnyi, Russia
4 Institute for Nuclear Research of Russian Academy of Sciences, Moscow, Russian
5Medeum LLC, Moscow, Russia
6Department of Physics, Lomonosov Moscow State University, Moscow, Russia
7City Clinical Hospital №67 named after L.A. Vorokhobova DZM, Moscow, Russia
8Laboratory for supporting medical decision making based on artificial intelligence technologies, First Moscow State Medical University (Sechenov University), Moscow, Russia
Email: eshirshin@gmail.com
One of the main sources of errors when conducting biochemical analysis of blood serum in a clinical diagnostic laboratory is the excessive concentration of hemoglobin (hemolysis) or lipids (lipemia) in the analyzed sample. Therefore, an important step to accurately determine the concentration of the target analyte is to first classify the sample into "suitable" and "unsuitable" classes for analysis. At the same time, to be used in practice, the method of preanalytical classification of samples must be both simple to implement and reliable, from the point of view of high sensitivity and specificity. In this work, we investigated the analytical ability of two approaches - an approach based on diffuse reflectance spectroscopy, characterizing the parameters of diffuse reflection of blood serum in the visible and near-IR range (500-1000 nm), and an approach based on computer vision - in classifying blood serum samples for normal suitable for analysis, and samples with hemolysis and lipemia. Diffuse reflectance spectroscopy has been found to demonstrate high sensitivity and specificity (more than 97%) in the classification of serum samples, but technically this method requires the application of a measuring probe to the sample. At the same time, computer vision methods have made it possible to determine the suitability of a sample for further analysis with lower classification accuracy values, but in more complex conditions, in particular, in the case of a sample moving along a conveyor line in a clinical diagnostic laboratory. The advantage of the studied methods, in addition to the high accuracy of preanalytical classification, is the simplicity of their technical implementation, as well as the ability to characterize samples without additional sampling of blood serum, which indicates their promise as methods for preanalytical analysis of blood serum samples. Keywords: diffuse reflectance spectroscopy, computer vision, lipemia, hemolysis, blood serum, preanalytics.
- J.Z. Ji, Q.H. Meng. Clinica Chimica Acta, 412 (17--18), 1550--1553 (2011)
- M.B. Smith, Y.W. Chan, A. Dolci, M.D. Kellogg, C.R. McCudden, M. McLean. Wayne, PA, USA: Clinical and Laboratory Standards Institute (2012)
- E.P. Kakorina, A.V. Polikarpov, N.A. Golubev. Laboratory Service, 7 (4), 32--39 (2018)
- P.L. Epner, J.E. Gans, M.L. Graber. BMJ Quality \& Safety, 22 (Suppl 2), ii6--ii10 (2013)
- P. Bonini, M. Plebani, F. Ceriotti, F. Rubboli. Clinical Chemistry, 48 (5), 691--698 (2002)
- G. Lippi, G.L. Salvagno, G. Lima-Oliveira, G. Brocco, E. Danese, G.C. Guidi. Clinica Chimica Acta, 440, 164--168 (2015)
- A.M. Simundic, K. Bolenius, J. Cadamuro, S. Church, M.P. Cornes, E.C. van Dongen-Lases, P. Eker, T. Erdeljanovic, K. Grankvist, J.T. Guimaraes, R. Hoke. Clinical Chemistry and Laboratory Medicine (CCLM), 56 (12), 2015--2038 (2018)
- G. Lima-Oliveira, G. Lippi, G.L. Salvagno, M. Montagnana, G. Picheth, G.C. Guidi. Biochemia Medica, 22 (2), 180--186 (2012)
- F. Sanchis-Gomar, G. Lippi. Biochemia Medica, 24 (1), 68--79 (2014)
- G. Lippi, G.L. Salvagno, E. Danese, G. Lima-Oliveira, G. Brocco, G.C. Guidi. Clinica Chimica Acta, 436, 183--187 (2014)
- A.-M. Simundic, M. Cornes, K. Grankvist, G. Lippi, M. Nybo. Clinica Chimica Acta, 432, 33--37 (2014)
- W. Barcellini. Transfusion Medicine and Hemotherapy, 42 (5), 287--293 (2015)
- A. Abdollahi, H. Saffar, H. Saffar. North Am. J. of Medical Sciences, 6 (5), 224 (2014)
- G. Lippi, M. Plebani, A.-M. Simundic. Biochemia Medica, 20 (2), 126--130 (2010)
- G. Tian, Y. Wu, X. Jin, Z. Zeng, X. Gu, T. Li, X. Chen, G. Li, J. Liu. J. Plos One, 17 (1), e0262748 (2022)
- N.J. Heyer, J.H. Derzon, L. Winges, C. Shaw, D. Mass, S.R. Snyder, P. Epner, J.H. Nichols, J.A. Gayken, D. Ernst, E.B. Liebow. Clinical Biochemistry, 45 (13--14), 1012--1032 (2012)
- G. Lippi, N. Blanckaert, P. Bonini, S. Green, S. Kitchen, V. Palicka, A.J. Vassault, M. Plebani. Clinical Chemistry and Laboratory Medicine, 46 (6), 764--772 (2008)
- R. Chawla, B. Goswami, D. Tayal, V. Mallika. Laboratory Medicine, 41 (2), 89--92 (2010)
- M.R. Glick, K.W. Ryder, S.J. Glick, J.R. Woods. Clinical Chemistry, 35 (5), 837--839 (1989)
- G. Lippi, J. Cadamuro, A. von Meyer, A.M. Simundic. Clinical Chemistry and Laboratory Medicine (CCLM), 56 (5), 718--727 (2018)
- A.M. Simundic, N. Nikolac, V. Ivankovic, D. Ferenec-Ruzic, B. Magdic, M. Kvaternik, E. Topic. Clinical Chemistry and Laboratory Medicine, 47 (11), 1361--1365 (2009)
- D.A. Noe, V. Weedn, W.R. Bell. Clinical Chemistry, 30 (5), 627--630 (1984)
- C. Burki, M. Volleberg, D. Brunner, M. Schmugge, M. Hersberger. Clinical Biochemistry, 100, 67--70 (2022)
- S. Storti, E. Battipaglia, M.S. Parri, A. Ripoli, S. Lombardi, G. Andreani. J. Laboratory Medicine, 43 (2), 67--76 (2019)
- C.-J.L. Farrell, A.C. Carter. Ann. Clin. Biochem., 53 (5), 527--538 (2016)
- Z. Du, J. Liu, H. Zhang, B. Bao, R. Zhao, Y. Jin. J. Clin. Lab. Anal., 33 (4), e22856 (2019)
- Z. Wang, Z. Zhao. In: MATEC Web Conf. 173, EDP Sciences (2018)
- H. Wang, H. Huang, X. Wu. Chemom. Intell. Lab. Syst., 231, 104688 (2022)
- C. Yang, D. Li, D. Sun, S. Zhang, P. Zhang, Y. Xiong, M. Zhao, T. Qi, B. Situ, L. Zheng. Clin. Chim. Acta, 531, 254--260 (2022)
- M. Ashenden, A. Clarke, K. Sharpe, G. d'Onofrio, J. Plowman, C.J. Gore. Int. J. Lab. Hematol., 35 (2), 183--192 (2013)
- Supervise.ly [Electronic source]. URL: https://supervisely.com/
- C.R. Harris, K.J. Millman, S.J. Van Der Walt, R. Gommers, P. Virtanen, D. Cournapeau, E. Wieser, J. Taylor, S. Berg, N.J. Smith, R. Kern. Nature, 585, 357--362 (2020). DOI: 10.1038/s41586-020-2649-2
- W. McKinney. In: Proceedings of the 9th Python in Science Conference, 445 (1), 51--56 (2010)
- J.D. Hunter. Computing in Science \& Engineering, 9 (03), 90--95 (2007)
- A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, A. Desmaison. Advances in Neural Information Processing Systems, 32 (2019)
- Ultralytics [Electronic source]. DOI: 10.5281/zenodo.7347926
- F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas. J. machine Learning Research, 12, 2825--2830 (2011)
- T.Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollar, C.L. Zitnick. In: Computer Vision--ECCV 2014: 13th European Conferenc Proceedings, Part V 13 (2014)
- R. Padilla, S.L. Netto, E.A. Da Silva. In: International conference on systems, signals and image processing ( IWSSIP), 237--242 (2020).
Подсчитывается количество просмотров абстрактов ("html" на диаграммах) и полных версий статей ("pdf"). Просмотры с одинаковых IP-адресов засчитываются, если происходят с интервалом не менее 2-х часов.
Дата начала обработки статистических данных - 27 января 2016 г.