0
Research Papers

Portable Device for Measuring Blood Test Hemolyzed Samples Based on Computer Vision and Neural Network

[+] Author and Article Information
Karyn Martinelli Lopes

Department of Production Engineering,
Polytechnic School at the
University of Sao Paulo,
Professor Almeida Prado Avenue, 128,
Sao Paulo, SP 05508-070, Brazil
e-mail: kmlopes@usp.br

Flavia Helena da Silva

Fleury Group,
Clinical Analysis,
General Valdomiro de Lima Avenue, 508,
Sao Paulo, SP 04344-070, Brazil
e-mail: flavia.silva@grupofleury.com.br

Alessandra S. Gil Maldonado

Fleury Group,
Clinical Analysis,
General Valdomiro de Lima Avenue, 508,
Sao Paulo, SP 04344-070, Brazil
e-mail: alessandra.maldonado@grupofleury.com.br

Simone Aparecida Santiago

Fleury Group,
Clinical Analysis,
General Valdomiro de Lima Avenue, 508,
Sao Paulo, SP 04344-070, Brazil
e-mail: simone.santiago@grupofleury.com.br

Tavani A. Pires

Fleury Group,
Clinical Analysis,
General Valdomiro de Lima Avenue, 508,
Sao Paulo, SP 04344-070, Brazil
e-mail: tavani.pires@grupofleury.com.br

Claudia Maria Ferrer

Fleury Group,
Clinical Analysis,
General Valdomiro de Lima Avenue, 508,
Sao Paulo, SP 04344-070, Brazil
e-mail: claudia.ferrer@grupofleury.com.br

Sara Josa Mena

Fleury Group,
Clinical Analysis,
General Valdomiro de Lima Avenue, 508,
Sao Paulo, SP 04344-070, Brazil
e-mail: sara.mena@grupofleury.com.br

Maria Emilia Germani Moura

Fleury Group,
Clinical Analysis,
General Valdomiro de Lima Avenue, 508,
Sao Paulo, SP 04344-070, Brazil
e-mail: mariaemilia.moura@grupofleury.com.br

Pietro Teruya Domingues

Department of Mechatronics Engineering,
Polytechnic School at the
University of Sao Paulo,
Professor Mello Moraes Avenue, 2231,
Sao Paulo, SP 05508-030, Brazil
e-mail: pietro.domingues@usp.br

Lincoln Makoto Kawakami

Department of Electronic Systems Engineering,
Polytechnic School at the
University of Sao Paulo,
Professor Luciano Gualberto Avenue, 158,
Sao Paulo, SP 05508-010, Brazil
e-mail: lincoln.kawakami@usp.br

Eduardo de Senzi Zancul

Department of Production Engineering,
Polytechnic School at the
University of Sao Paulo,
Professor Almeida Prado Avenue, 128,
Sao Paulo, SP 05508-070, Brazil
e-mail: ezancul@usp.br

Manuscript received June 4, 2018; final manuscript received February 27, 2019; published online April 4, 2019. Assoc. Editor: Chris Rylander.

J. Med. Devices 13(2), 021004 (Apr 04, 2019) (8 pages) Paper No: MED-18-1096; doi: 10.1115/1.4043078 History: Received June 04, 2018; Revised February 27, 2019

Hemolysis is a challenging problem and still represents a frequent source of errors in blood test laboratory practice. Due to the broad and heterogeneous bias induced in the measurement of several parameters by hemolysis, inaccurate results may be reported, and the patient may be required to repeat sample collection, delaying diagnosis. Existing automated laboratory devices including hemolysis detection are not suitable for lower volume and smaller sample collection sites. In many situations, hemolysis is still detected by visual inspection of the sample after centrifugation, during the blood test pre-analytical stage. Visual inspection is highly dependent on a qualified workforce, subjective to interpretation discrepancies, and thus difficult to standardize. The paper aims to describe the design and performance of a portable device for measuring hemolyzed samples based on computer vision and neural network. The results indicate that the device provides hemolysis indexes with sufficient accuracy to guide laboratory decision in the blood test pre-analytical stage.

FIGURES IN THIS ARTICLE
<>
Copyright © 2019 by ASME
Your Session has timed out. Please sign back in to continue.

References

Heireman, L. , Van Geel, P. , Musger, L. , Heylen, E. , Uyttenbroeck, W. , and Mahieu, B. , 2017, “ Causes, Consequences, and Management of Sample Hemolysis in the Clinical Laboratory,” Clin. Biochem., 50(18), pp. 1317–1322. [CrossRef] [PubMed]
Howanitz, P. J. , Lehman, C. M. , Jones, B. A. , Meier, F. A. , and Horowitz, G. L. , 2015, “ Practices for Identifying and Rejecting Hemolyzed Specimens are Highly Variable in Clinical Laboratories,” Arch. Pathol. Lab. Med., 139(8), pp. 1014–1019. [CrossRef] [PubMed]
Lippi, G. , Cervellin, G. , Favaloro, J. E. , and Plebani, M. , 2012, In Vitro and In Vivo Hemolysis. An Unresolved Dispute in Laboratory Medicine, De Gruyter, Berlin.
Taskin, M. E. , Zhang, T. , Fraser, H. K. , Griffith, P. E. , and Zhongjun, J. W. , 2012, “ Design Optimization of a Wearable Artificial Pump-Lung Device With Computational Modeling,” ASME J. Med. Devices, 6(3), p. 031009. [CrossRef]
Lippi, G. , Blanckaert, N. , Bonini, P. , Green, S. , Kitchen, S. , Palicka, V. , Vassault, J. A. , and Plebani, M. , 2008, “ Haemolysis: An Overview of the Leading Cause of Unsuitable Specimens in Clinical Laboratories,” Clin. Chem. Lab. Med., 46(6), pp. 764–772. [CrossRef] [PubMed]
Janatpour, K. A. , Paglieroni, T. G. , Crocker, V. L. , DuBois, D. J. , and Holland, P. V. , 2004, “ Visual Assessment of Hemolysis in Red Blood Cell Units and Segments Can Be Deceptive,” Transfusion, 44(7), pp. 984–989. [CrossRef] [PubMed]
Grant, M. S. , 2003, “ The Effect of Blood Drawing Techniques and Equipment on the Hemolysis of ED Laboratory Blood Samples,” J. Emerg. Nurs., 29(2), pp. 116–121. [CrossRef] [PubMed]
Hawkins, R. C. , 2005, “ Poor Knowledge and Faulty Thinking Regarding Hemolysis and Potassium Elevation,” Clin. Chem. Lab. Med., 43(2), pp. 216–220. [CrossRef] [PubMed]
Dolci, A. , and Panteghini, M. , 2014, “ Harmonization of Automated Hemolysis Index Assessment and Use: Is It Possible?,” Clin. Chim. Acta, 432, pp. 38–43. [CrossRef] [PubMed]
Haykin, S. O. , 2009, Neural Networks and Learning Machines, Pearson, Hoboken, NJ.
Sebe, N. , and Lew, M. , 2003, Robust Computer Vision. Theory and Applications, Springer, Dordrecht, The Netherlands.
Tavares, J. M. , and Jorge, R. N. , 2015, Developments in Medical Image Processing and Computational Vision, Springer, Berlin.
Stevanović, M. , Marjanović, D. , and Štorga, M. , 2016, “ Idea Assessment and Selection in Product Innovation—The Empirical Research Results,” Tehnički Vjesnik, 23(6), pp. 1707–1716. https://hrcak.srce.hr/index.php?show=clanak&id_clanak_jezik=249918
Ko, D. H. , Won, D. , Jeong, T. D. , Lee, W. , Chun, S. , and Min, W. K. , 2015, “ Comparison of Red Blood Cell Hemolysis Using Plasma and Serum Separation Tubes for Outpatient Specimens,” Ann. Lab. Med., 35(2), pp. 194–197. [CrossRef] [PubMed]
Killilea, D. W. , Rohner, F. , Ghosh, S. , Otoo, G. E. , Smith, L. , Siekmann, J. H. , and King, J. C. , 2017, “ Identification of a Hemolysis Threshold That Increases Plasma and Serum Zinc Concentration,” J. Nutr., 147(6), pp. 1218–1225. [CrossRef] [PubMed]
Oh, J. Y. , Hamm, J. , Xu, X. , Genschmer, K. , Zhong, M. , Lebensburger, J. , Marques, M. B. , Kerby, J. D. , Pittet, J. F. , Gaggar, A. , and Patel, R. P. , 2016, “ Absorbance and Redox Based Approaches for Measuring Free Heme and Free Hemoglobin in Biological Matrices,” Redox Biol., 9, pp. 167–177. [CrossRef] [PubMed]
Schaer, D. J. , Buehler, P. W. , Alayash, A. I. , Belcher, J. D. , and Vercellotti, G. M. , 2013, “ Hemolysis and Free Hemoglobin Revisited: Exploring Hemoglobin and Hemin Scavengers as a Novel Class of Therapeutic Proteins,” Blood, 121(8), pp. 1276–1284. [CrossRef] [PubMed]
Su, C. H. , Chiu, H. S. , Hung, J. H. , and Hsieh, T. M. , 2014, “ Color Space Comparison Between RGB and HSV Based Images Retrieval,” Adv. Mater. Res., 989, pp. 4123–4126. https://doi.org/10.4028/www.scientific.net/AMR.989-994.4123
Lippi, G. , Plebani, M. , Di Somma, S. , and Cervellin, G. , 2011, “ Hemolyzed Specimens: A Major Challenge for Emergency Departments and Clinical Laboratories,” Crit. Rev. Clin. Lab. Sci., 48(3), pp. 143–153. [CrossRef] [PubMed]
Ji, J. Z. , and Meng, Q. H. , 2011, “ Evaluation of the Interference of Hemoglobin, Bilirubin, and Lipids on Roche Cobas 6000 Assays,” Clin. Chim. Acta, 412(17–18), pp. 1550–1553. [CrossRef] [PubMed]
Carraro, P. , Servidio, G. , and Plebani, M. , 2000, “ Hemolyzed Specimens: A Reason for Rejection or a Clinical Challenge?,” Clin. Chem., 46(2), pp. 306–307. http://clinchem.aaccjnls.org/content/46/2/306 [PubMed]

Figures

Grahic Jump Location
Fig. 1

Mechanical drawing of the device and three-dimensional perspectives

Grahic Jump Location
Fig. 3

Original image (left) and the image of the region selected by the algorithm (right)

Grahic Jump Location
Fig. 4

(a) Raw red index reading by the camera with the white LED switched on, (b) raw green index reading by the camera with the white LED switched on, (c) raw blue index reading by the camera with the white LED switched on, and (d) a linear regression that best fitted the data

Grahic Jump Location
Fig. 5

Comparison between the NN and the linear regression within the critical range

Grahic Jump Location
Fig. 6

Errors frequency without special cases

Grahic Jump Location
Fig. 7

Device error distribution

Tables

Errata

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In