Performance Comparison of Reticulocyte Count using Multilayer Perceptron and Convolution Neural Networks
Keywords:
Reticulocyte count, Multilayer perceptron, Convolutional neural networkAbstract
The reticulocyte count detected in the blood stream indicates the red blood cell production efficiency of the bone marrow which can be used for diagnosis and treatment monitoring. This research studied a method for counting reticulocytes from blood smear images stained with brilliant cresyle blue and couterstained with Wright-giemsa dye. We performed digital image processing techniques to segment red blood cell images and artificial neural networks to count reticulocytes. The results show that multilayer perceptron networks (MLP) using histograms of hue and saturation values of red blood cell images as inputs were more effecient in reticulocyte counting. This MLP used a smaller number of parameters and took less training and processing time compared artificial neural networks (CNN) that used red blood cell image as inputs. The MLP had a reticulocyte discrimination with 98.83% accuracy, 0.80 precision, 0.88 recall and 0.84 F1-score. This study indicates that the histograms of color information of red blood cell images are important features for reticulocyte discrimination. This program should be developed for use in laboratory in the future.
References
Riley RS, Ben-Ezra JM, Goel R, Tidwell A. Reticulocytes and reticulocyte enumeration. J Clin Lab Anal. 2001; 15: 267-294.
Briggs C, Bain BJ. Basic haematological techiques. In: Brain BJ, Bates I, Laffan MA, Lewis SM, editors. Dacies and Lewis practical haematology. 11th ed. Elsevier Churchill Livingstone. 2012: p 33-36.
Bracho FJ, Osorio IA. Evaluation of reticulocyte production index in pediatric population. Am J Clin Pathol. 2020; 154: 70-77.
Marks PW. Approach to anemia in the adult and child. In: Hoffman R, Benz, Jr EJ, Silberstein LE, Heslop HE, Weitz JI, Anastasi J, editors. Hematology: basic principles and practice. 6th ed. Elsevier Saunders. 2013: p 418-426.
NCCLS. Methods for reticulocyte counting (automated blood cell counters, flow cytometry and supravital dyes). Approved guideline. 2nd ed. Dcument H44-A2, Wayne PA: NCCLS; 2004.
Piva E, Brugnara C, Chiandetti L, Plebani M, Automated reticulocyte count: state of the art and clinical application in the evaluation of erythropoiesis. Clin Chem Lab Med. 2010; 48: 1369-1380.
Kratz A, Bengtsson H, Casey JE, Keefe JK, Beatrice GH, Grzybek DY, et al., Performance evaluation of the CellaVision DM96 system: WBC differentials by automated digital image analysis supported by an artificial neural network. Am J Clin Pathol. 2005; 124(5): 770-781.
Park SJ, Yoon J, Kwon JA, Yoon S. Evaluation of the CellaVision advanced RBC application for detecting red blood cell morphological abnormalities. Anal Lab Med. 2021; 41: 44-50.
Kratz A, Bengtsson H, Casey JE, Keefe JK, Beatrice GH, Grzybek DY, et al. Performance evaluation of the CellaVision DM96 system: WBC differentials by automated digital image analysis supported by an artificial neural network. Am J Clin Pathol. 2005; 124(5): 770-781.
Horn CL, Mansoor A, Wood B, Nelson H, Higa D, Lee LH, et al., Performance of the CellaVision® DM96 system for detecting red blood cell morphologic abnormalities. J Pathol Inform. 2015; 6: 11.
Park SJ, Yoon J, Kwon JA, Yoon S. Evaluation of the CellaVision advanced RBC application for detecting red blood cell morphological abnormalities. Anal Lab Med. 2021; 41: 44-50.
Abiodun OI, Jantan A, Omolara AE, Dada KV, Mohamed NA, Arshad H. State of the art in artificial neural network applications: a survey. Heliyon. 2018; 4(11): e00938.
Kaur J, Singh M, Bains PS, Singh G. Analysis of multi layer perceptron network. Inter J Comput Tech. 2013; 7(2): 600–606.
Ajit A, Acharya K, Samanta A. A review of convolutional neural networks. International Conference on Emerging Trends in Information Technology and Engineering; 2020 Feb 24-25; Vellore, India. IEEE; 2020. p. 1–5.
Ting FF, Sim KS. Self-regulated multilayer perceptron neural network for breast cancer classification. International Conference on Robotics, Automation and Sciences; 2017 Nov 27-29; Multimedia University, Melaka, Malaysia. IEEE; 2017. p. 1–5.
Maity M, Banerjee S, Sinha Chaudhuri S. Faster R-CNN and YOLO based vehicle detection: a survey. 5th International Conference on Computing Methodologies and Communication; 2021 April 8-10; Erode, India. IEEE; 2021. p. 1442–1447.
Rachmawati E, Khodra ML, Supriana I. Histogram based color pattern identification of multiclass fruit using feature selection. International Conference on Electrical Engineering and Informatics; 2015 Aug 10-11; Denpasar, Bali, Indonesia. IEEE; 2015. p. 43–48.
Drałus G, Mazur D, Czmil A. Automatic detection and counting of blood bells in smear images using RetinaNet. Entropy. 2021; 23(11): 1522.
Lamberti WF. Blood cell classification using interpretable shape features: a comparative study of SVM models and CNN-Based approaches. Computer Methods Programs Biomed Up. 2021;1:100023.
Parab MA, Mehendale ND. Red blood cell classification using image processing and CNN. SN Computer Sci. 2021; 2(2): 70.
Kitchen SF. The demonstration of reticulocyte with wright’s stain. Stain Technology 1938; 13: 107-109.
Yeldhos M, Peeyush KP. Red blood cell counter using embedded image processing techniques. Research Reports. 2018: e1-e5.
Thejashwini M, Padma MC. Counting of RBC’s and WBC’s using image processing technique. Int J Recent Innov Trends Comput Commun. 2015; 3(5): 2948–2953.
Maitra M, Kumar Gupta R, Mukherjee M. Detection and counting of red blood cells in blood cell images using Hough transform. Inter J Comput App. 2012. 53(16): 13–17.
Dvanesh VD, Lakshmi PS, Reddy K, Vasavi AS. Blood cell count using digital image processing. International Conference on Current Trends towards Converging Technologies; 2018 Mar 1-3; Coimbatore, Tamil Nadu, India. IEEE; 2018. p. 1–7.
Mazalan SM, Mahmood NH, Razak MAA. Automated red blood cells counting in peripheral blood smear image using circular Hough transform. 1st International Conference on Artificial Intelligence, Modelling and Simulation; 2013 Dec 3-5; Kota Kinabalu, Malaysia. IEEE; 2013. p. 320–324.
Alomari YM, Sheikh Abdullah SNH, Zaharatul Azma R, Omar K. Automatic detection and quantification of WBCs and RBCs using iterative structured circle detection algorithm. Comput Math Methods Med. 2014; 2014: 1–17.
Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, et al., MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861v1. Web 17 Apr 2017
Huang G, Liu Z, van der Maaten L, Weinberger KQ. Densely connected convolutional networks. arXiv:1608.06993v5. Web 28 Jan 2018.
Downloads
Published
Issue
Section
License
Copyright (c) 2023 KKU Research Journal (Graduate Studies)
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
