Generic placeholder image

Current Bioinformatics

Editor-in-Chief

ISSN (Print): 1574-8936
ISSN (Online): 2212-392X

Research Article

Benchmarking Classification Models for Cell Viability on Novel Cancer Image Datasets

Author(s): Akın Özkan*, Sultan Belgin İşgör, Gökhan Şengül and Yasemin Gülgün İşgör

Volume 14, Issue 2, 2019

Page: [108 - 114] Pages: 7

DOI: 10.2174/1574893614666181120093740

Price: $65

Abstract

Background: Dye-exclusion based cell viability analysis has been broadly used in cell biology including anticancer drug discovery studies. Viability analysis refers to the whole decision making process for the distinction of dead cells from live ones. Basically, cell culture samples are dyed with a special stain called trypan blue, so that the dead cells are selectively colored to darkish. This distinction provides critical information that may be used to expose influences of the studied drug on considering cell culture including cancer. Examiner’s experience and tiredness substantially affect the consistency throughout the manual observation of cell viability. The unsteady results of cell viability may end up with biased experimental results accordingly. Therefore, a machine learning based automated decision-making procedure is inevitably needed to improve consistency of the cell viability analysis.

Objective: In this study, we investigate various combinations of classifiers and feature extractors (i.e. classification models) to maximize the performance of computer vision-based viability analysis.

Method: The classification models are tested on novel hemocytometer image datasets which contain two types of cancer cell images, namely, caucasian promyelocytic leukemia (HL60), and chronic myelogenous leukemia (K562).

Results: From the experimental results, k-Nearest Neighbor (KNN) and Random Forest (RF) by combining Local Phase Quantization (LPQ) achieve the lowest misclassification rates that are 0.031 and 0.082, respectively.

Conclusion: The experimental results show that KNN and RF with LPQ can be powerful alternatives to the conventional manual cell viability analysis. Also, the collected datasets are released from the “biochem.atilim.edu.tr/datasets/” web address publically to academic studies.

Keywords: Cell viability, pattern classification, computer vision, hemocytometer, cancer cells, HL60, K562.

Graphical Abstract
[1]
Lovitt CJ, Shelper TB, Avery VM. Advanced cell culture techniques for cancer drug discovery. Biology 2014; 3: 345-67.
[2]
Mccullough B, Ying X, Monticello T, Bonnefoi M. Digital microscopy imaging and new approaches in toxicologic pathology. Toxicol Pathol 2004; 32: 49-58.
[3]
Lin DS, Huang FY, Chiu NC, et al. Comparison of hemocytometer leukocyte counts and standard urinalyses for predicting urinary tract infections in febrile infants. Pediatr Infect Dis J 2000; 19: 223-7.
[4]
Louis KS, Siegel AC. Cell viability analysis using trypan blue: manual and automated methods. Methods Mol Biol 2011; 740: 7-12.
[5]
Antony PP, Trefois C, Stojanovic A, Baumuratov AS, Kozak K. Light microscopy applications in systems biology: opportunities and challenges. Cell Commun Signal 2013; 11: 24.
[6]
Avelar-Freitas BA, Almeida VG, Pinto MC, et al. Trypan blue exclusion assay by flow cytometry. Braz J Med Biol Res 2014; 47: 307-15.
[7]
Birnie GD. The HL60 cell line: a model system for studying human myeloid cell differentiation. Br J Cancer Suppl 1988; 9: 41-5.
[8]
Klein E, Vánky F, Ben-Bassat H, et al. Properties of the K562 cell line, derived from a patient with chronic myeloid leukemia. Int J Cancer 1976; 18: 421-31.
[9]
Gultekin T, Koyuncu CF, Sokmensuer C, Gunduz-Demir C. Two-tier tissue decomposition for histopathological image representation 0and classification. IEEE Trans Med Imaging 2015; 34: 275-83.
[10]
Wang P, Hu X, Li Y, Liu Q, Zhu X. Automatic cell nuclei segmentation and classification of breast cancer histopathology images. Signal Processing 2016; 122: 1-3.
[11]
Sirinukunwattana K, Khan AM, Rajpoot NM. Cell words: Modelling the visual appearance of cells in histopathology images. Comput Med Imaging Graph 2015; 42: 16-24.
[12]
Kruk M, Osowski S, Koktysz R. Recognition and classification of colon cells applying the ensemble of classifiers. Comput Biol Med 2009; 39: 156-65.
[13]
Lyashenko VV, Babker AM, Kobylin OA. The methodology of wavelet analysis as a tool for cytology preparations image processing. Cukurova Med J 2016; 41: 453-63.
[14]
Pribyl LJ, Coughlin KA, Sueblinvong T, et al. Method for obtaining primary ovarian cancer cells from solid specimens. J Vis Exp 2014; 84: e51581.
[15]
Bora K, Chowdhury M, Mahanta LB, Kundu MK, Das AK. Automated classification of Pap smear images to detect cervical dysplasia. Comput Methods Programs Biomed 2017; 138: 31-47.
[16]
Nazlibilek S, Karacor D, Ertürk KL, Sengul G, Ercan T, Aliew F. White Blood Cells Classifications by SURF Image Matching, PCA and Dendrogram. Biomed Res 2015; 26: 633-40.
[17]
Das DK, Ghosh M, Pal M, Maiti AK, Chakraborty C. Machine learning approach for automated screening of malaria parasite using light microscopic images. Micron 2013; 45: 97-106.
[18]
Ojala T, Pietikäinen M, Harwood D. A comparative study of texture measures with classification based on featured distributions. Pattern Recognit 1996; 29: 51-9.
[19]
Ojala T, Pietikainen M, Maenpaa T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Pattern Anal Mach Intell 2002; 24: 971-87.
[20]
Paci M, Nanni L, Lahti A, Aalto-Setala K, Hyttinen J, Severi S. Non-binary coding for texture descriptors in sub-cellular and stem cell image classification. Curr Bioinform 2013; 8: 208-19.
[21]
Ojansivu V, Heikkilä J. Blur insensitive texture classification using local phase quantization. In: International conference on image and signal processing. 2008 Jul 1; Berlin, Heidelberg: Springer 2008; pp. 236-43.
[22]
Zhou SR, Yin JP, Zhang JM. Local binary pattern (LBP) and local phase quantization (LBQ) based on Gabor filter for face representation. Neurocomputing 2013; 116: 260-4.
[23]
Rahtu E, Heikkilä J, Ojansivu V, Ahonen T. Local phase quantization for blur-insensitive image analysis. Image Vis Comput 2012; 30: 501-12.
[24]
Dalal N, Triggs B. Histograms of oriented gradients for human detection. In: Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference; 2005 Jun 25 IEEE: 2005; pp. 886-93.
[25]
Chayeb A, Ouadah N, Tobal Z, Lakrouf M, Azouaoui O. HOG based multi-object detection for urban navigation. In: Intelligent Transportation Systems (ITSC), 2014 IEEE 17th International Conference; 2014; Oct 8. IEEE: 2014; pp. 2962-67.
[26]
Shawky DM, Seddik AF. On the Temporal Effects of Features on the Prediction of Breast Cancer Survivability. Curr Bioinform 2017; 12: 378-84.
[27]
Cortes C, Vapnik V. Support-vector networks. Mach Learn 1995; 20: 273-97.
[28]
Zhang N, Sa Y, Guo Y, Lin W, Wang P, Feng Y. Discriminating Ramos and Jurkat Cells with Image Textures from Diffraction Imaging Flow Cytometry Based on a Support Vector Machine. Curr Bioinform 2018; 13: 50-6.
[29]
Günal S. Hybrid feature selection for text classification. Turk J Electr Eng Comput Sci 2012; 20: 1296-311.
[30]
Breiman L. Random forests. Mach Learn 2001; 45: 5-32.
[31]
Wolpert DH, Macready WG. No free lunch theorems for optimization. IEEE Trans Evol Comput 1997; 1: 67-82.
[32]
Schaffer C. Selecting a classification method by cross-validation. Mach Learn 1993; 13: 135-43.
[33]
Kothandan R, Biswas S. Comparison of Kernel and Decision Tree-based Algorithms for the Prediction of microRNAs Associated with Cancer. Curr Bioinform 2016; 11: 143-51.
[34]
Catal C, Diri B. Investigating the effect of dataset size, metrics sets, and feature selection techniques on software fault prediction problem. Inf Sci 2009; 179: 1040-58.

Rights & Permissions Print Export Cite as
© 2024 Bentham Science Publishers | Privacy Policy