Automated Cell Counter for Dunaliella Under Laboratory Condition
Article Sidebar
Main Article Content
Abstract
In order to maximize the potential of Dunaliella sp. as feedstock for biodiesel production, the laboratory culture conditions must be fully understood to obtain high yield and good quality lipids. However, optimizing culture conditions need rigorous daily monitoring of algal growth that entails time-consuming protocol like manual counting of cells under the microscope. This research developed a cost-effective system that utilizes Haar Cascade Algorithm as classifier, to automatically count Dunaliella sp. cells in order to calculate the culture cell density and generate data through graphs. The Automated Cell Counter has a percentage accuracy of 87.75% and percentage performance of 87.75% using F-measure (F1-score). Moreover, the precision (exactness) of the system and recall (sensitivity of the classifier) has values of 72.76% and 71.3%, respectively. Analysis of Variance (ANOVA) revealed that the calculated cell density from automated cell counting and from manual counting done by domain experts of Dunaliella sp. is not significantly different (α0.05<0.609). Therefore, the Haar Cascade Algorithm can be used as classifier to count Dunaliella sp. cells.
Downloads
Article Details
Section
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
References
Bamford P, & Lovell, B. (1998). Unsupervised cell nucleus segmentation with active contours. Signal Processing Special Issue: Deformable Models and Techniques for Image and Signal Processing, 71(2), 203-231.
Cordoba-Matson, M.V., Gutierrez, J., & Porta-Gandara, A. (2010). Evaluation of Isochrysis galbana (clone T-ISO) cell numbers by digital image analysis of color intensity. Journal of Applied Phycology, 22(4), 427-434.
Han, S. (2014). How to count cells: An overview of cell counting methods. Retrieved September 15, 2015 https://www.linkedin.com/pulse/20140929030437-16207202-how-to-count-cells-an-overview-of-cell-counting-methods
Imamoglu E., Vardar S.F., & Conk D.M. (2007). Effect of different culture media and light intensities on growth of Haematococcus pluvialis. International Journal of Natural and Engineering Sciences, 1(3), 05-09.
Invitrogen (2009). Comparison of image-based cell counting methods: Countess automated cell counter vs the hemocytometer. Life Technologies Corporation. Retrieved September 15, 2015 http://www.mc.vanderbilt.edu/documents/ mclaughlinlab/files/W-082494-Cell-Counting-Hemocytometer.pdf
Li, C., Xu, C., Gui, C., & Fox, M.D. (2010). Distance regularized level set evolution and its application to image segmentation. IEEE Transactions on Image Processing, 19(12), 3243 – 3254.
Nielson, L., Smyth G., & Greenfield P. (1991). Hemacytometer cell count distributions: implications of non-poisson behavior. Biotechnology Progress, 7(6), 560-563.
Sjostrom, P.J., Frydel, B.R., & Wahlberg, L.U. (1999). Artificial neural network-aided image analysis system for cell counting. Cytometry, 36(1), 18-26.
Viola, P. & Jones, M. (2001). Rapid object detection using boosted cascade of simple features. Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol 2:iiii-xxii.
Young, D., Glasbey, C., Gray, A., & Martin, N. (1998). Towards automatic cell identification in DIC microscopy. Journal of Microscopy, 192(2), , 186-193.