Abstract
The problem of detecting neurons in optical microscopy is considered by the example of Nissl-stained mouse brain slices. The proposed algorithm consists of the following steps: preprocessing, textural feature extraction, pixel classification, and pixel clustering. When solving this problem, we investigate various preprocessing methods, machine learning algorithms, and textural features. At the classification step, the k nearest neighbor (kNN) algorithm or the naive Bayes classifier (NBC) is used to determine whether each pixel of the image belongs to the neuron’s cell body. In this paper, we investigate textural features of two types: features based on the normalized histogram and features based on the gray level co-occurrence matrix (GLCM). To find the centers of the neurons, all pixels that belong to the neurons are clustered using the mean shift algorithm. It is shown that the best detection quality (precision = 0.82, recall = 0.92, and F1 = 0.86) is achieved with GLCM-based features and neighborhood radius R = 6. It is also shown that the selection of different preprocessing algorithms significantly affects the detection result. In terms of detection quality, the kNN algorithm outperforms the NBC. On the dataset used, the selection of the parameter k > 15 does not significantly improve the quality of detection. The proposed method yields the result similar to that achieved in [1]: Recall(A) = 865%. In sampling tests on some microscopy images from the Broad Bioimage Benchmark Collection (BBBC), the proposed approach shows the best or equivalent quality in detecting the number of cells on the image. For detection, the algorithm uses only local textural features, which removes restrictions on the parallelization of computations.
Similar content being viewed by others
REFERENCES
Inglis, A. et al., Automated identification of neurons and their locations, J. Microsc., 2008, vol. 230, no. 3, pp. 339–352.
Yao, X. and Nilanjan, R., Cell detection in microscopy images with deep convolutional neural network and compressed sensing, 2018.
Zohaib, M., Shan, A., Rahman, A.U., and Ali, H., Image enhancement by using histogram equalization technique in Matlab, Int. J. Adv. Res. Comput. Eng. Technol., 2018, vol. 7, no. 2, pp. 150–154. http://www. ijarcet.org/wp-content/uploads/IJARCET-VOL-7-ISSUE-2-150-154.pdf.
Lundin, H.F., Characterization and correction of analog-to-digital converters, Doctoral thesis, Stockholm, 2005. http://www.cis.rit.edu/class/simg712-90/notes/14-Quantization.pdf.
Yang, Yu.B., Elbuken, C., Ren, C.L., and Huissoon, J.P., Image processing and classification algorithm for yeast cell morphology in a microfluidic chip, J. Biomed. Opt., 2011, vol. 16, no. 6, p. 066008. https://doi.org/10.1117/1.3589100
Bustomi, M.A., Faricha, A., Ramdhan, A., and Faridawati, Integrated image processing analysis and naive Bayes classifier method for lungs X-ray image classification, ARPN J. Eng. Appl. Sci., 2018, vol. 13, no. 2, pp. 718–724. http://www.arpnjournals.org/jeas/research_papers/rp_2018/jeas_0118_6727.pdf.
Park, B.E., Jang, W.S., and Yoo, S.K., Texture analysis of supraspinatus ultrasound image for computer aided diagnostic system, Healthcare Inf. Res., 2016, vol. 22, no. 4, pp. 299–304.
Haralick, R.M., Shanmugam, L., and Dinstein, I., Textural features for image classification, IEEE Trans. Syst., Man, Cybern., 1973, vol. SMC-3, pp. 610–621.
Cheng, Y., Mean shift, mode seeking, and clustering, IEEE Trans. Pattern Anal. Mach. Intel., 1995, vol. 17, pp. 790–799.
Jiao, Y. and Du, P., Performance measures in evaluating machine learning based bioinformatics predictors for classifications, Quant. Biol., 2016, vol. 4, no. 4, pp. 320–330. https://doi.org/10.1007/s40484-016-0081-2
BrainMaps: An interactive multiresolution brain atlas. http://www.brainmaps.org.
Broad Bioimage Benchmark Collection: Annotated biological image sets for testing and validation. https://www.data.broadinstitute.org/bbbc/image_sets.html.
Open source computer vision library (OpenCV), 2018. https://www.opencv.org.
Akram, S.U., Kannala, J., Eklund, L., and Heikkilä, J., Cell segmentation proposal network for microscopy image analysis, Deep Learning and Data Labeling for Medical Applications, Carneiro, G., et al., Eds., Springer, 2016, vol. 10008. https://doi.org/10.1007/978-3-319-46976-8_3
Li, J., Tseng, K.-K., Hsieh, Z.Y., Yang, C.W., and Huang, H.-N., Staining pattern classification of antinuclear autoantibodies based on block segmentation in indirect immunofluorescence images. https://doi.org/10.1371/journal.pone.0113132
Han, J.W., Breckon, T.P., Randell, D.A., and Landini, G., The application of support vector machine classification to detect cell nuclei for automated microscopy, Mach. Vision Appl., 2012, vol. 23, no. 1, pp. 15–24. https://doi.org/10.1007/s00138-010-0275-y
Li, S., Wu, L., and Sun, Y., Cell image segmentation based on an improved watershed transformation, Proc. Int. Conf. Computational Aspects of Social Networks, 2010, no. 5636803, pp. 93–96.
He, Y. et al., iCut: An integrative cut algorithm enables accurate segmentation of touching cells, Sci. Rep., 2015, vol. 5, p. 12089.
Ojala, T. and Pietikainen, M., Texture classification, machine vision, and media processing unit, University of Oulu, Finland, 2008, vol. 230, pp. 339–352. http://www.homepages.inf.ed.ac.uk/rbf/CVonline/LOCAL_ COPIES/OJALA1/texclas.htm.
MicroImages, 2018. http://www.microimages.com/documentation.
Bino Sebastian, V., Unnikrishnan, A., and Balakrishnan, K., Grey level co-occurrence matrices: Generalization and some new features, Int. J. Comput. Sci., Eng., Inf. Technol., 2012, vol. 2, no. 2, pp. 151–157.
Rampun, A., Strange, H., and Zwiggelaar, R., Texture segmentation using different orientations of GLCM features, Proc. 6th Int. Conf. Computer Vision/Computer Graphics Collaboration Techniques and Applications (MIRAGE), 2013.
Pathak, B. and Barooah, D., Texture analysis based on the gray-level co-occurrence matrix considering possible orientations, Int. J. Adv. Res. Electr., Electron., Instrum. Eng., 2013, vol. 2, no. 9, pp. 4206–4212.
Subudhi, A., Sahoo, S., Biswal, P., and Sabut, S., Segmentation and classification of ischemic stroke using optimized features in brain MRI, Biomed. Eng.: Appl., Basis, Commun., 2018, vol. 30, no. 3.
Macedo, S., Melo, G., and Kelner, J., A comparative study of grayscale conversion techniques applied to sift descriptors, SBC J. Interact. Syst., 2015, vol. 6, no. 2, pp. 3–36.
Carpenter, A.E. et al., Cellprofiler: Image analysis software for identifying and quantifying cell phenotypes, Genome Biol., 2006, vol. 7, no. 10. https://www.genomebiology.biomedcentral.com/articles/10.1186/gb-2006-7-10-r100.
Author information
Authors and Affiliations
Corresponding authors
Additional information
Translated by Yu. Kornienko
Rights and permissions
About this article
Cite this article
Nosova, S.A., Turlapov, V.E. Detection of Brain Cells in Optical Microscopy Based on Textural Features with Machine Learning Methods. Program Comput Soft 45, 171–179 (2019). https://doi.org/10.1134/S0361768819040054
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S0361768819040054