Abstract
Indirect Immuno-Fluorescence (IIF) microscopy imaging of human epithelial (HEp-2) cells is a popular method for diagnosing autoimmune diseases. Considering large data volumes, computer-aided diagnosis (CAD) systems, based on image-based classification, can help in terms of time, effort, and reliability of diagnosis. Such approaches are based on extracting some representative features of the images. This work studies the selection of most distinctive features for HEp-2 cell images using the random forest framework. This framework provides a notion of variable importance for ranking features, which we use to select a good subset of features from a large set so that addition of new features to this subset does not increase classification accuracy. We perform various experiments to show the effectiveness of random forest in feature ranking as well as selection using three feature sets. We focus on using simple feature computation, and very less training data, and yet demonstrate high classification accuracy.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Blum, A.L., Langley, P.: Selection of relevant features and examples in machine learning. Artif. Intell. 97(1), 245–271 (1997)
Prasath, V.B.S., Kassim, Y.M., Oraibi, Z.A., Guiriec, J.-B., Hafiane, A., Seetharaman, G., Palaniappan, K.: HEp-2 cell classification and segmentation using motif texture patterns and spatial features with random forests. In: 23th International Conference on Pattern Recognition (ICPR). IEEE (2016)
Strandmark, P., Ulén, J., Kahl, F.: HEp-2 staining pattern classification. In: 2012 21st International Conference on Pattern Recognition (ICPR), pp. 33–36. IEEE (2012)
Li, B.H., Zhang, J., Zheng, W.-S.: HEp-2 cells staining patterns classification via wavelet scattering network and random forest. In: 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR), pp. 406–410. IEEE (2015)
Agrawal, P., Vatsa, M., Singh, R.: HEp-2 cell image classification: a comparative analysis. In: Wu, G., Zhang, D., Shen, D., Yan, P., Suzuki, K., Wang, F. (eds.) MLMI 2013. LNCS, vol. 8184, pp. 195–202. Springer, Cham (2013). doi:10.1007/978-3-319-02267-3_25
Moorthy, K., Mohamad, M.S.: Random forest for gene selection and microarray data classification. In: Lukose, D., Ahmad, A.R., Suliman, A. (eds.) KTW 2011. CCIS, vol. 295, pp. 174–183. Springer, Heidelberg (2012). doi:10.1007/978-3-642-32826-8_18
Paul, A., Dey, A., Mukherjee, D.P., Sivaswamy, J., Tourani, V.: Regenerative random forest with automatic feature selection to detect mitosis in histopathological breast cancer images. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9350, pp. 94–102. Springer, Cham (2015). doi:10.1007/978-3-319-24571-3_12
Nguyen, C., Wang, Y., Nguyen, H.N.: Random forest classifier combined with feature selection for breast cancer diagnosis and prognostic (2013)
Hariharan, S., Tirodkar, S., De, S., Bhattacharya, A.: Variable importance and random forest classification using RADARSAT-2 PolSAR data. In: IGARSS, pp. 1210–1213 (2014)
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)
Strobl, C., Zeileis, A.: Danger: high power!-exploring the statistical properties of a test for random forest variable importance (2008)
Hobson, P., Percannella, G., Vento, M., Wiliem, A.: Competition on cells classification by fluorescent image analysis. In: Proceedings of 20th IEEE International Conference Image Processing (ICIP), pp. 2–9 (2013)
Foggia, P., Percannella, G., Soda, P., Vento, M.: Benchmarking HEp-2 cells classification methods. IEEE Trans. Med. Imaging 32(10), 1878–1889 (2013)
Gupta, V., Gupta, K., Bhavsar, A., Sao, A.K.: Hierarchical classification of HEp-2 cell images using class-specific features. In: European Workshop on Visual Information Processing (EUVIP 2016). IEEE (2016)
Segal, M.R.: Machine learning benchmarks and random forest regression. Cent. Bioinform. Mol. Biostat. (2004)
Liaw, A., Wiener, M.: Classification and regression by randomforest. R News 2(3), 18–22 (2002)
Ensafi, S., Lu, S., Kassim, A.A., Tan, C.L.: A bag of words based approach for classification of HEp-2 cell images. In: 2014 1st Workshop on Pattern Recognition Techniques for Indirect Immunofluorescence Images (I3A), pp. 29–32. IEEE (2014)
Manivannan, S., Li, W., Akbar, S., Wang, R., Zhang, J., McKenna, S.J.: An automated pattern recognition system for classifying indirect immunofluorescence images of HEp-2 cells and specimens. Pattern Recogn. 51, 12–26 (2016)
Gao, Z., Wang, L., Zhou, L., Zhang, J.: HEp-2 cell image classification with deep convolutional neural networks (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Gupta, V., Bhavsar, A. (2017). Random Forest-Based Feature Importance for HEp-2 Cell Image Classification. In: Valdés Hernández, M., González-Castro, V. (eds) Medical Image Understanding and Analysis. MIUA 2017. Communications in Computer and Information Science, vol 723. Springer, Cham. https://doi.org/10.1007/978-3-319-60964-5_80
Download citation
DOI: https://doi.org/10.1007/978-3-319-60964-5_80
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-60963-8
Online ISBN: 978-3-319-60964-5
eBook Packages: Computer ScienceComputer Science (R0)