Novel Features for Automated Cell Phenotype Image Classification

  • Loris Nanni
  • Sheryl Brahnam
  • Alessandra Lumini
Conference paper
Part of the Advances in Experimental Medicine and Biology book series (AEMB, volume 680)


The most common method of handling automated cell phenotype image classification is to determine a common set of optimal features and then apply standard machine-learning algorithms to classify them. In this chapter, we use advanced methods for determining a set of optimized features for training an ensemble using random subspace with a set of Levenberg–Marquardt neural networks. The process requires that we first run several experiments to determine the individual features that offer the most information. The best performing features are then concatenated and used in the ensemble classification. Applying this approach, we have obtained an average accuracy of 97.4% using the three best benchmarks for this problem: the 2D HeLa dataset and both the endogenous and the transfected LOCATE mouse protein subcellular localization databases.


Pattern classification and recognition Image processing in medicine and biological sciences 


  1. 1.
    Boland MV & Murphy RF (2001). A neural network classifier capable of recognizing the patterns of all major subcellular structures in fluorescence microscope images of HeLa cells. Bioinformatics, 17:1213–1223.PubMedCrossRefGoogle Scholar
  2. 2.
    Chebira A, Barbotin Y, Jackson C, Merryman T, Srinivasa G, Murphy RF & Kovačević J (2007). A multiresolution approach to automated classification of protein subcellular location images. BMC Bioinformatics, 8:210.PubMedCrossRefGoogle Scholar
  3. 3.
    Chen X & Murphy RF (2005). Objective clustering of proteins based on subcellular location patterns. Journal of Biomedicine Biotechnology, 2:87–95.CrossRefGoogle Scholar
  4. 4.
    Chen S-C, Zhao T, Gordon GJ & Murphy RF (2007). Automated image analysis of protein localization in budding yeast. Bioinformatics, 23:66–71.CrossRefGoogle Scholar
  5. 5.
    Conrad C, Erfle H, Warnat P, Daigle N, Lorch T, Ellenberg J, Pepperkok R & Eils R (2004). Automatic identification of subcellular phenotypes on human cell arrays. Genome Research, 14(6):1130–1136.PubMedCrossRefGoogle Scholar
  6. 6.
    Eisenhaber F & Bork P (1998). Wanted: subcellular localization of proteins based on sequence. Trends in Cell Biology, 8:169–170.PubMedCrossRefGoogle Scholar
  7. 7.
    Fink JL, Aturaliya RN, Davis MJ, Zhang F, Hanson K, Teasdale MS & Teasdale RD (2006). LOCATE: a protein subcellular localization database. Nucleic Acids Research, 34(database issue):D213–D217.PubMedCrossRefGoogle Scholar
  8. 8.
    Glory E, Newberg J & Murphy RF (2008). Automated comparison of protein subcellular location patterns between images of normal and cancerous tissues. In ISBI, 304–307.Google Scholar
  9. 9.
    Hagan MT & Menhaj M (1999). Training feed-forward networks with the Marquardt algorithm. IEEE Transactions on Neural Networks, 5(6):989–993.CrossRefGoogle Scholar
  10. 10.
    Hamilton N, Pantelic R, Hanson K & Teasdale RD (2007). Fast automated cell phenotype classification. BMC Bioinformatics, 8:110.PubMedCrossRefGoogle Scholar
  11. 11.
    Haralick RM (1979). Statistical and structural approaches to texture. Proceedings of the IEEE, 67(5):768–804.CrossRefGoogle Scholar
  12. 12.
    Ho TK (1998). The random subspace method for constructing decision forests. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(8):832–844.CrossRefGoogle Scholar
  13. 13.
    Huang K & Murphy RF (2004). Automated classification of subcellular patterns in multicell images without segmentation into single cells. In IEEE International Symposium on Biomedical Imaging: Nano to Macro, Arlington, VA, USA, 1139–1142.Google Scholar
  14. 14.
    Huang K & Murphy R (2004). Boosting accuracy of automated classification of fluorescence microscope images for location proteomics. BMC Bioinformatics, 5:78, doi:10.1186/1471-2105-5-78.PubMedCrossRefGoogle Scholar
  15. 15.
    Lin CC, Tsai Y-S, Lin Y-S, Chiu T-Y, Hsiung C-C, Lee M-I, Simpson JC & Hsu C-N (2007). Boosting multiclass learning with repeating codes and weak detectors for protein subcellular localization. Bioinformatics, 23(24):3374–3381.PubMedCrossRefGoogle Scholar
  16. 16.
    Nakai K & Horton P (1999). Psort: a program for detecting sorting signals in proteins and predicting their subcellular localization. Trends in Biochemical Science, 24:34–35.CrossRefGoogle Scholar
  17. 17.
    Nanni L & Lumini A (2008). A reliable method for cell phenotype image classification. Artificial Intelligence in Medicine, 43(2):87–97.PubMedCrossRefGoogle Scholar
  18. 18.
    Nanni L & Lumini A (2009). Ensemble of neural networks for automated cell phenotype image classification. Biomedical Image Analysis and Machine Learning Technologies: Applications and Techniques.Google Scholar
  19. 19.
    Ojala T, Pietikainen M & Maeenpaa T (2002). Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(7):971–987.CrossRefGoogle Scholar
  20. 20.
    Ojansivu V & Heikkilä J (2008). Blur insensitive texture classification using local phase quantization. In Proc. 3rd International Conference on Image and Signal Processing (ICISP 2008), volume 5099 of LNCS, Springer, Berlin, 236–243.Google Scholar
  21. 21.
    Tan X, Triggs B (2007). Enhanced local texture feature sets for face recognition under difficult lighting conditions. In Analysis and Modelling of Faces and Gestures, volume 4778 of LNCS, Springer, Heidelberg, 168–182.Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2010

Authors and Affiliations

  1. 1.Computer Information SystemsMissouri State UniversitySpringfieldUSA

Personalised recommendations