Skip to main content
Springer Nature Link
Log in

Novel Mahalanobis-based feature selection improves one-class classification of early hepatocellular carcinoma

  • Original Article
  • Published:
Medical & Biological Engineering & Computing Aims and scope Submit manuscript

Abstract

Detection of early hepatocellular carcinoma (HCC) is responsible for increasing survival rates in up to 40%. One-class classifiers can be used for modeling early HCC in multidetector computed tomography (MDCT), but demand the specific knowledge pertaining to the set of features that best describes the target class. Although the literature outlines several features for characterizing liver lesions, it is unclear which is most relevant for describing early HCC. In this paper, we introduce an unconstrained GA feature selection algorithm based on a multi-objective Mahalanobis fitness function to improve the classification performance for early HCC. We compared our approach to a constrained Mahalanobis function and two other unconstrained functions using Welch’s t-test and Gaussian Data Descriptors. The performance of each fitness function was evaluated by cross-validating a one-class SVM. The results show that the proposed multi-objective Mahalanobis fitness function is capable of significantly reducing data dimensionality (96.4%) and improving one-class classification of early HCC (0.84 AUC). Furthermore, the results provide strong evidence that intensity features extracted at the arterial to portal and arterial to equilibrium phases are important for classifying early HCC.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

References

  1. Stewart BW, Wild CP, Report WC, et al (2014) World cancer report 2014. World Health Organ 1–2

  2. Hayat M a. (2008) Methods of cancer diagnosis, therapy and prognosis. https://doi.org/10.1007/978-1-4020-8369-3

  3. Bruix J, Sherman M (2011) Management of hepatocellular carcinoma: an update. Hepatology 53:1020–1022. https://doi.org/10.1002/hep.24199

    Article  PubMed  PubMed Central  Google Scholar 

  4. Tiferes DA, D’lppolito G (2008) Liver neoplasms: imaging characterization. Radiol Bras 41:119–127

    Article  Google Scholar 

  5. Kumar SS, Moni RS, Rajeesh J (2011) Automatic segmentation of liver and tumor for CAD of liver. Advances 2:63–70. https://doi.org/10.4304/jait.2.1.63-70

    Google Scholar 

  6. Freiman M, Cooper O, Lischinski D, Joskowicz L (2011) Liver tumors segmentation from CTA images using voxels classification and affinity constraint propagation. Int J Comput Assist Radiol Surg 6:247–255. https://doi.org/10.1007/s11548-010-0497-5

    Article  PubMed  Google Scholar 

  7. Quatrehomme A, Millet I, Hoa D et al (2013) Assessment of an automatic system classifying hepatic lesions on multi-phase computer tomography images. Eusipco 2013:2–6

    Google Scholar 

  8. Gletsos M, Mougiakakou SG, Matsopoulos GK et al (2003) A computer-aided diagnostic system to characterize CT focal liver lesions: design and optimization of a neural network classifier. IEEE Trans Inf Technol Biomed 7:153–162. https://doi.org/10.1109/TITB.2003.813793

    Article  PubMed  Google Scholar 

  9. Mougiakakou SG, Valavanis IK, Nikita A, Nikita KS (2007) Differential diagnosis of CT focal liver lesions using texture features, feature selection and ensemble driven classifiers. Artif Intell Med 41:25–37. https://doi.org/10.1016/j.artmed.2007.05.002

    Article  PubMed  Google Scholar 

  10. Chen EL, Chung PC, Chen CL et al (1998) An automatic diagnostic system for CT liver image classification. IEEE Trans Biomed Eng 45:783–794. https://doi.org/10.1109/10.678613

    Article  CAS  PubMed  Google Scholar 

  11. Bilello M, Gokturk SB, Desser T et al (2004) Automatic detection and classification of hypodense hepatic lesions on contrast-enhanced venous-phase CT. Med Phys 31:2584–2593. https://doi.org/10.1118/1.1782674

    Article  PubMed  Google Scholar 

  12. Kumar SS, Moni RS, Rajeesh J (2013) An automatic computer-aided diagnosis system for liver tumours on computed tomography images. Comput Electr Eng 39:1516–1526. https://doi.org/10.1016/j.compeleceng.2013.02.008

    Article  Google Scholar 

  13. Duda D, Kretowski M, Bezy-Wendling J (2006) Texture characterization for hepatic tumor recognition in multiphase CT. Biocybern Biomed Eng 26:15

    Google Scholar 

  14. Ye J, Sun Y, Wang S, et al (2009) Multi-phase CT image based hepatic lesion diagnosis by SVM. In: 2009 2nd Int. Conf. Biomed. Eng. Informatics. IEEE, pp 1–5

  15. Okumura E, Sanada S, Suzuki M, Matsui O (2006) A computer-aided temporal and dynamic subtraction technique of the liver for detection of small hepatocellular carcinomas on abdominal CT images. Phys Med Biol 51:4759–4771. https://doi.org/10.1088/0031-9155/51/19/003

    Article  CAS  PubMed  Google Scholar 

  16. Tajima T, Zhang X, Kitagawa T, et al (2007) Computer-aided detection (CAD) of hepatocellular carcinoma on multiphase CT images. Proc SPIE 6514:65142Q–65142Q–10. https://doi.org/10.1117/12.709174

  17. Kim KW, Lee JMJY, Klotz E et al (2009) Quantitative CT color mapping of the arterial enhancement fraction of the liver to detect hepatocellular carcinoma. Radiology 250:425–434. https://doi.org/10.1148/radiol.2501072196

    Article  PubMed  Google Scholar 

  18. Quatrehomme A, Millet I, Hoa D, et al (2013) Assessing the classification of liver focal lesions by using multi-phase computer tomography scans. In: Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics). pp 80–91

  19. Huang Y, Chen J, Shen W (2004) Computer-aided diagnosis of liver tumors in non-enhanced CT images. J Med Phys 9:141–150. https://doi.org/10.6558/MTJM.2004.9(3).1

    Google Scholar 

  20. Chi Y, Zhou J, Venkatesh SK et al (2013) Computer-aided focal liver lesion detection. Int J Comput Assist Radiol Surg 8:511–525. https://doi.org/10.1007/s11548-013-0832-8

    Article  PubMed  Google Scholar 

  21. Tax DMJ (2001) One-class classification. Technische Universiteit Delft

  22. Gheyas IA, Smith LS (2010) Feature subset selection in large dimensionality domains. Pattern Recogn 43:5–13. https://doi.org/10.1016/j.patcog.2009.06.009

    Article  Google Scholar 

  23. Zhu W, Huang W, Lin Z et al (2015) Data and feature mixed ensemble based extreme learning machine for medical object detection and segmentation. Multimed Tools Appl. https://doi.org/10.1007/s11042-015-2582-9

  24. Ververidis D, Kotropoulos C (2009) Information loss of the Mahalanobis distance in high dimensions: application to feature selection. IEEE Trans Pattern Anal Mach Intell 31:2275–2281. https://doi.org/10.1109/TPAMI.2009.84

    Article  PubMed  Google Scholar 

  25. Silverman PM, Szklaruk J (2005) Controversies in imaging of hepatocellular carcinoma: multidetector CT (MDCT). Cancer Imaging 5:178–187. https://doi.org/10.1102/1470–7330.2005.0105

    Article  PubMed  PubMed Central  Google Scholar 

  26. Haralick RM, Shanmugam K, Dinstein IH (1973) Textural features for image classification. Syst Man Cybern IEEE Trans 610–621

  27. Laws KI (1980) Textured image segmentation. Image Vis Comput. https://doi.org/10.1016/S0262-8856(97)00021-8

  28. Laws KI (1980) Rapid texture identification. Proc SPIE 0238. Image Process Missile Guid 238:376–381. https://doi.org/10.1117/12.959169

    Article  Google Scholar 

  29. Siedlecki W, Sklansky J (1989) A note on genetic algorithms for large-scale feature selection. Pattern Recogn Lett 10:335–347. https://doi.org/10.1016/0167-8655(89)90037-8

    Article  Google Scholar 

  30. Mahalanobis PC (1936) On the generalized distance in statistics. Proc Natl Inst Sci 2:49–55

    Google Scholar 

  31. Moya M, Hush D (1996) Network constraints and multi-objective optimization for one-class classification. Neural Netw 9:463–474. https://doi.org/10.1016/0893–6080(95)00120-4

    Article  Google Scholar 

  32. Tax DMJ, Duin RPW (1999) Data domain description using support vectors. Eur Symp Artif Neural Netw 251–256

  33. Stonehouse JM, Forrester GJ (1998) Robustness of the t and U tests under combined assumption violations. J Appl Stat 25:63–74. https://doi.org/10.1080/02664769823304

    Article  Google Scholar 

  34. Zimmerman DW, Zumbo BD (1993) Rank transformations and the power of the student T-test and Welch T-test for nonnormal populations with unequal variances. Can J Exp Psychol 47:523–539. https://doi.org/10.1037/h0078850

    Article  Google Scholar 

  35. Fagerland MW, Sandvik L (2009) Performance of five two-sample location tests for skewed distributions with unequal variances. Contemp Clin Trials 30:490–496. https://doi.org/10.1016/j.cct.2009.06.007

    Article  PubMed  Google Scholar 

  36. Jaakkola T, Diekhans M, Haussler D (1999) Using the Fisher kernel method to detect remote protein homologies. Int Conf Intell Syst Mol Biol 149–158

  37. Chih-Wei Hsu, Chih-Chung Chang and C-JL (2003) A practical guide to support vector classification

  38. Yang J, Singh H, Hines EL et al (2012) Channel selection and classification of electroencephalogram signals: an artificial neural network and genetic algorithm-based approach. Artif Intell Med 55:117–126. https://doi.org/10.1016/j.artmed.2012.02.001

    Article  PubMed  Google Scholar 

  39. Snoek J, Larochelle H, Adams RP (2012) Practical Bayesian optimization of machine learning algorithms. Adv Neural Inf Process Syst 25:2960–2968

  40. Metz CE (1978) Basic principles of ROC analysis. Semin Nucl Med 8:283–298. https://doi.org/10.1016/S0001-2998(78)80014-2

    Article  CAS  PubMed  Google Scholar 

  41. Sokolova M, Japkowicz N, Szpakowicz S (2006) Beyond accuracy F-score and ROC: a family of discriminant measures for performance evaluation, pp 1015–1021

  42. Braillon A (2015) Hepatocellular carcinoma surveillance: moving forward or looking in the rear-view mirror? Am J Gastroenterol 110:1625–1625. https://doi.org/10.1038/ajg.2015.329

    Article  CAS  PubMed  Google Scholar 

  43. Lee HC (2012) Noninvasive diagnostic criteria for hepatocellular carcinoma. Clin Mol Hepatol 18:174. https://doi.org/10.3350/cmh.2012.18.2.174

    Article  PubMed  PubMed Central  Google Scholar 

Download references

Acknowledgements

The authors would like to thank CNPq, CAPES, and FAPEMIG (Brazil) for the financial support.

Author information

Authors and Affiliations

  1. Biomedical Engineering Lab, Faculty of Electrical Engineering, Federal University of Uberlândia, Av. João Naves de Ávila 2121, Uberlândia, MG, 38408-100, Brazil

    Ricardo de Lima Thomaz, Pedro Cunha Carneiro, Ana Claudia Patrocinio & Alcimar Barbosa Soares

  2. Department of Radiology, General Hospital of Uberlândia, Federal University of Uberlândia, Av. Pará 1720, Uberlândia, MG, 38405-320, Brazil

    João Eliton Bonin & Túlio Augusto Alves Macedo

Authors
  1. Ricardo de Lima Thomaz
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Pedro Cunha Carneiro
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. João Eliton Bonin
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Túlio Augusto Alves Macedo
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Ana Claudia Patrocinio
    View author publications

    You can also search for this author inPubMed Google Scholar

  6. Alcimar Barbosa Soares
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Ricardo de Lima Thomaz.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Thomaz, R.d., Carneiro, P.C., Bonin, J.E. et al. Novel Mahalanobis-based feature selection improves one-class classification of early hepatocellular carcinoma. Med Biol Eng Comput 56, 817–832 (2018). https://doi.org/10.1007/s11517-017-1736-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-017-1736-5

Keywords