Skip to main content

Advertisement

SpringerLink
Log in

Hermite-based texture feature extraction for classification of humeral head in proton density-weighted MR images

  • New Trends in data pre-processing methods for signal and image classification
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

The objective of this research is to develop a computer-based diagnosis system which is capable of recognizing normal and edematous humeral head images by using texture features derived from Hermite transform. The performance of Hermite-based texture features in classification of humeral bone was compared with curvelet, contourlet and gray level co-occurrence matrix-based texture feature descriptors. To measure the performance of the extracted features, we deployed MLP (multilayer perceptron), SVM (support vector machine) and KNN (K-nearest neighbors) methods and demonstrated their power in differentiating the normal and abnormal regions. The proposed approach was tested on our own dataset which consists of 79 normal and 91 edematous humeral heads in PD (proton density)-weighted MR (magnetic resonance) images. The highest classification accuracy of Hermite-based method was 98.23% by MLP. In most cases, Hermite-based texture features surpassed the results of other proposed methods under all of the three classifiers. Our results suggest that the proposed system is a promising tool for classification of edematous and normal bone from PD-weighted MR images. This study is unique in the literature of using PD-weighted MR images and Hermite transform to classify bone edema .

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

Access this article

Log in via an institution

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

Similar content being viewed by others

References

  1. Pérez G, Garamendi JF, Diez RM, Schiavi E (2009) A multiphase approach to MRI shoulder images classification. In: Biomedical engineering systems and technologies. Springer, Berlin, pp 321–329

  2. Chaoui J, Hamitouche C, Stindel E, Roux C (2011) Recognition-based segmentation and registration method for image guided shoulder surgery. In: Annual international conference of the IEEE Engineering in Medicine and Biology Society, EMBC, pp 6212–6215

  3. Srinivasan EM, Ramar K, Suruliandi A (2011) Texture analysis using local texture patterns: a fuzzy logic approach. Int J Pattern Recognit Artif Intell 25(05):741–762

    Article  MathSciNet  Google Scholar 

  4. Thibault G, Fertil B, Navarro C, Pereira S, Cau P, Levy N, Mari JL (2013) Shape and texture indexes application to cell nuclei classification. Int J Pattern Recognit Artif Intell 27(01):1357002

    Article  MathSciNet  Google Scholar 

  5. Liu B, Cheng HD, Huang J, Tian J, Tang X, Liu J (2010) Fully automatic and segmentation-robust classification of breast tumors based on local texture analysis of ultrasound images. Pattern Recognit 43(1):280–298

    Article  MATH  Google Scholar 

  6. Xian GM (2010) An identification method of malignant and benign liver tumors from ultrasonography based on GLCM texture features and fuzzy SVM. Expert Syst Appl 37(10):6737–6741

    Article  MathSciNet  Google Scholar 

  7. Sertel O, Kong J, Shimada H, Catalyurek UV, Saltz JH, Gurcan MN (2009) Computer-aided prognosis of neuroblastoma on whole-slide images: classification of stromal development. Pattern Recognit 42(6):1093–1103

    Article  Google Scholar 

  8. Yu H, Caldwell C, Mah K, Mozeg D (2009) Coregistered FDG PET/CT-based textural characterization of head and neck cancer for radiation treatment planning. IEEE Trans Med Imaging 28(3):374–383

    Article  Google Scholar 

  9. Korchiyne R, Farssi SM, Sbihi A, Touahni R, Alaoui MT (2014) A combined method of fractal and GLCM features for MRI and CT scan images classification. arXiv preprint arXiv:1409.4559

  10. Zhang J, Tong L, Wang L, Li N (2008) Texture analysis of multiple sclerosis: a comparative study. Magn Reson Imaging 26(8):1160–1166

    Article  Google Scholar 

  11. Zhou S, Shi J, Zhu J, Cai Y, Wang R (2013) Shearlet-based texture feature extraction for classification of breast tumor in ultrasound image. Biomed Signal Process Control 8(6):688–696

    Article  Google Scholar 

  12. Eltoukhy MM, Faye I, Samir BB (2010) A comparison of wavelet and curvelet for breast cancer diagnosis in digital mammogram. Comput Biol Med 40(4):384–391

    Article  Google Scholar 

  13. Eltoukhy MM, Faye I, Samir BB (2010) Breast cancer diagnosis in digital mammogram using multiscale curvelet transform. Comput Med Imaging Graph 34(4):269–276

    Article  Google Scholar 

  14. González-Castro V, Alegre E, García-Olalla O, García-Ordás D, García-Ordás MT, Fernández-Robles L (2012) Curvelet-based texture description to classify intact and damaged boar spermatozoa. In: Image analysis and recognition. Springer, Berlin, pp 448–455

  15. Dettori L, Semler L (2007) A comparison of wavelet, ridgelet, and curvelet-based texture classification algorithms in computed tomography. Comput Biol Med 37(4):486–498

    Article  Google Scholar 

  16. Reddy T, Kalpalatha, Kumaravel N (2011) A comparison of wavelet, curvelet and contourlet based texture classification algorithms for characterization of bone quality in dental CT. In: Proceedings of international conference on environmental, biomedical and biotechnology, IPCBEE, vol 16

  17. Martens JB (2006) The Hermite transform: a survey. EURASIP J Appl Sig Process 2006:97

    MathSciNet  MATH  Google Scholar 

  18. Olveres J, Nava R, Moya-Albor E, Escalante-Ramírez B, Brieva J, Cristóbal G, Vallejo E (2014) Texture descriptor approaches to level set segmentation in medical images. In: International society for optics and photonics SPIE photonics Europe, pp 91380J–91380J

  19. Cruz-Techica S, Escalante-Ramirez B (2011) Image fusion algorithm using the multiresolution directional-oriented hermite transform. In: Pattern recognition. Springer, Berlin, pp 202–210

  20. Estudillo-Romero A, Esclante-Ramirez B (2011) Classification of low level visual texture features based on the hermite transform. In: IEEE seventh international conference on signal-image technology and internet-based systems (SITIS), 2011, pp 461–467

  21. Sezer A, Sezer HB, Albayrak S (2015). Segmentation of humeral head from axial proton density weighted shoulder MR images. In: International society for optics and photonics tenth international symposium on medical information processing and analysis, pp 928715–928715

  22. Haralick RM, Shanmugam K, Dinstein IH (1973) Textural features for image classification. IEEE Trans Syst Man Cybern 6:610–621

    Article  Google Scholar 

  23. Candes EJ, Donoho DL (2000) Curvelets, multiresolution representation, and scaling laws. In: Proceeding of SPIE, vol 4119, No. 1, pp 1–12

  24. Candes E, Demanet L, Donoho D, Ying L (2006) Fast discrete curvelet transforms. Multiscale Model Simul 5(3):861–899

    Article  MathSciNet  MATH  Google Scholar 

  25. Hall MA, Smith LA (1999) Feature selection for machine learning: comparing a correlation-based filter approach to the wrapper. In: FLAIRS conference, pp 235–239

  26. Do MN, Vetterli M (2005) The contourlet transform: an efficient directional multiresolution image representation. IEEE Trans Image Process 14(12):2091–2106

    Article  Google Scholar 

  27. Martens JB (1997) Local orientation analysis in images by means of the Hermite transform. IEEE Trans Image Process 6(8):1103–1116

    Article  Google Scholar 

  28. Ruck DW, Rogers SK, Kabrisky M (1990) Feature selection using a multilayer perceptron. J Neural Netw Comput 2(2):40–48

    Google Scholar 

  29. Suykens JA, Vandewalle J (1999) Least squares support vector machine classifiers. Neural Process Lett 9(3):293–300

    Article  MATH  Google Scholar 

  30. Sezer A, Sezer HB, Albayrak S (2015) An identification method of normal and edematous humeral head from PD weighted MR images based on GLCM texture features. In: International conference on medical, biological and pharmaceutical sciences (ICMBPS)

Download references

Author information

Authors and Affiliations

  1. Computer Engineering Department, Yildiz Technical University, 34220, Istanbul, Turkey

    Aysun Sezer & Songul Albayrak

  2. Orthopedics and Traumatology Clinic, Sisli Hamidiye Etfal Training and Research Hospital, 34371, Istanbul, Turkey

    Hasan Basri Sezer

Authors
  1. Aysun Sezer
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hasan Basri Sezer
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Songul Albayrak
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Aysun Sezer.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Sezer, A., Sezer, H.B. & Albayrak, S. Hermite-based texture feature extraction for classification of humeral head in proton density-weighted MR images. Neural Comput & Applic 28, 3021–3033 (2017). https://doi.org/10.1007/s00521-016-2709-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-016-2709-6

Keywords

Search

Navigation