Advertisement

Biomedical Engineering Letters

, Volume 9, Issue 3, pp 387–394 | Cite as

Content based medical image retrieval based on new efficient local neighborhood wavelet feature descriptor

  • Amita ShindeEmail author
  • Amol Rahulkar
  • Chetankumar Patil
Original Article

Abstract

This paper presents a new class of local neighborhood based wavelet feature descriptor (LNWFD) for content based medical image retrieval (CBMIR). To retrieve images effectively from large medical databases is backbone of diagnosis. Existing wavelet transform based medical image retrieval methods suffer from high length feature vector with confined retrieval performance. Triplet half-band filter bank (THFB) enhanced the properties of wavelet filters using three kernels. The influence of THFB has employed in the proposed method. First, triplet half-band filter bank (THFB) is used for single level wavelet decomposition to obtain four sub-bands. Next, the relationship among wavelet coefficients is exploited at each sub-band using 3 × 3 neighborhood window to form LNWFD pattern. The novelty of the proposed descriptor lies in exploring relation between wavelet transform values of pixels rather than intensity values which gives more detail local information in wavelet sub-bands. Thus, proposed feature descriptor is robust against illumination. Manhattan distance is used to compute similarity between query feature vector and feature vector of database. The proposed method is tested for medical image retrieval using OASIS-MRI, NEMA-CT, and Emphysema-CT databases. The average retrieval precisions achieved are 71.45%, 99.51% of OASIS-MRI and NEMA-CT databases for top ten matches considered respectively and 55.51% of Emphysema-CT database for top 50 matches. The superiority in terms of performance of the proposed method is confirmed by the experimental results over the well-known existing descriptors.

Keywords

Medical image retrieval Feature extraction Local neighborhood wavelet feature descriptor Triplet half-band filter bank Wavelet decomposition 

Notes

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical approval

This article does not contain any studies with human participants or animals performed by any of the authors.

References

  1. 1.
    Cai W, Kim J, Feng DD. Content based medical image retrieval. In: Feng D, editor. Biomedical information technology. Amsterdam: Elsevier; 2008. p. 83–113.CrossRefGoogle Scholar
  2. 2.
    Kumar A, Kim J, Cai W, Fulham M, Feng D. Content based medical image retrieval: a survey of applications to multidimensional and multimodality data. J Digit Imaging. 2013;26(6):1025–39.CrossRefGoogle Scholar
  3. 3.
    Unay D, Ekin A, Jasinschi R. Local structure-based region-of-interest retrieval in brain MR images. IEEE Trans Inf Technol Biomed. 2009;14(4):897–903.CrossRefGoogle Scholar
  4. 4.
    Iakovidis DK, Pelekis N, Kotsifakos EE, Kopanakis I, Karanikas H, Theodoridis Y. A pattern similarity scheme for medical image retrieval. IEEE Trans Inf Technol Biomed. 2009;13(4):442–50.CrossRefGoogle Scholar
  5. 5.
    Yang L, Jin R, Mummert L, Sukthankar R, Goode A, Zheng B, Hoi SCH, Satyanarayanan M. A boosting framework for visuality-preserving distance metric learning and its application to medical image retrieval. IEEE Trans Pattern Anal Mach Intell. 2010;32(1):30–44.CrossRefGoogle Scholar
  6. 6.
    Xu X, Lee DJ, Antani S, Long LR. A spine X-ray image retrieval system using partial shape matching. IEEE Trans Inf Technol Biomed. 2008;12(1):100–8.CrossRefGoogle Scholar
  7. 7.
    Murala S, Maheshwari RP, Balasubramanian R. Directional binary wavelet patterns for biomedical image indexing and retrieval. J Med Syst. 2012;36(5):2865–79.CrossRefGoogle Scholar
  8. 8.
    Swanson MD, Tewfik AH. A binary wavelet decomposition of binary images. IEEE Trans Image Process. 1996;5(12):1637–50.CrossRefGoogle Scholar
  9. 9.
    Ojala T, Pietikainen M, Harwood D. A comparative study of texture measures with classification based on feature distributions. Pattern Recognit. 1996;29(1):51–9.CrossRefGoogle Scholar
  10. 10.
    Quellec G, Lamard M, Cazuguel G, Cochener B, Roux C. Fast wavelet-based image characterization for highly adaptive image retrieval. IEEE Trans Image Process. 2012;21(4):1613–23.MathSciNetCrossRefzbMATHGoogle Scholar
  11. 11.
    Quellec G, Lamard M, Cazuguel G, Cochener B, Roux C. Wavelet optimization for content-based image retrieval in medical databases. Med Image Anal. 2010;14(2):227–41.CrossRefzbMATHGoogle Scholar
  12. 12.
    Dubey SR, Singh SK, Singh RK. Local wavelet pattern: a new feature descriptor for image retrieval in medical CT databases. IEEE Trans Image Process. 2015;24(12):5892–903.MathSciNetCrossRefzbMATHGoogle Scholar
  13. 13.
    Shinde AA, Rahulkar AD, Patil CY. Fast discrete curvelet transform-based anisotropic feature extraction for biomedical image indexing and retrieval. Int J Multimed Inf Retr. 2017;6(4):281–8.  https://doi.org/10.1007/s13735-017-0132-0.CrossRefGoogle Scholar
  14. 14.
    Murala S, Maheshwari RP, Balasubramanian R. Local tetra patterns: a new feature descriptor for content based image retrieval. IEEE Trans Image Process. 2012;21(5):2874–86.MathSciNetCrossRefzbMATHGoogle Scholar
  15. 15.
    Murala S, Wu QMJ. Local ternary co-occurrence patterns: a new feature descriptor for MRI and CT image retrieval. Neurocomputing. 2013;119:399–412.CrossRefGoogle Scholar
  16. 16.
    Murala S, Wu QMJ. Peak valley edge patterns: a new descriptor for biomedical image indexing and retrieval. In: CVPR. 2013; p. 444–9.Google Scholar
  17. 17.
    Murala S, Wu QMJ. Local mesh patterns versus local binary patterns: biomedical image indexing and retrieval. IEEE J Biomed Health Inform. 2014;18(3):929–38.CrossRefGoogle Scholar
  18. 18.
    Deep G, Kaur L, Gupta S. Directional local ternary quantized extrema pattern: a new descriptor for biomedical image indexing and retrieval. Eng Sci Technol. 2016;19(4):1895–909.Google Scholar
  19. 19.
    Shinde AA, Rahulkar AD, Patil CY. Local neighboring binary pattern: a new feature descriptor for biomedical image indexing and retrieval. IEEE ICSIP. 2017.  https://doi.org/10.1109/siprocess.2017.8124524.Google Scholar
  20. 20.
    Dubey SR, Singh SK, Singh RK. Local diagonal extrema pattern: a new and efficient feature descriptor for CT image retrieval. IEEE Signal Process Lett. 2015;22(9):1215–9.CrossRefGoogle Scholar
  21. 21.
    Dubey SR, Singh SK, Singh RK. Local bit-plane decoded pattern: a novel feature descriptor for biomedical image retrieval. IEEE J Biomed Health Inform. 2016;20(4):1139–47.CrossRefGoogle Scholar
  22. 22.
    Ansari R, Kim C, Dedovic M. Structure and design of two-channel filter banks derived from a triplet of halfband filters. IEEE Trans Circuits Syst II: Analog Digit Signal Process. 1999;46(12):1487–96.CrossRefGoogle Scholar
  23. 23.
    Kha HH, Tuan HD, Nguyen TQ. Optimal design of FIR triplet halfband filterbank and application in image coding. IEEE Trans Image Process. 2011;20(2):586–91.MathSciNetCrossRefzbMATHGoogle Scholar
  24. 24.
    Rahulkar AD, Patil BD, Holambe RS. A new approach to the design of biorthogonal triplet halfband filterbanks using generalized half band polynomials. Signal Image Video Process. 2014;8(8):1451–7.CrossRefGoogle Scholar
  25. 25.
    Rahulkar AD, Holambe RS. Half–iris feature extraction and recognition using a new class of biorthogonal triplet half-band filter bank and flexible k-out-of-n: a post classifier. IEEE Trans Inf Forensics Secur. 2012;7(1):230–40.CrossRefGoogle Scholar
  26. 26.
    Gawande JP, Rahulkar AD, Holambe RS. Design of new class of regular biorthogonal wavelet filter banks using generalized and hybrid lifting structures. Signal Image Video Process. 2015;9(1):S265–73.CrossRefGoogle Scholar
  27. 27.
    Gawande JP, Rahulkar AD, Holambe RS. A new approach to design triplet halfband filter banks based on balanced-uncertainty optimization. Digit Signal Process. 2016;56:123–31.MathSciNetCrossRefGoogle Scholar
  28. 28.
    Chopade PB, Rahulkar AD, Patil PM. Hybrid- thresholding based image super resolution technique by the use of triplet half-band wavelets. J Inst Eng India Ser B. 2016.  https://doi.org/10.1007/s40031-016-0244-6.Google Scholar
  29. 29.
    OASIS-MRI image database. http://www.oasis-brains.org/. Accessed 6 July 2016.
  30. 30.
    NEMA-CT image database. ftp://medical.nema.org/medical/Dicom/Multiframe/CT. Accessed 8 Mar 2017.
  31. 31.
    Emphysema-CT image database. http://image.diku.dk/emphysema_database/. Accessed 24 Jan 2017.
  32. 32.
    Cha SH. Comprehensive survey on distance/similarity measures between probability density functions. Int J Math Models Methods Appl Sci. 2007;1(4):300–7.Google Scholar

Copyright information

© Korean Society of Medical and Biological Engineering 2019

Authors and Affiliations

  • Amita Shinde
    • 1
    Email author
  • Amol Rahulkar
    • 2
  • Chetankumar Patil
    • 1
  1. 1.Instrumentation and ControlCollege of Engineering PunePuneIndia
  2. 2.Electrical and Electronics EngineeringNational Institute of Technology GoaFarmagudiIndia

Personalised recommendations