Display options
Cite
Khalid S, Jamil U, Saleem K, et al. Segmentation of skin lesion using Cohen-Daubechies-Feauveau biorthogonal wavelet. Springerplus. 2016;5(1):1603doi: 10.1186/s40064-016-3211-4.
Khalid, S., Jamil, U., Saleem, K., Akram, M. U., Manzoor, W., Ahmed, W., & Sohail, A. (2016). Segmentation of skin lesion using Cohen-Daubechies-Feauveau biorthogonal wavelet. SpringerPlus, 5(1), 1603. https://doi.org/10.1186/s40064-016-3211-4
Khalid, Shehzad, et al. "Segmentation of skin lesion using Cohen-Daubechies-Feauveau biorthogonal wavelet." SpringerPlus vol. 5,1 (2016): 1603. doi: https://doi.org/10.1186/s40064-016-3211-4
Khalid S, Jamil U, Saleem K, Akram MU, Manzoor W, Ahmed W, Sohail A. Segmentation of skin lesion using Cohen-Daubechies-Feauveau biorthogonal wavelet. Springerplus. 2016 Sep 19;5(1):1603. doi: 10.1186/s40064-016-3211-4. eCollection 2016. PMID: 27652176; PMCID: PMC5028360.
Copy Download .nbib Format: NLM
Share it on

Springerplus. 2016 Sep 19;5(1):1603. doi: 10.1186/s40064-016-3211-4. eCollection 2016.

Segmentation of skin lesion using Cohen-Daubechies-Feauveau biorthogonal wavelet.

SpringerPlus

Shehzad Khalid, Uzma Jamil, Kashif Saleem, M Usman Akram, Waleed Manzoor, Waqas Ahmed, Amina Sohail

Affiliations

  1. Department of Computer Engineering, Bahria University, Islamabad, Pakistan.
  2. Department of Computer Engineering, Bahria University, Islamabad, Pakistan ; Government College University, Faisalabad, Pakistan.
  3. National University of Sciences and Technology, Islamabad, Pakistan.

PMID: 27652176 PMCID: PMC5028360 DOI: 10.1186/s40064-016-3211-4

Abstract

This paper presents a novel technique for segmentation of skin lesion in dermoscopic images based on wavelet transform along with morphological operations. The acquired dermoscopic images may include artifacts inform of gel, dense hairs and water bubble which make accurate segmentation more challenging. We have also embodied an efficient approach for artifacts removal and hair inpainting, to enhance the overall segmentation results. In proposed research, color space is also analyzed and selection of blue channel for lesion segmentation have confirmed better performance than techniques which utilizes gray scale conversion. We tackle the problem by finding the most suitable mother wavelet for skin lesion segmentation. The performance achieved with 'bior6.8' Cohen-Daubechies-Feauveau biorthogonal wavelet is found to be superior as compared to other wavelet family. The proposed methodology achieves 93.87 % accuracy on dermoscopic images of PH2 dataset acquired at Dermatology Service of Hospital Pedro Hispano, Matosinhos, Portugal.

Keywords: Border detection; Dermoscopy; Image enhancement; Image segmentation; Skin cancer

References

  1. Comput Math Methods Med. 2012;2012:578721 - PubMed
  2. Skin Res Technol. 2000 Feb;6(1):1-5 - PubMed
  3. Br J Dermatol. 2003 Oct;149(4):801-9 - PubMed
  4. IEEE J Transl Eng Health Med. 2015 Apr 03;3:2900310 - PubMed
  5. Br J Dermatol. 2008 Sep;159(3):669-76 - PubMed
  6. IEEE Trans Image Process. 2012 Mar;21(3):1153-68 - PubMed
  7. JAMA. 2004 Dec 8;292(22):2771-6 - PubMed
  8. IEEE Trans Biomed Eng. 2008 Jan;55(1):157-61 - PubMed
  9. IEEE Trans Med Imaging. 1999 Feb;18(2):164-71 - PubMed
  10. IEEE Trans Biomed Eng. 2013 Apr;60(4):1134-41 - PubMed
  11. Med Phys. 2013 Feb;40(2):021911 - PubMed
  12. Skin Res Technol. 2008 Aug;14(3):347-53 - PubMed
  13. Comput Methods Programs Biomed. 2011 Dec;104(3):e1-15 - PubMed
  14. Skin Res Technol. 2011 Feb;17(1):91-100 - PubMed
  15. CA Cancer J Clin. 2016 Jan-Feb;66(1):7-30 - PubMed

Publication Types