Skip to main content

Advertisement

SpringerLink
Log in

Hair detection and lesion segmentation in dermoscopic images using domain knowledge

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

Abstract

Automated segmentation and dermoscopic hair detection are one of the significant challenges in computer-aided diagnosis (CAD) of melanocytic lesions. Additionally, due to the presence of artifacts and variation in skin texture and smooth lesion boundaries, the accuracy of such methods gets hampered. The objective of this research is to develop an automated hair detection and lesion segmentation algorithm using lesion-specific properties to improve the accuracy. The aforementioned objective is achieved in two ways. Firstly, a novel hair detection algorithm is designed by considering the properties of dermoscopic hair. Second, a novel chroma-based geometric deformable model is used to effectively differentiate the lesion from the surrounding skin. The speed function incorporates the chrominance properties of the lesion to stop evolution at the lesion boundary. Automatic initialization of the initial contour and chrominance-based speed function aids in providing robust and flexible segmentation. The proposed approach is tested on 200 images from PH2 and 900 images from ISBI 2016 datasets. Average accuracy, sensitivity, specificity, and overlap scores of 93.4, 87.6, 95.3, and 11.52% respectively are obtained for the PH2 dataset. Similarly, the proposed method resulted in average accuracy, sensitivity, specificity, and overlap scores of 94.6, 82.4, 97.2, and 7.20% respectively for the ISBI 2016 dataset. Statistical and quantitative analyses prove the reliability of the algorithm for incorporation in CAD systems.

Overview of proposed system

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
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

References

  1. Pathan S, Prabhu KG, Siddalingaswamy P (2018) Techniques and algorithms for computer aided diagnosis of pigmented skin lesions—a review. Biomed Signal Process Control 39:237–262. https://doi.org/10.1016/j.bspc.2017.07.010

    Article  Google Scholar 

  2. Skin Cancer Foundation. In: Skin cancer facts & statistics - SkinCancer.org. https://www.skincancer.org/skin-cancer-information/skin-cancer-facts [Accessed 12 Jan 2018]

  3. Riaz F, Hassan A, Nisar R et al (2017) Content-adaptive region-based color texture descriptors for medical images. IEEE J Biomed Health Inf 21(1):162–171. https://doi.org/10.1109/jbhi.2015.2492464

    Article  Google Scholar 

  4. Ma Z, Tavares JMRS (2016) A novel approach to segment skin lesions in dermoscopic images based on a deformable model. IEEE J Biomed Health Inf 20(2):615–623. https://doi.org/10.1109/jbhi.2015.2390032

    Article  Google Scholar 

  5. Abuzaghleh O, Barkana BD, Faezipour M (2015) Noninvasive real-time automated skin lesion analysis system for melanoma early detection and prevention. IEEE J Transl Eng Health Med 3:1–12. https://doi.org/10.1109/jtehm.2015.2419612

    Article  Google Scholar 

  6. Lee T, Ng V, Gallagher R et al (1997) Dullrazor®: a software approach to hair removal from images. Comput Biol Med 27(6):533–543. https://doi.org/10.1016/s0010-4825(97)00020-6

    Article  CAS  PubMed  Google Scholar 

  7. Kiani K, Sharafat AR (2011) E-shaver: an improved DullRazor® for digitally removing dark and light-colored hairs in dermoscopic images. Comput Biol Med 41(3):139–145. https://doi.org/10.1016/j.compbiomed.2011.01.003

    Article  PubMed  Google Scholar 

  8. Xie F-Y, Qin S-Y, Jiang Z-G, Meng R-S (2009) PDE-based unsupervised repair of hair-occluded information in dermoscopy images of melanoma. Comput Med Imaging Graph 33(4):275–282. https://doi.org/10.1016/j.compmedimag.2009.01.003

    Article  PubMed  Google Scholar 

  9. Fleming MG, Steger C, Zhang J et al (1998) Techniques for a structural analysis of dermatoscopic imagery. Comput Med Imaging Graph 22(5):375–389. https://doi.org/10.1016/s0895-6111(98)00048-2

    Article  CAS  PubMed  Google Scholar 

  10. Abbas Q, Celebi M, García IF (2011) Hair removal methods: a comparative study for dermoscopy images. Biomed Signal Process Control 6(4):395–404. https://doi.org/10.1016/j.bspc.2011.01.003

    Article  Google Scholar 

  11. Pathan S, Prabhu KG, Siddalingaswamy P (2018) A methodological approach to classify typical and atypical pigment network patterns for melanoma diagnosis. Biomed Signal Process Control 44:25–37. https://doi.org/10.1016/j.bspc.2018.03.017

    Article  Google Scholar 

  12. Yuksel M, Borlu M (2009) Accurate segmentation of dermoscopic images by image thresholding based on type-2 fuzzy logic. IEEE Trans Fuzzy Syst 17(4):976–982. https://doi.org/10.1109/tfuzz.2009.2018300

    Article  Google Scholar 

  13. Celebi ME, Wen Q, Hwang S et al (2012) Lesion border detection in dermoscopy images using ensembles of thresholding methods. Skin Res Technol 19(1):252–258. https://doi.org/10.1111/j.1600-0846.2012.00636.x

    Article  Google Scholar 

  14. Xie F, Fan H, Li Y et al (2017) Melanoma classification on dermoscopy images using a neural network ensemble model. IEEE Trans Med Imaging 36(3):849–858. https://doi.org/10.1109/tmi.2016.2633551

    Article  PubMed  Google Scholar 

  15. Dalila F, Zohra A, Reda K, Hocine C (2017) Segmentation and classification of melanoma and benign skin lesions. Optik - Int J Light Electron Opt 140:749–761. https://doi.org/10.1016/j.ijleo.2017.04.084

    Article  Google Scholar 

  16. J Qi, M Le, C Li, P Zhou (2017) Global and local information based deep network for skin lesion segmentation, arXiv preprint arXiv:1703.05467

  17. Yu L, Chen H, Dou Q et al (2017) Automated melanoma recognition in dermoscopy images via very deep residual networks. IEEE Trans Med Imaging 36(4):994–1004. https://doi.org/10.1109/tmi.2016.2642839

    Article  PubMed  Google Scholar 

  18. Yuan Y, Chao M, Lo Y-C (2017) Automatic skin lesion segmentation using deep fully convolutional networks with Jaccard distance. IEEE Trans Med Imaging 36:1876–1886. https://doi.org/10.1109/tmi.2017.2695227

    Article  PubMed  Google Scholar 

  19. Abbas Q, Celebi ME, García IF, Rashid M (2011) Lesion border detection in dermoscopy images using dynamic programming. Skin Res Technol 17(1):91–100. https://doi.org/10.1111/j.1600-0846.2010.00472.x

    Article  PubMed  Google Scholar 

  20. Abbas Q, Celebi ME, García IF (2011) Skin tumor area extraction using an improved dynamic programming approach. Skin Res Technol 18(2):133–142. https://doi.org/10.1111/j.1600-0846.2011.00544.x

    Article  PubMed  Google Scholar 

  21. Zhou H, Li X, Schaefer G et al (2013) Mean shift based gradient vector flow for image segmentation. Comput Vis Image Underst 117(9):1004–1016. https://doi.org/10.1016/j.cviu.2012.11.015

    Article  Google Scholar 

  22. Mete M, Sirakov N (2010) Lesion detection in demoscopy images with novel density-based and active contour approaches. BMC Bioinformat 11(6). https://doi.org/10.1186/1471-2105-11-s6-s23

    Article  PubMed  PubMed Central  Google Scholar 

  23. Zhou H, Schaefer G, Celebi ME et al (2011) Gradient vector flow with mean shift for skin lesion segmentation. Comput Med Imaging Graph 35(2):121–127. https://doi.org/10.1016/j.compmedimag.2010.08.002

    Article  PubMed  Google Scholar 

  24. Barata C, Marques JS, Rozeira J (2012) A system for the detection of pigment network in dermoscopy images using directional filters. IEEE Trans Biomed Eng 59(10):2744–2754. https://doi.org/10.1109/tbme.2012.2209423

    Article  PubMed  Google Scholar 

  25. Piantanelli A, Maponi P, Scalise L et al (2005) Fractal characterisation of boundary irregularity in skin pigmented lesions. Med Biol Eng Compu 43(4):436–442. https://doi.org/10.1007/bf02344723

    Article  CAS  Google Scholar 

  26. Pathan S, Siddalingaswamy PC, Prabhu G (2017) Study of Melanocytic Nevi using image processing. 2017 2nd IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT). https://doi.org/10.1109/rteict.2017.8256618

  27. Liu Z-Q, Cai J, Buse R (2003) Handwriting recognition: soft computing and probabilistic approaches. Springer, Berlin

    Book  Google Scholar 

  28. Rakowska A (2009) Trichoscopy (hair and scalp videodermoscopy) in the healthy female. Method standardization and norms for measurable parameters. J Dermatol Case Rep 3(1):14. https://doi.org/10.3315/jdcr.2008.1021

    Article  PubMed  PubMed Central  Google Scholar 

  29. Chang C-I, Chen K, Wang J, Althouse ML (1994) A relative entropy-based approach to image thresholding. Pattern Recogn 27(9):1275–1289. https://doi.org/10.1016/0031-3203(94)90011-6

    Article  Google Scholar 

  30. Esedoglu S, Shen J (2002) Digital inpainting based on the Mumford–Shah–Euler image model. Europ J Appl Math 13(4):353–370. https://doi.org/10.1017/s0956792502004904

    Article  Google Scholar 

  31. Chan T, Vese L (2001) Active contours without edges. IEEE Trans Image Process 10:266–277. https://doi.org/10.1109/83.902291

    Article  CAS  PubMed  Google Scholar 

  32. Mendonca T, Ferreira PM, Marques JS, et al (2013) PH2—a dermoscopic image database for research and benchmarking. 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). https://doi.org/10.1109/embc.2013.6610779

  33. ISIC (2016) Skin lesion analysis towards melanoma detection. Available:https://challenge.kitware.com/#challenge/n/ISBI_2016%3A_Skin_Lesion_Analysis_Towards_Melanoma_Detection [Accessed: 24-Sep-2017]

  34. Kothari CR (2019) Research methodology: methods and techniques. New Age International (P) Limited, Publishers, New Delhi

    Google Scholar 

  35. Schoonjans F, Zalata A, Depuydt C, Comhaire F (1995) MedCalc: a new computer program for medical statistics. Comput Method Prog Biomed 48(3):257–262. https://doi.org/10.1016/0169-2607(95)01703-8

    Article  CAS  Google Scholar 

  36. Machin D, Campbell MJ, Tan SB, Tan SH (2018) Sample size tables for clinical studies. Wiley, Hoboken

    Google Scholar 

  37. Bozorgtabar B, Sedai S, Roy PK, Garnavi R (2017) Skin lesion segmentation using deep convolution networks guided by local unsupervised learning. IBM J Res Dev 61(4):1–8. https://doi.org/10.1147/jrd.2017.2708283

    Article  Google Scholar 

  38. Pennisi A, Bloisi DD, Nardi D et al (2016) Skin lesion image segmentation using Delaunay Triangulation for melanoma detection. Comput Med Imaging Graph 52:89–103. https://doi.org/10.1016/j.compmedimag.2016.05.002

    Article  PubMed  Google Scholar 

  39. Ahn E, Kim J, Bi L et al (2017) Saliency-based lesion segmentation via background detection in dermoscopic images. IEEE J. Biomed. Health Inf 21(6):1685–1693. https://doi.org/10.1109/jbhi.2017.2653179

    Article  Google Scholar 

  40. Fan H, Xie F, Li Y et al (2017) Automatic segmentation of dermoscopy images using saliency combined with Otsu threshold. Comput Biol Med 85:75–85. https://doi.org/10.1016/j.compbiomed.2017.03.025

    Article  PubMed  Google Scholar 

Download references

Acknowledgments

The authors thank Dr. Sathish Pai Ballambat, Professor and Head, Department of Dermatology, Venereology and Leprosy, Kasturba Medical College, Manipal for the expert guidance. The authors express their gratitude to Prof. Tanweer, REVA University Bangalore, for his extensive support and contribution in carrying out this research.

Author information

Authors and Affiliations

  1. Department of Computer Science and Engineering, Manipal Institute of Technology, MAHE, Manipal-576104, India

    Sameena Pathan & P. C. Siddalingaswamy

  2. Department of Electronics and Communication Engineering, Faculty of Engineering, Manipal University Jaipur, Manipal, India

    K. Gopalakrishna Prabhu

Authors
  1. Sameena Pathan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. K. Gopalakrishna Prabhu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. P. C. Siddalingaswamy
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to P. C. Siddalingaswamy.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Pathan, S., Prabhu, K. & Siddalingaswamy, P.C. Hair detection and lesion segmentation in dermoscopic images using domain knowledge. Med Biol Eng Comput 56, 2051–2065 (2018). https://doi.org/10.1007/s11517-018-1837-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-018-1837-9

Keywords

Search

Navigation