Applied Intelligence

, Volume 40, Issue 3, pp 415–426 | Cite as

Skin cancer extraction with optimum fuzzy thresholding technique

  • Howard Lee
  • Yi-Ping Phoebe ChenEmail author


This paper discusses a new approach to segment different types of skin cancers using fuzzy logic approach. The traditional skin cancer segmentation involves the analysis of image features to delineate the cancerous region from the normal skin. Using low level features such as colour and intensity, segmentation can be done by obtaining a threshold level to separate the two regions. Methods like Otsu optimisation provide a quick and simple process to optimise such threshold level; however this process is prone to the lighting and skin tone variations. Fuzzy clustering algorithm has also been widely used in image processing due to its ability to model the fuzziness of human visual perception. Classical fuzzy C means (FCM) clustering algorithm has been applied to image segmentation with good results; however, the classical FCM is based on type-1 fuzzy sets and is unable to handle uncertainties in the images. In this paper, we proposed an optimum threshold segmentation algorithm based on type-2 fuzzy sets algorithms to delineate the cancerous area from the skin images. By using the 3D colour constancy algorithm, the effect of colour changes and shadows due to skin tone variation in the image can be significantly reduced in the preprocessing stage. We applied the optimum thresholding technique to the preprocessed image over the RGB channels, and combined individual results to achieve the overall skin cancer segmentation. Compared to the Otsu algorithm, the proposed method is less affected by the shadows and skin tone variations. The results also showed more tolerance at the boundary of the cancerous area. Compared with the type-1 FCM algorithm, the proposed method significantly reduced the segmentation error at the normal skin regions.


Type-2 fuzzy theory Optimum threshold level Colour constancy matrix Skin cancer segmentation 


  1. 1.
    An J, Chen YPP (2008) Finding edging genes from microarray data. J Biotechnol 135(3):233–240 CrossRefGoogle Scholar
  2. 2.
    Aribarg T, Supratid S, Lursinsap C (2012) Optimizing the modified fuzzy ant-miner for efficient medical diagnosis. Appl Intell 37(3):357–376 CrossRefGoogle Scholar
  3. 3.
    Bergman R, Nachlieli H (2011) Perceptual segmentation: combine image segmentation with object tagging. IEEE Trans Image Process 20(6):1668–1681 CrossRefMathSciNetGoogle Scholar
  4. 4.
    Bezdek JC, Ehrlich R, Full W (1984) FCM: the fuzzy c-means clustering algorithm. Comput Geosci 10(2–3):191–203 CrossRefGoogle Scholar
  5. 5.
    Bustince H, Barrenechea E, Pagola M (2007) Image thresholding using restricted equivalence functions and maximizing the measures of similarity. Fuzzy Sets Syst 158(5) Google Scholar
  6. 6.
    Bustince H, Pagola M, Barrenechea E, Fernandez J, Melo-Pinto P, Couto P, Tizhoosh HR, Montero J (2010) Ignorance functions. An application to the calculation of the threshold in prostate ultrasound images. Fuzzy Sets Syst 161(1) Google Scholar
  7. 7.
    Campadelli P, Casiraghi E, Oratissoli S (2010) A segmentation framework for abdominal organs from CT scans. Artif Intell Med 50(1):3–11 CrossRefGoogle Scholar
  8. 8.
    Carrara M, Bono A, Bartolic (2007) Multispectral imaging and artificial neural network: mimicking the management decision of the clinician facing pigmented skin lesion. Phys Med Biol 149:2599–2613 CrossRefGoogle Scholar
  9. 9.
    Chen Y, Timms P, Chen YPP (2007) CIDB: chlamydia interactive database for cross-querying genomics, transcriptomics and proteomics data. Biomol Eng 24(6):603–608 CrossRefGoogle Scholar
  10. 10.
    Chuang KS, Tzeng HL, Chen S, Wu j, Chen TJ (2006) Fuzzy c-means clustering with spatial information for image segmentation. Comput Med Imaging Graph 30(1):9–15 CrossRefGoogle Scholar
  11. 11.
    Cruz-Roa A, Caicedo JC, Gonzalez FA (2011) Visual pattern mining in histology image collections using bag of features. Artif Intell Med 52(2):91–106 CrossRefGoogle Scholar
  12. 12.
    Cuevas E, Gonzalez M (2013) Multi-circle detection on images inspired y collective animal behavior. Appl Intell 30(1):101–120 CrossRefGoogle Scholar
  13. 13.
    D’Alessandro B, Dhawan AP (2012) 3-D volume reconstruction of skin lesions for melanin and blood volume estimation and lesion severity analysis. IEEE Trans Med Imaging 31(11):2083–2092 CrossRefGoogle Scholar
  14. 14.
    Dobrescu R, Dobrescu M, Mocanu S, Popescu D (2010) Medical image classification for skin cancer diagnosis based on combined texture and fractal analysis. WSEAS Trans Biol Biomed 7(3):223–232 Google Scholar
  15. 15.
    Garnavi R, Aldeen M, Celebi ME, Variqos G, Finch S Border detection in dermoscopy images using hybrid thresholding on optimised colour channels. Comput Med Imaging Graph 35(2):105–115 Google Scholar
  16. 16.
    Gonzales R, Woods R (2008) Digital image processing, 3rd edn. Pearson/ Prentice Hall, Upper Saddle River Google Scholar
  17. 17.
    Hosseini R, Qanadli SD, Barman S, Mazinani M, Ellis T, Dehmeshki J (2012) An automatic approach for learning and tuning Gaussian interval type-2 fuzzy membership functions applied to lung CAD classification system. IEEE Trans Fuzzy Syst 20(2):224–234 CrossRefGoogle Scholar
  18. 18.
    Hung W-L, Chen D-H, Yang M-S (2011) Suppressed fuzzy-soft learning vector quantization for MRI segmentation. Artif Intell Med 52(1):33–43 CrossRefGoogle Scholar
  19. 19.
    John RI, Coupland S (2007) Type-2 fuzzy logic: a historical view. IEEE Comput Intell 2(1):57–62 CrossRefGoogle Scholar
  20. 20.
    Kumar A, Kaur J (2012) Extract fuzzy optimal solution of fully fuzzy linear programming problems with unrestricted fuzzy variables. Appl Intell 37(1):145–154 CrossRefGoogle Scholar
  21. 21.
    Lopes NV, Couto PAM d., Bustince H, Melo-Pinto P (2010) Automatic histogram threshold using fuzzy measures. IEEE Trans Image Process 19(1) Google Scholar
  22. 22.
    Luac R, Plataniotis KN (2007) Color image processing–methods and application. Taylor and Francis, London Google Scholar
  23. 23.
    Mirghasemi S, Yazdi H, Lotfizad M (2012) A target-based color space for sea target detection 36(4):960–978 Google Scholar
  24. 24.
    Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern SMC-9(1) Google Scholar
  25. 25.
    Pagola M, Lopez-Molina C, Fernandez J, Barrenechea E, Bustince H (2011) Interval type-2 fuzzy sets constructed from several membership functions: application to the fuzzy thresholding algorithm. IEEE Trans Fuzzy Syst 99:1–15 Google Scholar
  26. 26.
    Ratnasingam S, Martin McGinnity T (2012) Chromaticity space for illuminant invariant recognition. IEEE Trans Image Process 21(8):3612–3623 CrossRefMathSciNetGoogle Scholar
  27. 27.
    Romero FP, Caballero I, Serrano-Guerrero J, Olivas JA (2012) An approach to web-based personal health records filtering using fuzzy prototypes and data quality criteria. Inf Process Manag 48(3) Google Scholar
  28. 28.
    Rong J, Li G, Chen YPP (2009) Acoustic feature selection for automatic emotion recognition from speech. Inf Process Manag 45(3):451–466 CrossRefGoogle Scholar
  29. 29.
    Saha S, Bandyopadhyay S (2011) Automatic MR brain image segmentation using a multiseed based multiobjecitve clustering approach 35(3):411–427 Google Scholar
  30. 30.
    Shi Y, Gao Y, Wang R, Zhang Y, Wang D (2013) Transductive cost-sensitive lung cancer image classification 38(1):16–28 Google Scholar
  31. 31.
    Sirakov NM, Mete M, Chakrader NS (2011) Automatic boundary detection and symmetry calculation in dermoscopy images of skin lesions. In: Proceedings on IEEE international conference on image processing, pp 1605–1608 Google Scholar
  32. 32.
    Son C (2013) Similarity measuring strategy of image patterns based on fuzzy entropy and energy variations in intelligent robot’s manipulative task. Appl Intell 38(2):131–145 CrossRefGoogle Scholar
  33. 33.
    Song XF, Chen WM, Chen YPP, Jiang B (2009) Candidate working set strategy based SMO algorithm in support vector machine. Inf Process Manag 45(5):584–592 CrossRefGoogle Scholar
  34. 34.
    Tang J, Guo S (2011) Segmentation of skin cancer using external force filtering snake based on wavelet diffusion. In: Multi Modality State-of-the-Art Medical Image Segmentation and Registration Methodologies. Springer, Berlin, pp 129–142 CrossRefGoogle Scholar
  35. 35.
    Umbaugh SE, Moss RH, Stoecker WV (1992) An automatic colour segmentation algorithm with application to identification of skin tumor borders. Comput Med Imaging Graph 16(3):227–238 CrossRefGoogle Scholar
  36. 36.
    Unnikrishnan R, Pantofaru C, Hebert M (2005) A measure for objective evaluation of image segmentation algorithms. In: CVPR workshop on computer vision applications, pp 394–400 Google Scholar
  37. 37.
    Wang H, Moss R, Chen X, Stanley R, Stoecker W, Celebi M, Malters J, Grichnik J, Marghoob A, Rabinovitz H, Menzies S, Szalapski T (2010) Modified watershed technique and post-processing for segmentation of skin lesions in dermoscopy images. Comput Med Imaging Graph 35:116–120 CrossRefGoogle Scholar
  38. 38.
    Wheless L, Black J, Alberg AJ (2010) Nonmelanoma skin cancer and the risk of second primary cancers: a systematic review. Cancer Epidemiol Biomark Prev 19:1686–1695 CrossRefGoogle Scholar
  39. 39.
    Wu J, Xiong H, Liu C, Chen J (2012) A generalization of distance functions for fuzzy c-means clustering with centroids of arithmetic means. IEEE Trans Fuzzy Syst, I 20(3):557–571 Google Scholar
  40. 40.
    Yaakob S, Jain L (2012) An insect classification analysis based on shape features using quality threshold ARTMAP and moment invariant. Appl Intell 37(1):12–30 CrossRefGoogle Scholar
  41. 41.
    Yang Y-B, Li Y-N, Pan L-Y, Li N, He G (2013) Image retrieval based on augmented relational graph representation. Appl Intell 38(4):489–501 CrossRefGoogle Scholar
  42. 42.
    Yeh CY, Jengm WHR, Lee S-J (2011) An enhanced type-reduction algorithm for type-2 fuzzy sets. IEEE Trans Fuzzy Syst 19(2):227–240 CrossRefGoogle Scholar
  43. 43.
    Yildirim MT, Basturk A, Yuksel ME (2008) Impulsive noise removal from digital images by a detail-preserving filter based on type-2 fuzzy logic. IEEE Trans Fuzzy Syst 16(4):920–928 CrossRefGoogle Scholar
  44. 44.
    Yuksel ME, 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 CrossRefGoogle Scholar
  45. 45.
    Zhou H, Schaefer G, Celebi ME, Lin F, Liu T (2011) Gradient vector flow with mean shift for skin lesion segmentation. Comput Med Imaging Graph 35(2):121–127 CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  1. 1.Department of Computer Science and Computer EngineeringLa Trobe University MelbourneBundooraAustralia

Personalised recommendations