Abstract
Two-dimensional asymmetry, border irregularity, colour variegation and diameter (ABCD) features are important indicators currently used for computer-assisted diagnosis of malignant melanoma (MM); however, they often prove to be insufficient to make a convincing diagnosis. Previous work has demonstrated that 3D skin surface normal features in the form of tilt and slant pattern disruptions are promising new features independent from the existing 2D ABCD features. This work investigates that whether improved lesion classification can be achieved by combining the 3D features with the 2D ABCD features. Experiments using a nonlinear support vector machine classifier show that many combinations of the 2D ABCD features and the 3D features can give substantially better classification accuracy than using (1) single features and (2) many combinations of the 2D ABCD features. The best 2D and 3D feature combination includes the overall 3D skin surface disruption, the asymmetry and all the three colour channel features. It gives an overall 87.8 % successful classification, which is better than the best single feature with 78.0 % and the best 2D feature combination with 83.1 %. These demonstrate that (1) the 3D features have additive values to improve the existing lesion classification and (2) combining the 3D feature with all the 2D features does not lead to the best lesion classification. The two ABCD features not selected by the best 2D and 3D combination, namely (1) the border feature and (2) the diameter feature, were also studied in separate experiments. It found that inclusion of either feature in the 2D and 3D combination can successfully classify 3 out of 4 lesion groups. The only one group not accurately classified by either feature can be classified satisfactorily by the other. In both cases, they have shown better classification performances than those without the 3D feature in the combinations. This further demonstrates that (1) the 3D feature can be used to improve the existing 2D-based diagnosis and (2) including the 3D feature with subsets of the 2D features can be used in distinguishing different benign lesion classes from MM. It is envisaged that classification performance may be further improved if different 2D and 3D feature subsets demonstrated in this study are used in different stages to target different benign lesion classes in future studies.
Similar content being viewed by others
References
Aribisala B, Claridge E (2005) A border irregularity measure using a modified conditional entropy method as a malignant melanoma predictor. In: International conference on image analysis and recognition, vol 3656, pp 914–921
Barata C, Figueiredo M, Celebi M, Marques J (2014) Color identification in dermoscopy images using gaussian mixture models. In: Proceedings of the IEEE international conference on acoustics, speech, and signal processing (ICASSP 2014), pp 3611–3615
Blum A, Luedtke H, Ellwanger U, Schwabe R, Rassner G, Garbe C (2004) Digital image analysis for diagnosis of cutaneous melanoma. Development of a highly effective computer algorithm based on analysis of 837 melanocytic lesions. Br J Dermatol 151(5):1029–1038
Burges C (1998) A tutorial on support vector machines for pattern recognition. Data Min Knowl Disc 2(2):121–167
Cancer Research UK (2015) CancerStats Key Facts—Skin Cancer. http://www.cancerresearchuk.org/cancer-info/cancerstats/keyfacts/skin-cancer/. Accessed 15 Jan 2015
Celebi M, Zornberg A (2014) Automated quantification of clinically significant colors in dermoscopy images and its application to skin lesion classification. IEEE Syst J 8(3):980–984
Celebi M, Kingravi H, Uddin B, Iyatomi H, Aslandogan Y, Stoecker W, Moss R (2007) A methodological approach to the classification of dermoscopy images. Comput Med Imaging Graph 31(6):362–373
Cheng Y, Swamisai R, Umbaugh S, Moss R, Stoecker W, Teegala S, Srinivasan S (2008) Skin lesion classification using relative color features. Skin Res Technol 14(1):53–64
Claridge E, Hall P, Keefe M, Allen J (1992) Shape analysis for classification of malignant melanoma. J Biomed Eng 14(3):229–234
Clawson K, Morrow P, Scotney B, McKenns D, Dolan O (2007) Computerised skin lesion surface analysis for pigment asymmetry quantification. In: International machine vision and image processing conference, pp 75–82
Clawson K, Morrow P, Scotney B, McKenns D, Dolan O (2007) Determination of optimal axes for skin lesion asymmetry quantification. In: IEEE international conference on image processing, vol 2, pp 453–456
D’Amico M, Ferri M, Stanganelli I (2004) Qualitative asymmetry measure for melanoma detection. In: IEEE international symposium on biomedical imaging: nano to macro, vol 2, pp 1155–1158
Demsar J (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learning Res 7:1–30
Ding Y, Smith L, Smith M, Warr R (2007) 3D skin texture analysis for early diagnosis for malignant melanoma. In: Proceedings of medical image understanding and analysis, pp 151–155
Ding Y, Smith L, Smith M, Sun J, Warr R (2008) Obtaining 3D malignant melanoma indicators through the analysis of skin tilt pattern and skin slant pattern. In: Proceedings of the MICCAI workshop on microscopic image analysis with application to biology (MIAAB)
Ding Y, Smith L, Smith M, Warr R, Sun J (2008) Enhancement of skin tilt pattern for lesion classification. In: IASTED conference on visualization, imaging and image processing, pp 1–6
Ding Y, Smith L, Smith M, Sun J, Warr R (2009) Obtaining malignant melanoma indicators through statistical analysis of 3D skin surface disruptions. Skin Res Technol 15(3):262–270
Ding Y, Smith L, Smith M, Sun J, Warr R (2010) A computer assisted diagnosis system for malignant melanoma using 3D skin surface texture features and artificial neural network. Int J Model Ident Control 90:370–381
Horn B (1986) Robot vision. MIT press, Cambridge
Iyatomi H, Oka H, Celebi M, Hashimoto M, Hagiwara M, Tanaka M, Ogawa K (2008) An improved internet-based melanoma screening system with dermatologist-like tumor area extraction algorithm. Comput Med Imaging Graph 32(7):566–579
Kuncheva L, Whitaker C (2003) Measures of diversity in classifier ensembles. Mach Learn 51:181–207
Lee T, McLean D, Atkins M (2003) Irregularity index: a new border irregularity measure for cutaneous melanocytic lesions. Med Image Anal 7(1):47–64
Mazzarello V, Soggiu D, Masia D, Ena P, Rubino C (2006) Melanoma versus dysplastic naevi: microtopographic skin study with noninvasive method. J Plast Reconstr Aesthet Surg 59(7):700–705
Menzies S, Bischof L, Talbot H, Gutenev A, Avramidis M, Wong L, Lo S, Mackellar G, Skladnev V, McCartny W, Kelly J, Cranney B, Lye P, Rabinovitz H, Oliviero M, Blum A, Varol A, De’Ambrosis B, McCleod R, Koga H, Grin C, Braun R, Johr R (2005) The performance of solarscan: an automated dermoscopy image analysis instrument for the diagnosis of primary melanoma. Arch Dermatol 141(11):1388–1396
Ng V, Benny Y, Fung M, Lee T (2005) Determining the asymmetry of skin lesion with fuzzy borders. Comput Biol Med 35(2):103–120
Pellacani G, Grana C, Seidenari S (2006) Algorithmic reproduction of asymmetry and border cut-off parameters according to the ABCD rule for dermoscopy. J Eur Acad Dermatol Venereol 20(10):1214–1219
Piantanelli A, Maponi P, Scalise L, Serresi S, Cialabrini A, Basso A (2005) Fractal characterisation of boundary irregularity in skin pigmented lesions. Med Biol Eng Compu 43(4):436–442
Rosado B, Menzies S, Herbauer A, Pehamberger H, Wolff K, Binder M, Kittler H, Corona R (2003) Accuracy of computer diagnosis of melanoma: a quantitative meta-analysis. Arch Dermatol 139(3):361–367
Rosenfeld A (1974) Compact figures in digital pictures. IEEE Trans Syst Man Cybern 4(2):221–223
Round A, Duller A, Fish P (2000) Lesion classification using skin patterning. Skin Res Technol 6(4):183–192
Sboner A, Eccher C, Blanzieri E, Bauer P, Cristofolini M, Zumiani G, Forti S (2003) A multiple classifier system for early melanoma diagnosis. Artif Intell Med 27(1):29–44
Stoecker W, Li W, Moss R (1992) Automatic detection of asymmetry in skin tumors. Comput Med Imaging Graph 16(3):191–197
Sun J, Smith M, Smith L, Coutts L, Dabis R, Harland C, Bamber J (2008) Reflectance of human skin using colour photometric stereo: with particular application to pigmented lesion analysis. Skin Res Technol 14(2):173–179
Sun J, Liu Z, Ding Y, Smith M (2014) Recovering skin reflectance and geometry for diagnosis of melanoma. In: Scharcanski J, Celebi ME (eds) Computer vision techniques for the diagnosis of skin cancer. Springer, Berlin, pp 243–265
Tsai D, Chao S (2005) An anisotropic diffusion-based defect detection for sputtered surfaces with inhomogeneous textures. Image Vis Comput 23(3):325–338
Umbaugh S, Moss R, Stoecker W (1989) Automatic color segmentation of images with application to detection of variegated coloring in skin tumors. IEEE Eng Med Biol Mag 8(4):43–50
Weickert J (1998) Anisotropic diffusion in image processing. Teubner, Stuttgart
Zhou Y, Smith M, Smith L, Farooq A, Warr R (2011) Enhanced 3D curvature pattern and melanoma diagnosis. Comput Med Imaging Graph 35(2):155–165
Acknowledgments
The authors would like to acknowledge the support of Pigmented Lesion clinic, North Bristol NHS Trust, Bristol (UK) and Royal Marsden NHS trust, Surrey (UK) for clinical trials using the Skin Analyser. The first author would like to thank Prof. Kuncheva for several interesting talks she and her students have given on applications of ensemble classifiers. The authors are also very thankful of the anonymous reviewers’ comments on improving this paper.
Author information
Authors and Affiliations
Corresponding author
Appendix 1: Locating a lesion’s centre of mass and principal axis using moment
Appendix 1: Locating a lesion’s centre of mass and principal axis using moment
The moment of order (p + q) for an M × N digital image is given by
The centralised moments are given by
where (m c, n c) is the centre of the mass, which is defined as
and S(m, n) is a binary image generated as
where S l denotes the lesion region. Then, the direction of the principle axis of a lesion is given by
Rights and permissions
About this article
Cite this article
Ding, Y., John, N.W., Smith, L. et al. Combination of 3D skin surface texture features and 2D ABCD features for improved melanoma diagnosis. Med Biol Eng Comput 53, 961–974 (2015). https://doi.org/10.1007/s11517-015-1281-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11517-015-1281-z