Learning methods for melanoma recognition

Melanoma is the most deadly skin cancer. Early diagnosis is a challenge for clinicians. Current algorithms for skin lesions' classification focus mostly on segmentation and feature extraction. This article instead puts the emphasis on the learning process, testing the recognition performance of three different classifiers: support vector machine (SVM), artificial neural network and k‐nearest neighbor. Extensive experiments were run on a database of more than 5000 dermoscopy images. The obtained results show that the SVM approach outperforms the other methods reaching an average recognition rate of 82.5% comparable with those obtained by skilled clinicians. If confirmed, our data suggest that this method may improve classification results of a computer‐assisted diagnosis of melanoma. © 2010 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 20, 316–322, 2010

[1]  P. Pattynama,et al.  Receiver operating characteristic (ROC) analysis: basic principles and applications in radiology. , 1998, European journal of radiology.

[2]  Randy H. Moss,et al.  A methodological approach to the classification of dermoscopy images , 2007, Comput. Medical Imaging Graph..

[3]  Patrick Haffner,et al.  Support vector machines for histogram-based image classification , 1999, IEEE Trans. Neural Networks.

[4]  Rita Cucchiara,et al.  A new algorithm for border description of polarized light surface microscopic images of pigmented skin lesions , 2003, IEEE Transactions on Medical Imaging.

[5]  Enrico Blanzieri,et al.  A multiple classifier system for early melanoma diagnosis , 2003, Artif. Intell. Medicine.

[6]  P. Barbini,et al.  Digital dermoscopy analysis and artificial neural network for the differentiation of clinically atypical pigmented skin lesions: a retrospective study. , 2002, The Journal of investigative dermatology.

[7]  Bernt Schiele,et al.  Recognition without Correspondence using Multidimensional Receptive Field Histograms , 2004, International Journal of Computer Vision.

[8]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.

[9]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[10]  W. Jaschke,et al.  Automated melanoma recognition , 2001, IEEE Transactions on Medical Imaging.

[11]  Ilias Maglogiannis,et al.  An integrated computer supported acquisition, handling, and characterization system for pigmented skin lesions in dermatological images , 2005, IEEE Transactions on Information Technology in Biomedicine.

[12]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[13]  Vapnik,et al.  SVMs for Histogram Based Image Classification , 1999 .

[14]  D. Rigel,et al.  Malignant melanoma: Prevention, early detection, and treatment in the 21st century , 2000, CA: a cancer journal for clinicians.

[15]  D. Signorini,et al.  Neural networks , 1995, The Lancet.

[16]  Philippe Schmid-Saugeona,et al.  Towards a computer-aided diagnosis system for pigmented skin lesions. , 2003, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[17]  Michael J. Swain,et al.  Color indexing , 1991, International Journal of Computer Vision.