Independent Histogram Pursuit for Segmentation of Skin Lesions

In this paper, an unsupervised algorithm, called the Independent Histogram Pursuit (IHP), for segmenting dermatological lesions is proposed. The algorithm estimates a set of linear combinations of image bands that enhance different structures embedded in the image. In particular, the first estimated combination enhances the contrast of the lesion to facilitate its segmentation. Given an N-band image, this first combination corresponds to a line in N dimensions, such that the separation between the two main modes of the histogram obtained by projecting the pixels onto this line, is maximized. The remaining combinations are estimated in a similar way under the constraint of being orthogonal to those already computed. The performance of the algorithm is tested on five different dermatological datasets. The results obtained on these datasets indicate the robustness of the algorithm and its suitability to deal with different types of dermatological lesions. The boundary detection precision using k-means segmentation was close to 97%. The proposed algorithm can be easily combined with the majority of classification algorithms.

[1]  B. S. Manjunath,et al.  Unsupervised Segmentation of Color-Texture Regions in Images and Video , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Jianping Fan,et al.  Seeded region growing: an extensive and comparative study , 2005, Pattern Recognit. Lett..

[3]  Wilhelm Stolz,et al.  Color Atlas of Dermatoscopy , 1991 .

[4]  Harald Ganster,et al.  Automated Melanoma Recognition , 2001, IEEE Trans. Medical Imaging.

[5]  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.

[6]  J. Astola,et al.  Fundamentals of Nonlinear Digital Filtering , 1997 .

[7]  Pasi Fr.  Genetic algorithm with deterministic crossover for vector quantization , 2000 .

[8]  R. H. Moss,et al.  Neural network diagnosis of malignant melanoma from color images , 1994, IEEE Transactions on Biomedical Engineering.

[9]  T Lee,et al.  Dullrazor®: A software approach to hair removal from images , 1997, Comput. Biol. Medicine.

[10]  James R. Mansfield,et al.  Near-infrared spectroscopy for dermatological applications , 2002 .

[11]  Randy H. Moss,et al.  Automatic lesion boundary detection in dermoscopy images using gradient vector flow snakes , 2005, Skin research and technology : official journal of International Society for Bioengineering and the Skin (ISBS) [and] International Society for Digital Imaging of Skin (ISDIS) [and] International Society for Skin Imaging.

[12]  L. K. Hansen,et al.  A Probabilistic Neural Network Framework forDetection of Malignant , 1999 .

[13]  D.D. Gomez,et al.  Precise multi-spectral dermatological imaging , 2004, IEEE Symposium Conference Record Nuclear Science 2004..

[14]  Jerzy W. Grzymala-Busse,et al.  Data mining methods supporting diagnosis of melanoma , 2005, 18th IEEE Symposium on Computer-Based Medical Systems (CBMS'05).

[15]  Otto Braun-Falco.  Color Atlas of Dermatoscopy , 1994 .

[16]  Clement T. Yu,et al.  Segmentation of skin cancer images , 1999, Image Vis. Comput..

[17]  Ralph Braun,et al.  The performance of SolarScan: an automated dermoscopy image analysis instrument for the diagnosis of primary melanoma. , 2005, Archives of dermatology.

[18]  E. Oja,et al.  Independent Component Analysis , 2013 .

[19]  J. Cohen,et al.  Color Science: Concepts and Methods, Quantitative Data and Formulas , 1968 .

[20]  L. Joshua Leon,et al.  Watershed-Based Segmentation and Region Merging , 2000, Comput. Vis. Image Underst..

[21]  David Delgado-Gómez,et al.  Precise acquisition and unsupervised segmentation of multi-spectral images , 2007, Comput. Vis. Image Underst..

[22]  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.

[23]  M. Nischik,et al.  Analysis of skin erythema using true-color images , 1997, IEEE Transactions on Medical Imaging.

[24]  P. Schmid.  Segmentation of digitized dermatoscopic images by two-dimensional color clustering , 1999, IEEE Transactions on Medical Imaging.

[25]  Audra E. Kosh,et al.  Linear Algebra and its Applications , 1992 .

[26]  M. Emre Celebi,et al.  Unsupervised border detection of skin lesion images , 2005, International Conference on Information Technology: Coding and Computing (ITCC'05) - Volume II.

[27]  Ilias Maglogiannis.  Automated Segmentation and Registration of Dermatological Images , 2003, J. Math. Model. Algorithms.

[28]  Lars Kai Hansen,et al.  A Probabilistic Neural Network Framework for the Detection of Malignant Melanoma , 2001 .

[29]  David Delgado-Gómez,et al.  Collecting highly reproducible images to support dermatological medical diagnosis , 2006, Image Vis. Comput..

[30]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[31]  E. Claridge,et al.  Spectrophotometric intracutaneous analysis: a new technique for imaging pigmented skin lesions , 2002, The British journal of dermatology.