Pattern Analysis of Dermoscopic Images Based on FSCM Color Markov Random Fields Carlos S. Mendoza ⋆ , Carmen Serrano, and Bego˜ na Acha Universidad of Sevilla Av. de los Descubrimientos s/n 41092 Sevilla, Spain {csanchez1,cserrano,bacha}@us.es Abstract. In this paper a method for pattern analysis in dermoscopic images of abnormally pigmented skin (melanocytic lesions) is presented. In order to diagnose a possible skin cancer, physicians assess the lesion according to different rules. The new trend in Dermatology is to clas- sify the lesion by means of pattern irregularity. In order to analyze the pattern turbulence, lesions ought to be segmented into single pattern regions. Our classification method, when applied on overlapping lesion patches, provides a pattern chart that could ultimately allow for in-region single-texture turbulence analysis. Due to the color-textured appearance of these patterns, we present a novel method based on a Finite Sym- metric Conditional Model (FSCM) Markov Random Field (MRF) color extension for the characterization and discrimination of pattern samples. Our classification success rate rises to 86%. 1 Introduction In the last two decades a rising incidence of malignant melanoma has been observed. Because of a lack of adequate therapies for metastatic melanoma, the best treatment is still early diagnosis and prompt surgical excision of the primary cancer. Dermoscopy (also known as epiluminescence microscopy) is an in vivo method that has been reported to be a useful tool for the early recognition of malignant melanoma [1]. Its use increases diagnostic accuracy between 5 and 30% in clinical visual inspection [2]. Currently available digital dermoscopic systems offer the possibility of com- puter storage and retrieval of dermoscopic images. Some systems even display the potential for Computer Assisted Diagnosis (CAD) [3,4]. As diagnostic accuracy with dermoscopy has been shown to depend on the experience of the dermatolo- gist, CAD systems will help less-experienced dermatologists and provide a lower impact for inter-subject variability. ⋆ The authors would like to thank Dr. Amalia Serrano for providing and classifying dermatoscopic images used in this work, that has been funded by project FIS05-2028. Carlos S. Mendoza is also funded by a doctoral scholarship provided by Universidad de Sevilla. J. Blanc-Talon et al. (Eds.): ACIVS 2009, LNCS 5807, pp. 676–685, 2009. c  Springer-Verlag Berlin Heidelberg 2009