Pattern analysis of dermoscopic images based on Markov random fields

被引：59

作者：

Serrano, Carmen ^{[1
]}

Acha, Begona ^{[1
]}

机构：

[1] Univ Seville, Escuela Super Ingn, Seville 41092, Spain

来源：

PATTERN RECOGNITION | 2009年 / 42卷 / 06期

关键词：

Dermoscopic images; Pattern classification; Markov random field; PIGMENTED SKIN-LESIONS; MALIGNANT-MELANOMA; COLOR; CLASSIFICATION; SEGMENTATION; DIAGNOSIS;

D O I：

10.1016/j.patcog.2008.07.011

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper a method for detecting different patterns in dermoscopic images is presented. In order to diagnose a possible skin cancer, physicians assess the lesion based on different rules. While the most famous one is the ABCD rule (asymmetry, border, colour, diameter), the new tendency in dermatology is to classify the lesion performing a pattern analysis. Due to the colour textured appearance of these patterns, this paper presents a novel method based on Markov random field (MRF) extended for colour images that classifies images representing different dermatologic patterns. First, each image plane in L*a*b* colour space is modelled as a MRF following a finite symmetric conditional model (FSCM). Coupling of colour components is taken into account by supposing that features of the MRF in the three colour planes follow a multivariate Normal distribution. Performance is analysed in different colour spaces. The best classification rate is 86% on average. (C) 2008 Elsevier Ltd. All rights reserved.

引用

页码：1052 / 1057

页数：6

共 30 条

[1]

[Anonymous], 2000, DIGITAL SIGNAL PROC

[2] Epiluminescence microscopy-based classification of pigmented skin lesions using computerized image analysis and an artificial neural network [J].

Binder, M ;

Kittler, H ;

Seeber, A ;

Steiner, A ;

Pehamberger, H ;

Wolff, K .

MELANOMA RESEARCH, 1998, 8 (03) :261-266

[3] Dermoscopy of pigmented skin lesions [J].

Braun, RP ;

Rabinovitz, HS ;

Oliviero, M ;

Kopf, AW ;

Saurat, JH .

JOURNAL OF THE AMERICAN ACADEMY OF DERMATOLOGY, 2005, 52 (01) :109-121

[4]

CHEN Y, 2004, IEEE P ICSP, V2, P1107

[5]

Duda R. O., 2000, Pattern classification

[6] Automatic lesion boundary detection in dermoscopy images using gradient vector flow snakes [J].

Erkol, B ;

Moss, RH ;

Stanley, RJ ;

Stoecker, WV ;

Hvatum, E .

SKIN RESEARCH AND TECHNOLOGY, 2005, 11 (01) :17-26

[7]

GAO J, 1998, IEEE INT C IMAGE PRO, V3, P823

[8] BOUNDARY DETECTION IN SKIN TUMOR IMAGES - AN OVERALL APPROACH AND A RADIAL SEARCH ALGORITHM [J].

GOLSTON, JE ;

MOSS, RH ;

STOECKER, WV .

PATTERN RECOGNITION, 1990, 23 (11) :1235-1247

[9] A new algorithm for border description of polarized light surface microscopic images of pigmented skin lesions [J].

Grana, C ;

Pellacani, G ;

Cucchiara, R ;

Seidenari, S .

IEEE TRANSACTIONS ON MEDICAL IMAGING, 2003, 22 (08) :959-964

[10] ESTIMATION AND CHOICE OF NEIGHBORS IN SPATIAL-INTERACTION MODELS OF IMAGES [J].

KASHYAP, RL ;

CHELLAPPA, R .

IEEE TRANSACTIONS ON INFORMATION THEORY, 1983, 29 (01) :60-72

← 1 2 3 →