Computer-Aided Diagnosis of Melanoma Using Border- and Wavelet-Based Texture Analysis

被引:127
作者
Garnavi, Rahil [1 ]
Aldeen, Mohammad
Bailey, James [2 ]
机构
[1] Univ Melbourne, Dept Elect & Elect Engn, NICTA Victoria Res Lab, Melbourne, Vic 3010, Australia
[2] Univ Melbourne, Dept Comp & Informat Syst, NICTA Victoria Res Lab, Melbourne, Vic 3010, Australia
来源
IEEE TRANSACTIONS ON INFORMATION TECHNOLOGY IN BIOMEDICINE | 2012年 / 16卷 / 06期
关键词
Classification; computer-aided diagnosis of melanoma; dermoscopy; feature extraction; wavelet; PIGMENTED SKIN-LESIONS; FEATURE-SELECTION; EPILUMINESCENCE MICROSCOPY; DIGITAL DERMOSCOPY; CLASSIFICATION; ASYMMETRY; PATTERN; FEATURES; COLOR;
D O I
10.1109/TITB.2012.2212282
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This paper presents a novel computer-aided diagnosis system for melanoma. The novelty lies in the optimized selection and integration of features derived from textural, border-based, and geometrical properties of the melanoma lesion. The texture features are derived from using wavelet-decomposition, the border features are derived from constructing a boundary-series model of the lesion border and analyzing it in spatial and frequency domains, and the geometry features are derived from shape indexes. The optimized selection of features is achieved by using the gain-ratio method, which is shown to be computationally efficient for melanoma diagnosis application. Classification is done through the use of four classifiers; namely, support vector machine, random forest, logistic model tree, and hidden naive Bayes. The proposed diagnostic system is applied on a set of 289 dermoscopy images (114 malignant, 175 benign) partitioned into train, validation, and test image sets. The system achieves an accuracy of 91.26% and area under curve value of 0.937, when 23 features are used. Other important findings include 1) the clear advantage gained in complementing texture with border and geometry features, compared to using texture information only, and 2) higher contribution of texture features than border-based features in the optimized feature set.
引用
收藏
页码:1239 / 1252
页数:14
相关论文
共 56 条
[1]  
[Anonymous], 2010, Int J Med Med Sci
[2]  
[Anonymous], 2009, AUSTR SKIN CANC FACT
[3]  
[Anonymous], 1998, Ph.D. Thesis
[4]   Epiluminescence microscopy for the diagnosis of doubtful melanocytic skin lesions - Comparison of the ABCD rule of dermatoscopy and a new 7-Point checklist based on pattern analysis [J].
Argenziano, G ;
Fabbrocini, G ;
Carli, P ;
De Giorgi, V ;
Sammarco, E ;
Delfino, M .
ARCHIVES OF DERMATOLOGY, 1998, 134 (12) :1563-1570
[5]   Dermoscopy of pigmented skin lesions:: Results of a consensus meeting via the Internet [J].
Argenziano, G ;
Soyer, HP ;
Chimenti, S ;
Talamini, R ;
Corona, R ;
Sera, F ;
Binder, M ;
Cerroni, L ;
De Rosa, G ;
Ferrara, G ;
Hofmann-Wellenhof, R ;
Landthater, M ;
Menzies, SW ;
Pehamberger, H ;
Piccolo, D ;
Rabinovitz, HS ;
Schiffner, R ;
Staibano, S ;
Stolz, W ;
Bartenjev, I ;
Blum, A ;
Braun, R ;
Cabo, H ;
Carli, P ;
De Giorgi, V ;
Fleming, MG ;
Grichnik, JM ;
Grin, CM ;
Halpern, AC ;
Johr, R ;
Katz, B ;
Kenet, RO ;
Kittler, H ;
Kreusch, J ;
Malvehy, J ;
Mazzocchetti, G ;
Oliviero, M ;
Özdemir, F ;
Peris, K ;
Perotti, R ;
Perusquia, A ;
Pizzichetta, MA ;
Puig, S ;
Rao, B ;
Rubegni, P ;
Saida, T ;
Scalvenzi, M ;
Seidenari, S ;
Stanganelli, I ;
Tanaka, M .
JOURNAL OF THE AMERICAN ACADEMY OF DERMATOLOGY, 2003, 48 (05) :679-693
[6]   Evaluation of digital dermoscopy in a pigmented lesion clinic: Clinician versus computer assessment of malignancy risk [J].
Boldrick, Jennifer C. ;
Layton, Christle J. ;
Nguyen, Josephine ;
Swetter, Susan M. .
JOURNAL OF THE AMERICAN ACADEMY OF DERMATOLOGY, 2007, 56 (03) :417-421
[7]  
Bono A, 1999, CANCER, V85, P72, DOI 10.1002/(SICI)1097-0142(19990101)85:1<72::AID-CNCR10>3.0.CO
[8]  
2-Q
[9]   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
[10]   Random forests [J].
Breiman, L .
MACHINE LEARNING, 2001, 45 (01) :5-32