WN-based approach to melanoma diagnosis from dermoscopy images

A new computer-aided diagnosis (CAD) system for detecting malignant melanoma from dermoscopy images based on a fixed grid wavelet network (FGWN) is proposed. This novel approach is unique in at least three ways: (i) the FGWN is a fixed WN which does not require gradient-type algorithms for its construction, (ii) the construction of FGWN is based on a new regressor selection technique: D-optimality orthogonal matching pursuit (DOOMP), and (iii) the entire CAD system relies on the proposed FGWN. These characteristics enhance the integrity and reliability of the results obtained from different stages of automatic melanoma diagnosis. The DOOMP algorithm optimises the network model approximation ability rapidly while improving the model adequacy and robustness. This FGWN is then used to build a CAD system, which performs image enhancement, segmentation, and classification. To classify the images, in the first stage, 441 features with respect to colour, texture, and shape of each lesion are extracted. By means of feature selection, these 441 features are then reduced to 10. The proposed CAD system achieved an accuracy of 91.82%, sensitivity of 92.61%, specificity of 91%, and area under the curve value of 0.944 on a challenging set of 1039 dermoscopy images.

[1]  Johan Debayle,et al.  Texture descriptors based on adaptive neighborhoods for classification of pigmented skin lesions , 2015, J. Electronic Imaging.

[2]  Jing Huang,et al.  Image indexing using color correlograms , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[3]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[4]  Huan Liu,et al.  Feature Selection for High-Dimensional Data: A Fast Correlation-Based Filter Solution , 2003, ICML.

[5]  Huan Liu,et al.  Advancing Feature Selection Research − ASU Feature Selection Repository , 2010 .

[6]  Ke Huang,et al.  Wavelet Feature Selection for Image Classification , 2008, IEEE Transactions on Image Processing.

[7]  Stephen A. Billings,et al.  A new class of wavelet networks for nonlinear system identification , 2005, IEEE Transactions on Neural Networks.

[8]  Xia Hong,et al.  Nonlinear model structure design and construction using orthogonal least squares and D-optimality design , 2002, IEEE Trans. Neural Networks.

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

[10]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[12]  Qinghua Zhang,et al.  Using wavelet network in nonparametric estimation , 1997, IEEE Trans. Neural Networks.

[13]  Huan Liu,et al.  Chi2: feature selection and discretization of numeric attributes , 1995, Proceedings of 7th IEEE International Conference on Tools with Artificial Intelligence.

[14]  Xiang Li,et al.  A Query-by-Example Content-Based Image Retrieval System of Non-melanoma Skin Lesions , 2009, MCBR-CDS.

[15]  Niloofar Gheissari,et al.  Segmentation of Dermoscopy Images Using Wavelet Networks , 2013, IEEE Transactions on Biomedical Engineering.

[16]  Behzad Nazari,et al.  Wavelet Network Approach for Structural Damage Identification Using Guided Ultrasonic Waves , 2014, IEEE Transactions on Instrumentation and Measurement.

[17]  Johan Debayle,et al.  Automatic classification of skin lesions using color mathematical morphology-based texture descriptors , 2015, International Conference on Quality Control by Artificial Vision.

[18]  Daniel W. C. Ho,et al.  A basis selection algorithm for wavelet neural networks , 2002, Neurocomputing.

[19]  James Bailey,et al.  Computer-Aided Diagnosis of Melanoma Using Border- and Wavelet-Based Texture Analysis , 2012, IEEE Transactions on Information Technology in Biomedicine.

[20]  Xiang Li,et al.  Estimating the ground truth from multiple individual segmentations incorporating prior pattern analysis with application to skin lesion segmentation , 2011, 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[21]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[22]  M. Moraud.  Wavelet Networks , 2018, Foundations of Wavelet Networks and Applications.

[23]  Masafumi Hagiwara,et al.  Quantitative assessment of tumour extraction from dermoscopy images and evaluation of computer-based extraction methods for an automatic melanoma diagnostic system , 2006, Melanoma research.

[24]  Reda Kasmi,et al.  Classification of malignant melanoma and benign skin lesions: implementation of automatic ABCD rule , 2016, IET Image Process..

[25]  David I. McLean,et al.  Generalizing Common Tasks in Automated Skin Lesion Diagnosis , 2011, IEEE Transactions on Information Technology in Biomedicine.

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

[27]  Niloofar Gheissari,et al.  Impulse Noise Cancellation of Medical Images Using Wavelet Networks and Median Filters , 2012, Journal of medical signals and sensors.

[28]  Larry A. Rendell,et al.  A Practical Approach to Feature Selection , 1992, ML.