PSO-SVM hybrid system for melanoma detection from histo-pathological images

This paper introduces an automated system for skin cancer (melanoma) detection from Histo-pathological images sampled from microscopic slides of skin biopsy. The proposed system is a hybrid system based on Particle Swarm Optimization and Support Vector Machine (PSO-SVM). The features used are extracted from the grayscale image histogram, the co-occurrence matrix and the energy of the wavelet coefficients resulting from the wavelet packet decomposition. The PSO-SVM system selects the best feature set and the best values for the SVM parameters (C and γ) that optimize the performance of the SVM classifier.   The system performance is tested on a real dataset obtained from the Southern Pathology Laboratory in Wollongong NSW, Australia. Evaluation results show a classification accuracy of 87.13%, a sensitivity of 94.1% and a specificity of 80.22%.The sensitivity and specificity results are comparable to those obtained by dermatologists.

[1]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[2]  Thierry Donadey,et al.  Boundary detection of black skin tumors using an adaptive radial-based approach , 2000, Medical Imaging: Image Processing.

[3]  W. Punch,et al.  Feature Extraction Using Genetic Algorithms , 1997 .

[4]  Adel Al-Jumaily,et al.  Automatic recognition of melanoma using Support Vector Machines: A study based on Wavelet, Curvelet and color features , 2014, 2014 International Conference on Industrial Automation, Information and Communications Technology.

[5]  R. Braun,et al.  Dermoscopy of pigmented lesions: a valuable tool in the diagnosis of melanoma. , 2004, Swiss medical weekly.

[6]  Adel Al-Jumaily,et al.  Hierarchical Parallel PSO-SVM Based Subject-Independent Sleep Apnea Classification , 2012, ICONIP.

[7]  Li-Yeh Chuang,et al.  Feature Selection using PSO-SVM , 2007, IMECS.

[8]  Xueying Zhang,et al.  Optimization of SVM Parameters Based on PSO Algorithm , 2009, 2009 Fifth International Conference on Natural Computation.

[9]  Bernhard Schölkopf,et al.  Kernel Methods in Computational Biology , 2005 .

[10]  M. Coory,et al.  Trends in melanoma mortality in Australia: 1950–2002 and their implications for melanoma control , 2005, Australian and New Zealand journal of public health.

[11]  Khairul Anam,et al.  SKKD No. 592/UN25.5.1/TU.3/2018 "Optimized Kernel Extreme Learning Machine for Myoelectric Pattern Recognition" , 2018 .

[12]  Cheng-Lung Huang,et al.  A distributed PSO-SVM hybrid system with feature selection and parameter optimization , 2008, Appl. Soft Comput..

[13]  Adel Al-Jumaily,et al.  A hybrid system for skin lesion detection: Based on gabor wavelet and support vector machine , 2015 .

[14]  B Terracini,et al.  Malignant mesothelioma of the pleura: interobserver variability. , 1995, Journal of clinical pathology.

[15]  O. R. Vincent,et al.  A Descriptive Algorithm for Sobel Image Edge Detection , 2009 .

[16]  Shih-Wei Lin,et al.  Particle swarm optimization for parameter determination and feature selection of support vector machines , 2008, Expert Syst. Appl..

[17]  Anil K. Jain,et al.  Object detection using gabor filters , 1997, Pattern Recognit..

[18]  Chunru Wan,et al.  Classification using support vector machines with graded resolution , 2005, 2005 IEEE International Conference on Granular Computing.

[19]  Qaisar Abbas,et al.  Lesion border detection in dermoscopy images using dynamic programming , 2011, 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.

[20]  M.Jayamanmadharao,et al.  Impulse Noise Removal from Digital Images- A Computational Hybrid Approach , 2013 .

[21]  Yen C. Chu.  Parallel Edge Detection , 1987, Other Conferences.

[22]  Abdesselam Bassou,et al.  Evaluation of the Medical Image Compression using Wavelet Packet Transform and SPIHT Coding , 2018 .

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

[24]  Adel Al-Jumaily,et al.  Self-advising support vector machine , 2013, Knowl. Based Syst..

[25]  Anil K. Jain,et al.  Address block location on envelopes using Gabor filters , 1992, Pattern Recognit..

[26]  Zne-Jung Lee,et al.  Parameter determination of support vector machine and feature selection using simulated annealing approach , 2008, Appl. Soft Comput..

[27]  Adel Al-Jumaily,et al.  Wavelet and Curvelet Analysis for Automatic Identification of Melanoma Based on Neural Network Classification , 2013 .

[28]  Madina Hamiane,et al.  SVM Classification of MRI Brain Images for Computer-Assisted Diagnosis , 2017 .

[29]  A. Al-Ani,et al.  Novel feature extraction method based on fuzzy entropy and wavelet packet transform for myoelectric Control , 2007, 2007 International Symposium on Communications and Information Technologies.

[30]  B. Yener,et al.  Automated cancer diagnosis based on histopathological images : a systematic survey , 2005 .

[31]  David Zhang,et al.  Dark line detection with line width extraction , 2008, 2008 15th IEEE International Conference on Image Processing.

[32]  Adel Al-Jumaily,et al.  Novel feature extraction methodology based on histopathalogical images and subsequent classification by support vector machine , 2014, 2014 World Symposium on Computer Applications & Research (WSCAR).

[33]  Patrick Pérez,et al.  Region filling and object removal by exemplar-based image inpainting , 2004, IEEE Transactions on Image Processing.

[34]  Anil K. Jain.  Fundamentals of Digital Image Processing , 2018, Control of Color Imaging Systems.

[35]  R. Newcombe,et al.  Observer variation in histopathological diagnosis and grading of cervical intraepithelial neoplasia. , 1989, BMJ.

[36]  Hua-chao Yang,et al.  Research into a Feature Selection Method for Hyperspectral Imagery Using PSO and SVM , 2007 .

[37]  Khairul Anam,et al.  Classification of Malignant Melanoma and Benign Nevi from Skin Lesions Based on Support Vector Machine , 2013, 2013 Fifth International Conference on Computational Intelligence, Modelling and Simulation.

[38]  John Sikorski.  Identification of Malignant Melanoma by Wavelet Analysis , 2004 .

[39]  Adel Al-Jumaily,et al.  The automatic identification of melanoma by wavelet and curvelet analysis: Study based on neural network classification , 2011, 2011 11th International Conference on Hybrid Intelligent Systems (HIS).