Robust skin diseases detection and classification using deep neural networks

 
 
 
  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract


    Since from last decade, there is significant growth in the design of Computer-Aided Diagnosis (CAD) Systems using image processing. There are different images processing steps on which the efficiency of such CAD systems relies such as image pre-processing, image segmentation, feature extraction, and classification. There are recent attempts by proposing novel algorithms in either of CAD model steps, however designing robust, useful and accurate CAD system for skin diseases' detection is still challenging research problem. In this paper, unique skin disease identification was proposed for three types of skin diseases such as Melanoma, Nevus, and Atypical. For pre-processing, an adaptive filtering method was designed to remove unwanted noisy areas from the input skin image. For segmentation, adaptive region growing technique was developed for efficient localization and region of interest (ROI) extraction of disease area. This segmentation adaptively selects the next region to grow for accurate lesion segmentation. For feature extraction, we exploited a hybrid feature extraction method composed of 2dimensions discrete wavelet transform (2D-DWT), geometric and texture features. The deep learning algorithm performs the classification. Convolutional neural networks (CNN) is used for the efficient prediction of skin disease. The experimental analysis is performed usingInternational Skin Imaging Collaboration (ISIC) dataset. The proposed method can classification the skin diseases with accuracy of 96.768%. The results obtained showing that the proposed method outperformed the state-of-art techniques.

     


  • Keywords


    Lesions; Skin Disease; CAD; Segmentation; Deep Learning; Melanoma; Nevus.

  • References


      [1] Lieber CA, Majumder SK, Billheimer DD, Ellis DJ, Mahadevan Jansen A.Raman microspectroscopy for skin cancer detection in vitro. J Biomed Opt 2008; 13(2):024013. https://doi.org/10.1117/1.2899155.

      [2] J. Glaister, A. Wong, and D. A. Clausi, "Segmentation of Skin Lesions from Digital Images Using Joint Statistical Texture Distinctiveness," IEEE Trans. Biomed. Eng., vol. 61, no. 4, pp. 1220–1231, Apr. 2014. https://www.skincancer.org/skin-cancer-information/melanoma/melanoma-prevention-guidelines. M. E. Celebi, H. A. Kingravi, H. Iyatomi, Y. A. Aslandogan, W. V. Stoecker, R. H. Moss, J. M. Malters, J. M. Grichnik, A. A. Marghoob, H. S. Rabinovitz, and S. W. Menzies, “Border detection in dermoscopy images using statistical region merging,” Skin Res. Technol., vol. 14, no. 3, pp. 347–353, 2008. https://doi.org/10.1111/j.1600-0846.2008.00301.x.

      [3] J. Glaister, A. Wong, and D. A. Clausi, “Automatic Skin Lesion Segmentation via Iterative Stochastic Region Merging," IEEE Trans. Biomed. Eng.,vol15,No.6,Nov 2011 https://doi.org/10.1109/TITB.2011.2157829.

      [4] M. Silveira, J. Nascimento, J. Marques, A. R. S. Marcal, T. Mendonca, S. Yamauchi, J. Maeda, and J. Rozeira, "Comparison of segmentation methods for melanoma diagnosis in dermoscopy images," Selected Topics in Signal Processing, IEEE Journal of, vol. 3, no. 1, pp. 35-45, 2009 https://doi.org/10.1109/JSTSP.2008.2011119.

      [5] G.Schaefer, M. Rajab, M. Emre Celebi, and Hitoshi Iyatomi, "Skin lesion extraction in dermoscopic images based on color enhancement and iterative segmentation, "ICIP, IEEE Journal,pp.3361-3364,2009 https://doi.org/10.1109/ICIP.2009.5413891.

      [6] J.Humayun, A.S.Malik, N.Kamel, "Multilevel thresholding for segmentation of pigmented skin lesions, " IEEE Int. Conf. Imaging Systems and Techniques, pp. 310-314, May. 2011 https://doi.org/10.1109/IST.2011.5962214.

      [7] H. S. Ganzeli, J. G. Bottesini, L. O. Paz and M. F. S. Ribeiro,” SKAN: Skin Scanner – System for Skin Cancer Detection Using Adaptive Techniques” IEEE LATIN AMERICA TRANSACTIONS, VOL. 9, NO. 2, APRIL 2011. https://doi.org/10.1109/TLA.2011.5765575.

      [8] M. Shamsul Arifini, M. Golam Kibria, Adnan Firoze" M. Ashraful Amini, Hong Yan," Dermatological Disease Diagnosis Using Colour-Skin Images" Proceedings of the 2012 International Conference on Machine Learning and Cybernetics, Xian, 15-17 July 2012. https://doi.org/10.1109/ICMLC.2012.6359626.

      [9] Catarina Barata, Margarida Ruela, Mariana Francisco, Teresa Mendonça, and Jorge S. Marques,” Two Systems for the Detection of Melanomas in Dermoscopy Images Using Texture and Colour Features” IEEE SYSTEMS JOURNAL 2013. https://doi.org/10.1109/JSYST.2013.2271540.

      [10] Rahat Yasir, Md. Ashiqur Rahman, and Nova Ahmed, "Dermatological Disease Detection using Image Processing and Artificial Neural Network" 8th International Conference on Electrical and Computer Engineering 20-22 December 2014, Dhaka, Bangladesh. https://doi.org/10.1109/ICECE.2014.7026918.

      [11] Naser Alfred, Fouad Khelifi, Member, IEEE, Ahmed Bouridane, Senior Member, IEEE, and Huseyin Seker, "Pigment network-based skin cancer detection" 2015 IEEE. https://doi.org/10.1109/EMBC.2015.7320056.

      [12] Adheena Santy, Robin Joseph,” Segmentation Methods for Computer Aided Melanoma Detection” Proceedings of 2015 Global Conference on Communication Technologies (GCCT 2015). https://doi.org/10.1109/GCCT.2015.7342710.

      [13] Sumithra Ra, Mahamad Suhilb, D.S.Guruc,” Segmentation and Classification of Skin Lesions for Disease Diagnosis”, International Conference on Advanced Computing Technologies and Applications (ICACTA-2015). https://doi.org/10.1016/j.procs.2015.03.090.

      [14] Shivangi Jain, Vandana jagtap, Nitin Pisea,” Computer aided Melanoma skin cancer detection using Image Processing” International Conference on Intelligent Computing, Communication & Convergence (ICCC-2014).

      [15] Palak Mehta, Bhumika Shah,” Review on Techniques and Steps of Computer Aided Skin Cancer Diagnosis” International Conference on Computational Modeling and Security (CMS 2016). https://doi.org/10.1016/j.procs.2016.05.238.

      [16] Supriya Joseph, Janu R Panicker,” Skin Lesion Analysis System for Melanoma Detection with an Effective Hair Segmentation Method” 2016 IEEE. https://doi.org/10.1109/INFOSCI.2016.7845307.

      [17] Vinayshekhar Bannihatti Kumar, Sujay S Kumar, Varun Saboo, "Dermatological Disease Detection Using Image Processing and Machine Learning" ISBN: 978-1-4673-9187-0 ©2016 IEEE 88.

      [18] Suganya R, "An Automated Computer Aided Diagnosis of Skin Lesions Detection and Classification for Dermoscopy Images" 2016 Fifth International Conference on Recent Trends in Information Technology. https://doi.org/10.1109/ICRTIT.2016.7569538.

      [19] Teck Yan Tan, Li Zhang, and Ming Jiang," An Intelligent Decision Support System for Skin Cancer Detection from Dermoscopic Images" 2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD).

      [20] Pradeep Mullangi, Y. Srinivasa Rao and Pushpa Kotipalli,” Texture and Clustering-based Skin Disease Classification”.2015.

      [21] Nishtha Garg, Vishakha Sharma, and Prabhjot Kaur," Melanoma Skin Cancer Detection Using Image Processing"2014.

      [22] S. Albawi, T. A. MOHAMMED, and S. Al-azawi, "Understanding of a Convolutional Neural Network," in 2017 International Conference on Engineering & Technology (ICET’2017), Akdeniz University, Antalya, Turkey, 2017, pp. 274-279. https://doi.org/10.1109/ICEngTechnol.2017.8308186.

      [23] https://ww2.mathworks.cn/en/solutions/deep-learning/models.html.

      [24] https://www.isic-archive.com/#!/topWithHeader/tightContentTop/about/isicArchive.


 

View

Download

Article ID: 24178
 
DOI: 10.14419/ijet.v7i4.24178




Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.