Extraction of Skin Lesions from Non Dermoscopic Images Using Deep Learning

Authors(2) :-Sumaiyya Begum, Syeda Asra

Melanoma is among most forceful sorts of disease. In any case, it is exceptionally treatable if distinguished in its initial stages. Prescreening of skeptical blot and sores for threat is of awesome significance. Location should be possible by pictures caught by standard cameras, which are more best because of ease and accessibility. One critical stride in electronic assessment of skin sores is precise discovery of sore's locale, i.e. division of a picture into two districts as injury and typical skin. Precise division can be trying because of weights, for example, brightening variety and low difference amongst injury and sound skin. In this work, a technique in light of profound neural systems is proposed for precise extraction of an injury locale. The info picture is preprocessed and afterward its patches are encouraged to a convolutional neural system (CNN). The tracts are handled keeping in mind the end goal to allocate pixels to sore. A strategy for compelling choice of preparing tracts is utilized for more precise discovery of a sore's fringe. The yield division cover is refined by some post handling operations. The trial consequences of subjective and quantitative assessments exhibit that our technique can beat other best in class calculations exist in the writing.

Authors and Affiliations

Sumaiyya Begum
Department of Computer Science and Engineering, Kalaburagi, Karnataka, India
Syeda Asra
Associate Professor, Department of Computer Science and Engineering, Kalaburagi, Karnataka, India

Convolution Neural Networks, Medical Image Segmentation, Deep Learning, Melanoma, Skin Cancer

  1. H. Iyatomi, M. Celebi ,W. V. Stoecker, and G. Schaefer, "Injury outskirt location in dermoscopy pictures," Comput. Med. Imag. Diagram., vol. 33, no. 2, pp. 148-153, 2009.
  2. J. T. Johnson, A. F. Jerant, T. J. Caffrey and C. Sheridan, "Early discovery and treatment of skin malignancy," American family doctor, no. 2, pp. 357-386, 2000.
  3. M. H. Jafari, S. M. R. Soroushmehr, N. Karimi, S. Samavi K. Najarian, K. Ward, "Programmed Detection of Melanoma Using Broad Extraction of Features from Digital Images," 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Florida, 2016.
  4. E. Nasr-Esfahani, K. Ward, M. H. Jafari, S. M. R. Soroushmehr, N. Karimi, S. Samavi, K. Najarian, "Melanoma Detection by Analysis of Clinical Images Using Convolutional Neural Network," 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Florida, 2016.
  5. J. Glaister, "Programmed division of skin injuries from dermatological photos," M.S. theory, Dept. of Systems Design Engineering, University of Waterloo, Waterloo, Ontario, Canada, 2013.
  6. American Cancer Society, "Tumor Facts and Figures 2016," American Cancer Society, Atlanta, GA, USA, 2016.
  7. Skincancer.org, "Melanoma - SkinCancer.org," 2016. Online]. Accessible: http://www.skincancer.org/skin-growth data/skin-disease truths.
  8. F. Nachbar, W. Stolz, T. Merkle, A. B Cognetta, T. Vogt, M. Landthaler, P. Bilek, O. B.- Falco, and G. Plewig, "The abcd run of dermatoscopy: high planned an incentive in the conclusion of dubious melanocytic skin injuries," Journal of the American Academy of Dermatology, vol. 30, no. 4, pp. 551-559, 1994.
  9. G. Argenziano, G. Fabbrocini, P. Carli, V. De Giorgi, E. Sammarco, and M. Delfino,"Epiluminescence microscopy for the conclusion of suspicious melanocytic skin injuries: comp. of the abcd govern of dermatoscopy and another 7-point agenda in view of example investigation," Archives of Dermatology, vol. 134, no. 12, pp. 1563-1570, 1998.
  10. I. Maglogiannis and C. Doukas, "Diagram of cutting edge PC vision frameworks for skin injuries portrayal," IEEE Transactions on Information Technology in Biomedicine, vol. 13, no. 5, pp. 721-733, 2009.
  11. K. Korotkov and R. Garcia, "Automated investigation of pigmented skin sores: An audit," Artificial intel. in solution, pp. 69-90, 2012.
  12. R. Amelard, J. Glaister, A. Wong and D. A. Clausi, "Abnormal state Intuitive Features (HLIFs) for Intuitive Skin Lesion Description," IEEE Transactions on Biomedical Engineering, vol. 62, no. 3, pp. 820-831, 2015.
  13. H. C. Engasser and E. M. Warshaw, "Dermatoscopy use by US dermatologists: a cross-sectional study," J. Amer. Foundation Dermatol., vol. 63, no. 3, pp. 412-419, 2010.
  14. M. H. Jafari, S. Samavi, S. M. R. Soroushmehr, H. Mohaghegh, N. Karimi, K. Najarian, "Set of Descriptors for Skin Cancer Diagnosis Using Non-Dermoscopic Color Images," Image Processing (ICIP), 2016 IEEE International Conference on, Arizona, 2016.

Publication Details

Published in : Volume 2 | Issue 4 | July-August 2017
Date of Publication : 2017-08-31
License:  This work is licensed under a Creative Commons Attribution 4.0 International License.
Page(s) : 591-596
Manuscript Number : CSEIT1724124
Publisher : Technoscience Academy

ISSN : 2456-3307

Cite This Article :

Sumaiyya Begum, Syeda Asra, "Extraction of Skin Lesions from Non Dermoscopic Images Using Deep Learning", International Journal of Scientific Research in Computer Science, Engineering and Information Technology (IJSRCSEIT), ISSN : 2456-3307, Volume 2, Issue 4, pp.591-596, July-August-2017.
Journal URL : http://ijsrcseit.com/CSEIT1724124

Article Preview

Follow Us

Contact Us