Melanoma Detection using Machine Learning

  • Alisha Loy
  • Aysha Thankayathil
  • Nimmy Baby
  • Melvin Thomas

Abstract

Melanoma being the deadliest form of cancer, if detected at an early stage can be completely cured. Most of the skin cancer detection methods are painful. Our project aims at non-invasive technique to detect skin cancer at an early stage. Initially the dermatoscopic images are pre-processed and segmented. Once segmentation is done, features such as Asymmetry, Border Irregularity, Colour and Diameter are extracted and a score is assigned. Based on the score, a TDS (Total Dermatoscopic Score) is calculated. This TDS score and extracted features are used to train the SVM (Support Vector Machine) and test images are given to SVM. It classifies the image as cancerous and non-cancerous.

Keywords: Asymmetry, Border irregularity, Colour, Diameter, Melanoma, Support Vector Machine, Total Dermatoscopic Score.

References

[1] L. Xu, M. Jackowski, A Goshtasby, D. Roseman, S. Bines, C. Yu, A. Dhawan and A. Huntely, “Segmentation of Skin cancer images,” Image and Vision Computing 17 (1999)65-74.
[2] Sumithra R, MahamadSuhil and D. S Guru “Segemntation and Classification of Skin Lesions for Disease Diagnosis,” International Conference on Advanced Computing Technologies and Applications (ICACTA), Procedia Computer Science 45(2015)76-85.
[3] Nidhal K. EL Abbadi and Zahraa Faisal, “Detection and Analysis of Skin Cancer from Skin Lesions,” International Journal of Applied Engineering Research ISSN 0973-4562 vol. 12, Number 19 (2017) pp.9046-9052.

[4] NayanaBanjan, Prajkta Dalvi and Neha Athavale “Melanoma Skin Cancer by Segmentation and Feature Extraction using Combination of OTSU and STOLZ Algorithm Technique,” SSRG International JournalofElectronicsandCommunicationEngineering,vol.4issue
.4, pp. 21- 25, April 2017
[5] Siddiq Iqbal, Divyashree.J.A, Sophia.M, MallikarjunMundas and Vidya.R “Implementation of Stolz’s Algorithm for Melanoma Detection,” International Advanced Research Journal in Science, Engineering and Technology (IARJSET), vol. 2, Issue 6, June2015.
[6] Nilkamal S. Ramteke, and Shwetha V. Jain, “ABCD rule based automatic computer -aided skin cancer detection using MATLAB,” Int.J.Computer Technology and Applications (IJCTA), vol. 4 (4), 691-697.
Statistics
0 Views | Downloads
How to Cite
Loy, A., Thankayathil, A., Baby, N., & Thomas, M. (2019). Melanoma Detection using Machine Learning. Asian Journal For Convergence In Technology (AJCT), 5(2). Retrieved from http://www.asianssr.org/index.php/ajct/article/view/876