An Image Processing and Genetic Algorithm-based Approach for the Detection of Melanoma in Patients

Summary

Melanoma skin cancer is the most aggressive type of skin cancer. It is most commonly caused by excessive exposure to Ultraviolet radiation which triggers uncontrollable proliferation of melanocytes. Early detection makes melanoma relatively easily curable. Diagnosis is usually done using traditional methods such as dermoscopy which consists of a manual examination performed by the physician. However, these methods are not always well founded because they depend heavily on the physician’s experience. Hence, there is a great need for a new automated approach in order to make diagnosis more reliable. In this paper, we present a twophase technique to classify images of lesions into benign or malignant. The first phase consists of an image processing-based method that extracts the Asymmetry, Border Irregularity, Color Variation and Diameter of a given mole. The second phase classifies lesions using a Genetic Algorithm. Our technique shows a significant improvement over other well-known algorithms and proves to be more stable on both training and testing data.

Keywords

Genetic algorithms - melanoma - disease prediction - machine learning - classification - cancer - image processing

• References

• 1 American Cancer Society. What is melanoma skin cancer? [Online].; 2016 [cited 2016 January 6. Available from: http://www.cancer.org/cancer/skincancer-melanoma/detailedguide/melanomaskin-cancer-what-is-melanoma
• 2 Miller A, Mihm M. Melanoma. New England Journal of Medicine 2006; 355 (01) 51-65.
• 3 Iyatomi H. Computer-based diagnosis of pigmented skin lesions. New Developments in Biomedical Engineering. 2010
• 4 Friedman R, Rigel D, Kopf A. Early detection of malignant melanoma: The role of physician examination and self examination of the skin. CA: a Cancer Journal for Clinicians 1985; 35 (03) 130-151.
• 5 Abbasi N, Shaw H, Rigel D, Friedman R, McCarthy W, Osman I. et al. Early diagnosis of cutaneous melanoma: revisiting the ABCD criteria. The Journal of Amercican Medical Association 2004; 292 (22) 2771-2776.
• 6 Jain S, Pise N. Computer aided melanoma skin cancer detection using image processing. Procedia Computer Science 2015; 48: 735-740.
• 7 Bhardwaj A, Bhatia J. An image segmentation method for early detection and analysis of melanoma. IOSR Journal of Dental and Medical Sciences 2014; 13 (10) 18-22.
• 8 Sheha M, Mabrouk M, Sharawy A. Automatic detection of melanoma skin cancer using texture analysis. International Journal of Computer Applications 2012; 42 (20) 22-26.
• 9 Lee T. Measuring border irregularity and shape of cutaneous melanocytic lesions. 2001. Doctoral dissertation: Simon Fraser University;
• 10 Amerald R, Wong A, Clausi D. Extracting morphological high-level intuitive features (HLIF) for enhancing skin lesion classification. In Engineering in Medicine and Biology Society (EMBC), 2012 Annual International Conference of the IEEE 2012 Aug 28: IEEE. 4458-4461.
• 11 Glaister J, Amerald R, Wong A, Clausi D. MSIM: Multistage illumination modeling of dermatological photographs for illumination-corrected skin lesion analysis. IEEE Transactions on Biomedical Engineering 2013; 60 (07) 1873-1883.
• 12 Amerald R, Wong A, Clausi D. Extracting highlevel intuitive features (HLIF) for classifying skin lesions using standard camera images. In Computer and Robot Vision (CRV), 2012 Ninth Conference; 2012 May 28. Toronto: IEEE; 396-403.
• 13 Amerald R, Glaister J, Wong A, Clausi D. Highlevel intuitive features (HLIFs) for intuitive skin lesion description. IEEE Transactions on Biomedical Engineering 2014; 62 (03) 820-831.
• 14 Abdul JJaleel, Sibi S, Aswin R. Diagnosis and detection of skin cancer using artificial intelligence. International Journal of Engineering and Innovative Technology 2013; 03 (02) 311-315.
• 15 Moussa R, Gerges F, Salem C, Akiki R, Falou O, Azar D. Computer-aided detection of Melanoma using geometric features. In Biomedical Engineering (MECBME), 2016 3rd Middle East Conference; 2016 Oct 6. Beirut: IEEE; 125–128
• 16 Cheerla N, Frazier D. Automatic melanoma detection using multi-stage neural networks. International Journal of Innovative Research in Science, Engineering and Technology. 2014 Feb 03. 02
• 17 Chang Y, Stanley RJ, Moss RH, Stoecker WV. A systematic heuristic approach for feature selection for melanoma discrimination using clinical images. Skin Research and Technology 2005; 11 (03) 165-178.
• 18 Quinlan J. C4.5: programs for machine learning California. Morgan Kaufmann Publishers; 1993
• 19 Bouktif S, Hanna E, Zaki N, Abu EKhousa. Ant Colony Optimization Algorithm for Interpretable Bayesian Classifiers Combination: Application to Medical Predictions. PloS one 2014; 09 (02) 1-15.