Transactions on Machine Intelligence

Transactions on Machine Intelligence

Skin Cancer Detection from Dermoscopic Images with Emphasis on Shape, Color, and Texture Feature Extraction Using a Two-Stage Classification Algorithm

Document Type : Original Article

Authors
Gh. Shakourian 1
H. Montazery Kordy 2
1 MSc student, Department of Biomedical Engineering, Faculty of Electrical and Computer Engineering, Babol Noshirvani University of Technology, Babol, Iran
2 Assistant Professor, Department of Biomedical Engineering, Babol Noshirvani University of Technology, Babol, Iran
10.47176/TMI.2018.220
Abstract
Malignant melanoma is one of the most aggressive and life-threatening forms of skin cancer, with a high potential for metastasis if not diagnosed and treated early. The definitive treatment for melanoma is possible when it is accurately detected by a trained specialist in a timely manner. Early detection can lead to a simple excision of the tumor, which can often result in complete cure. However, current diagnostic procedures typically involve a biopsy of the lesion, an invasive and often painful procedure that can cause discomfort to the patient. Given these challenges, this study aims to develop a more efficient, non-invasive method for the early detection of melanoma, leveraging advanced machine learning and image processing techniques. The proposed method utilizes a set of features based on the shape, color, and texture of dermoscopic images, which are extracted to capture critical characteristics of the lesion. These features are then analyzed through a two-stage classification process, designed to categorize the lesion into one of three categories: common nevus, atypical nevus, and melanoma. The method was tested on the PH2 dataset, a well-known dermatological dataset containing images of skin lesions. Results demonstrate that the two-stage classification model achieved an accuracy of approximately 90%, significantly outperforming traditional single-stage classification models for multi-class lesion classification. This innovative approach holds promise for enhancing the accuracy of melanoma detection and reducing the need for invasive procedures, ultimately improving patient outcomes.
Keywords
Skin Cancer
Melanoma
Feature Extraction
Shape
Color
Texture
Classification
Optimal Features
KNN
[1]    American Cancer Society. (2017). Cancer facts and figures 2017. Retrieved from http://www.cancer.org/acs/groups/content/@editorial/documents/document/acspc048738.pdf. Accessed January 10, 2017.
[2]    Scheafer, G., Krawczyk, B., Celebi, M. E., & Iyatomi, H. (2014). An ensemble classification approach for melanoma diagnosis. Memetic Computing, 6(4), 233–240. https://doi.org/10.1007/s12293-014-0144-8
[3]    Xie, F., et al. (2017). Melanoma classification on dermoscopy images using a neural network ensemble model. IEEE Transactions on Medical Imaging, 36(3), 849–858. https://doi.org/10.1109/TMI.2016.2633551
[4]    Rastgoo, M., Garcia, R., Morel, O., & Marzani, F. (2015). Automatic differentiation of melanoma from dysplastic nevi. Computerized Medical Imaging and Graphics, 43, 44–52. https://doi.org/10.1016/j.compmedimag.2015.02.011
[5]    Kavitha, J. C., Suruliandi, A., & Nagarajan, D. (2017). Melanoma detection in dermoscopic images using global and local feature extraction. International Journal of Multimedia and Ubiquitous Engineering, 12(5), 19–28. https://doi.org/10.14257/ijmue.2017.12.5.02
[6]    Kavimathi, P. (2016). Comparative analyses of classifiers for diagnosis of skin cancer using dermoscopic images. Indian Journal of Science and Technology, 9(43). https://doi.org/10.17485/ijst/2016/v9i43/103824
[7]    AlAsadi, A. H. H., & AL-Safy, B. M. R. (2016). Early detection and classification of melanoma skin cancer. LAP LAMBERT Academic Publishing.
[8]    Celebi, M. E., Kingravi, H., Uddin, B., Iyatomi, H., Aslandogan, A., Stoecker, W. V., & Moss, R. H. (2007). A methodological approach to the classification of dermoscopy images. Computers in Medical Imaging and Graphics, 31(6), 362–373. https://doi.org/10.1016/j.compmedimag.2007.01.003
[9]    Fatih, M., Beigi, M. M., Fatih, M., & Mansouri, P. (2009). Melanoma detection using extraction of appropriate features from dermatoscopic images. Research Paper, Medical Lasers, 6(1).
[10]    Bhuiyan, M. A. H., Azad, I., & Uddin, M. K. (2013). Image processing for skin cancer features extraction. International Journal of Scientific & Engineering Research, 4(2), 1–6.
[11]    Gonzalez, R. C., & Woods, R. E. (2008). Digital image processing (2nd ed.). Prentice-Hall.
Transactions on Machine Intelligence
Volume 1, Issue 4
Autumn 2018
Pages 220-227

  • Receive Date 15 June 2018
  • Revise Date 27 August 2018
  • Accept Date 12 December 2018