Loading...

Automatic Skin Cancer (Melanoma) Detection Using Visual Features

Moazen, Hadi | 2019

1468 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 51581 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Jamzad, Mansour
  7. Abstract:
  8. Melanoma is a malignant skin cancer which is caused by cancerous growth of melanocytes. If not treated at its early development stages, melanoma is the deadliest form of cancer. The best way to cure melanoma is to treat it in its earliest stage of development. Since a melanoma leasion is similar to benign moles (regaring its shape and appearance) at its early stages of development, it is often mistaken for moles and left untreated. Therefore, automatic melanoma detection can increase the survival rate of patients by detecting melanoma in its early stages. In this thesis, a new method for automatic diagnosis of melanoma using segmented dermoscopic images is provided. Almost all related methods follow similar approach but using different features. We have introduced several new features inspired by the characteristics used by dermatologists for the diagnosis of melanoma, which could improve the accuracy of diagnosis. For evaluation we have implemented and tested the proposed method and previous methods on the ISIC archive, which is the largest openly available dataset of dermoscopic melanoma images. Our method outperforms the 52f method, which had the best accuracy among the most recent works. Our accuracy on the ISIC dataset increased by 1.5 percent and we achieved a 2.32 point higher F1 score while obtaining a comparable true positive rate as well
  9. Keywords:
  10. Skin Cancer ; Melanoma Cancer ; Automatic Melanoma Diagnosis ; Visual Feature ; Feature Extraction

 Digital Object List