Skin lesion detection using fuzzy region growing and ABCD feature extraction for melanoma skin cancer diagnosis

Chastine Fatichah, Bilqis Amaliah, Muhammad Rahmat Widyanto

Research output: Contribution to conferencePaperpeer-review

Abstract

To improve accuracy of localize suspicious lesion region in dermatoscopic images using Region Growing, the initial step based on fuzzy sets to enhance the lesion region of interest (ROI) is developed. The result of skin lesion detection is used to extract Asymmetry, Border Irregularity, Color Variation, Diameter (ABCD) features for melanoma skin cancer diagnosis. ABCD feature is the rule that is used dermatologist for obtain the important information of image dermatoscopic lesion. This feature is used to diagnose melanoma skin cancer based on Total Dermatoscopic Value (TDV). There are three diagnosis that is used on this research i.e. melanoma, suspicious, and benign skin lesion. The experiment uses 30 samples of image dermatoscopic lesion that is suspicious melanoma skin cancer. Based on the experiment, the accuracy using fuzzy region growing is 86.6% that there are 4 false diagnoses of 30 samples. But the accuracy using region growing is 76.6% that there are 7 false of 30 samples.

Original languageEnglish
Publication statusPublished - 1 Dec 2009
EventInternational Workshop on Advanced Computational Intelligence and Intelligent Informatics, IWACIII 2009 - Tokyo, Japan
Duration: 7 Nov 20097 Nov 2009

Conference

ConferenceInternational Workshop on Advanced Computational Intelligence and Intelligent Informatics, IWACIII 2009
Country/TerritoryJapan
CityTokyo
Period7/11/097/11/09

Keywords

  • ABCD feature extraction
  • Fuzzy set
  • Malignant melanoma
  • Region growing
  • Skin lesion detection

Fingerprint

Dive into the research topics of 'Skin lesion detection using fuzzy region growing and ABCD feature extraction for melanoma skin cancer diagnosis'. Together they form a unique fingerprint.

Cite this