TY - JOUR ID - TI - Skin Cancer Prognosis Based on Color Matching and Segmentation of Pigmented Skin Lesion ألتنبؤ بسرطان ألجلد بالاعتماد على ألتقطیع ومطابقة أللون لصبغة ألورم AU - Muthana H. Hamd AU - Laith M. Mohamad PY - 2013 VL - 31 IS - 12 Part (A) Engineering SP - 2343 EP - 2356 JO - Engineering and Technology Journal مجلة الهندسة والتكنولوجيا SN - 16816900 24120758 AB - This work develops a new computerized vision of skin cancer diagnosis based oncolor matching of pigmented skin lesion and some parameters of ABCD method.Initially, the clinical diagnostic criteria have been translated to mathematicalconcepts. So the lesion edge detection; symmetry; even-symmetry; and segmentationare computed. Then, the suspicious images would be classified into one of threecategories: benign (mole), malignant (melanoma/non-melanoma), or unknown tumorusing image profile information. The remaining malignant images (melanoma, BasalCell Carcinoma, or Squamous Cell Carcinoma) would be further classified usingmatching procedure for color spectrums (Red, Yellow, Brown, Black/Gray) withlesion pigment. The lesion image is segmented into four quarters and the matchingprocedure of 120 spectrums is started searching for better result with mean squarederror less than 0.003. The software has been tested over 40 classified images and itsuccessfully re-classified 92%. This result could be improved if lesion quarters and/orspectrums are increased.

ER -