• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.1
• /
• pp.425-429
• /
• 2016

Background: Dermatoscopy can be applied to diagnose pigmented skin lesions. The aim of the present study was to compare dermatoscopic and histopathologic results in basal cell carcinoma (BCC) and melanocytic nevus of theface. Materials and Methods: In an analytical-descriptive study, 61 patients suspected of BCC or melanocytic nevi of face were randomly selected. The skin lesions of patients were evaluated with dermatoscopic method from February 2012 to February 2014 and results were compared with pathological features of samples. Results: In this study, mean age of patients was $49.5{\pm}18.9$. Some 25 (41%) were men and 36 (59%) were women. In 27 cases (44.3%) there was diagnosis of melanocytic nevus, in 28 cases (45.9%) diagnosis of BCC, and in 3 cases (4.9%) there was mixed diagnosis. The relationship between patients' gender and dermatoscopic diagnosis of the patients was statistically significant (P=0.001). For BCC the sensitivity and specificity of dermatoscopic method were 100% and 97% respectively and for melanocytic nevi 96.4% and 97%. Conclusions: Dermatoscopic study not only can be helpful in improving clinical diagnosis while guiding missed malignant lesions to pathologic evaluations, but also could be useful in evaluating further suspicious or recurrent cases.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.4
• /
• pp.533-540
• /
• 2022

Specialists diagnose skin cancer using a dermatoscopy to detect skin cancer as early as possible, but it is difficult to determine accurate skin lesions because skin lesions have various shapes. Recently, the skin lesion segmentation method using deep learning, which has shown high performance, has a problem in segmenting skin lesions because the boundary between healthy skin and skin lesions is not clear. To solve these issues, the proposed method constructs a transformer block to effectively segment the skin lesion, and constructs an edge decoder for each layer of the network to segment the skin lesion in detail. Experiment results have shown that the proposed method achieves a performance improvement of 0.041 ~ 0.071 for Dic Coefficient and 0.062 ~ 0.112 for Jaccard Index, compared with the previous method.