• Asian Pacific Journal of Cancer Prevention
• /
• 제17권1호
• /
• 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.

• 한국정보통신학회논문지
• /
• 제26권4호
• /
• pp.533-540
• /
• 2022

전문의는 피부암을 조기에 발견하기 위해 피부경을 사용하여 진단하지만 다양한 형태로 인해 피부 병변을 판단하는 데 어려움이 있다. 최근 높은 성능을 보인 딥러닝을 이용한 피부 병변 분할 방법이 제안되었지만 피부와 피부 병변 경계가 명확하지 않아서 피부 병변을 분할하는 데 문제점이 있었다. 이러한 문제를 개선하기 위해 제안하는 방법은 효과적으로 피부 병변을 분할하기 위해 트랜스포머 블록을 구성하였으며, 네트워크의 각 계층마다 윤곽선 디코더를 구성하여 피부 병변을 자세히 분할하였다. 실험 결과, 제안하는 방법은 기존의 방법보다 Dice coefficient 기준 0.041 ~ 0.071, Jaccard Index 기준 0.067 ~ 0.112의 성능 향상을 보인다.