Melanoma is considered the deadliest skin cancer and when it is in an advanced state it is difficult to treat. Diagnoses are visually performed by dermatologists, by naked-eye observation. This paper proposes an augmented reality smartphone application for supporting the dermatologist in the real-time analysis of a skin lesion. The app augments the camera view with information related to the lesion features generally measured by the dermatologist for formulating the diagnosis. The lesion is also classified by a deep learning approach for identifying melanoma. The real-time process adopted for generating the augmented content is described. The real-time performances are also evaluated and a user study is also conducted. Results revealed that the real-time process may be entirely executed on the Smartphone and that the support provided is well judged by the target users.

黑色素瘤被认为是最致命的皮肤癌，处于晚期时很难治疗。诊断由皮肤科医生通过肉眼观察进行。本文提出了一种增强现实智能手机应用程序，以支持皮肤科医生进行皮肤病变的实时分析。该应用程序通过与病变特征有关的信息增强了相机视图，这些信息通常由皮肤科医生测量以制定诊断。病变还通过深度学习方法进行分类，以识别黑色素瘤。描述了用于生成增强内容的实时处理。还评估了实时性能，并进行了用户研究。