Background: Recent studies have successfully demonstrated the use of deep-learning algorithms for dermatologist-level classification of suspicious lesions by the use of excessive proprietary image databases and limited numbers of dermatologists. For the first time, the performance of a deep-learning algorithm trained by open-source images exclusively is compared to a large number of dermatologists covering all levels within the clinical hierarchy. Methods: We used methods from enhanced deep learning to train a convolutional neural network (CNN) with 12,378 open-source dermoscopic images. We used 100 images to compare the performance of the CNN to that of the 157 dermatologists from 12 university hospitals in Germany.

Background: Recent studies have demonstrated the use of convolutional neural networks (CNNs) to classify images of melanoma with accuracies comparable to those achieved by board-certified dermatologists. However, the performance of a CNN exclusively trained with dermoscopic images in a clinical image classification task in direct competition with a large number of dermatologists has not been measured to date. This study compares the performance of a convolutional neuronal network trained with dermoscopic images exclusively for identifying melanoma in clinical photographs with the manual grading of the same images by dermatologists.

No abstract

No abstract

The skin is an important extra-gonadal steroidogenic organ, capable of metabolizing various hormones from their precursors, as well as of synthesizing de novo a broad palette of sex steroids and glucocorticoids from cholesterol. In this manuscript, we review the major steroidogenic properties of human skin and we suggest steroidogenesis' impairment as a cardinal factor for various pathological conditions such as acne, rosacea, atopic dermatitis, and androgenic alopecia.

Aging is a complex process not only influenced by inherited but also by several environmental factors. It is characterized by a progressive loss of function in multiple tissues, which leads to an increased probability of death. On the other hand, several morphological and histological changes are registered in aged skin that is mostly dependent on the cumulative exposure in environmental aging promoters, such as ultraviolet radiation. Understanding of individual pathogenesis and introduction of preventive measurements require objective assessment, i.e., the administration of biomarkers. Because of the complexity of skin aging, the exact definition of biomarkers is a major research challenge. In this article, we summarize the basic knowledge involving skin aging and its biomarkers.

The introduction of BRAF and MEK inhibitors into clinical practice improved the prognosis of metastatic melanoma patients. The combination of BRAF inhibitor dabrafenib with MEK inhibitor trametinib has shown its superiority to single agent therapy and is characterized by a tolerable spectrum of adverse events which shows a decrease in incidence over time on treatment. Areas covered: The current scientific literature on safety and adverse events (AEs) related to BRAF and MEK-inhibition has been investigated with special focus on the large phase 3 studies (COMBI-v, COMBI-d and CoBRIM) as well as recent updates presented at oncology and melanoma meetings. Additionally, published case series/case reports were screened for information on AEs. Expert opinion: Even though almost every patient (98%) under combination therapy with dabrafenib and trametinib experiences at least one adverse event, these are generally mild to moderate, reversible and can be managed with dose reductions or interruptions. However, due to an increased life expectancy, there is a substantial need to prevent and treat also mild adverse events, as they play a central role for the quality of life of patients. Ongoing clinical trials will have to demonstrate the efficacy as well as safety of triple combination with anti-PD-1/anti-PD-L1 antibodies.

No abstract