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.

Background: In recent studies, convolutional neural networks (CNNs) outperformed dermatologists in distinguishing dermoscopic images of melanoma and nevi. In these studies, dermatologists and artificial intelligence were considered as opponents. However, the combination of classifiers frequently yields superior results, both in machine learning and among humans. In this study, we investigated the potential benefit of combining human and artificial intelligence for skin cancer classification. Methods: Using 11,444 dermoscopic images, which were divided into five diagnostic categories, novel deep learning techniques were used to train a single CNN. Then, both 112 dermatologists of 13 German university hospitals and the trained CNN independently classified a set of 300

No abstract

The transcription factor NRF2 is the major mediator of oxidative stress responses and is closely connected to therapy resistance in tumors harboring activating mutations in the NRF2 pathway. In melanoma, such mutations are rare, and it is unclear to what extent melanomas rely on NRF2. Here we show that NRF2 suppresses the activity of the melanocyte lineage marker MITF in melanoma, thereby reducing the expression of pigmentation markers. Intriguingly, we furthermore identified NRF2 as key regulator of immune-modulating genes, linking oxidative stress with the induction of cyclooxygenase 2 (COX2) in an ATF4-dependent manner. COX2 is critical for the secretion of prostaglandin E2 and was strongly induced by H2O2 or TNFα only in presence of NRF2. Induction of MITF and depletion of COX2 and PGE2 were also observed in NRF2-deleted melanoma cells in vivo. Furthermore, genes corresponding to the innate immune response such as RSAD2 and IFIH1 were strongly elevated in absence of NRF2 and coincided with immune evasion parameters in human melanoma datasets. Even in vitro, NRF2 activation or prostaglandin E2 supplementation blunted the induction of the innate immune response in melanoma cells. Transcriptome analyses from lung adenocarcinomas indicate that the observed link between NRF2 and the innate immune response is not restricted to melanoma.