Infi ltration of human melanomas with cytotoxic immune cells correlates with spontaneous type I IFN activation and a favorable prognosis. Therapeutic blockade of immune-inhibitory receptors in patients with preexisting lymphocytic infi ltrates prolongs survival, but new complementary strategies are needed to activate cellular antitumor immunity in immune cell-poor melanomas. Here, we show that primary melanomas in Hgf-Cdk4 R24C mice, which imitate human immune cell-poor melanomas with a poor outcome, escape IFN-induced immune surveillance and editing. Peritumoral injections of immunostimulatory RNA initiated a cytotoxic infl ammatory response in the tumor microenvironment and signifi cantly impaired tumor growth. This critically required the coordinated induction of type I IFN responses by dendritic, myeloid, natural killer, and T cells. Importantly, antibodymediated blockade of the IFN-induced immune-inhibitory interaction between PD-L1 and PD-1 receptors further prolonged the survival. These results highlight important interconnections between type I IFNs and immune-inhibitory receptors in melanoma pathogenesis, which serve as targets for combination immunotherapies. SIGNIFICANCE:Using a genetically engineered mouse melanoma model, we demonstrate that targeted activation of the type I IFN system with immunostimulatory RNA in combination with blockade of immune-inhibitory receptors is a rational strategy to expose immune cell-poor tumors to cellular immune surveillance. Cancer Discov; 4(6);

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

A high intratumoral frequency of neutrophils is associated with poor clinical outcome in most cancer entities. It is hypothesized that immunosuppressive MDSC (myeloid-derived suppressor cell) activity of neutrophils against tumor-reactive T cells contributes to this effect. However, direct evidence for such activity in situ is lacking. Here, we used whole-mount labeling and clearing, three-dimensional (3D) light sheet microscopy and digital image reconstruction supplemented by 2D multiparameter immunofluorescence, for in situ analyses of potential MDSC–T cell interactions in primary human head and neck cancer tissue. We could identify intratumoral hotspots of high polymorphonuclear (PMN)–MDSC and T cell colocalization. In these areas, the expression of effector molecules Granzyme B and Ki67 in T cells was strongly reduced, in particular for T cells that were in close proximity or physically engaged with PMN-MDSC, which expressed LOX-1 and arginase I. Patients with cancer with evidence for strong down-regulation of T cell function by PMN-MDSC had significantly impaired survival. In summary, our approach identifies areas of clinically relevant functional interaction between MDSC and T cells in human cancer tissue and may help to inform patient selection in future combination immunotherapies.

Background: The diagnosis of most cancers is made by a board-certified pathologist based on a tissue biopsy under the microscope. Recent research reveals a high discordance between individual pathologists. For melanoma, the literature reports 25e26% of discordance for classifying a benign nevus versus malignant melanoma. Deep learning was successfully implemented to enhance the precision of lung and breast cancer diagnoses. The aim of this study is to illustrate the potential of deep learning to assist human assessment for a histopathologic melanoma diagnosis. Methods: Six hundred ninety-five lesions were classified by an expert histopathologist in accordance with current guidelines (350 nevi and 345 melanomas). Only the haematoxylin and eosin stained (H&E) slides of these lesions were digitalised using a slide scanner and then randomly cropped. Five hundred ninety-five of the resulting images were used for the training of a convolutional neural network (CNN). The additional 100 H&E image sections were used to test the results of the CNN in comparison with the original class labels.

No abstract

No abstract