Search

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. Outperformance of dermatologists by the deep neural network was measured in terms of sensitivity, specificity and receiver operating characteristics. Findings The mean sensitivity and specificity achieved by the dermatologists with dermoscopic images was 74.1% (range 40.0%–100%) and 60% (range 21.3%–91.3%), respectively. At a mean sensitivity of 74.1%, the CNN exhibited a mean specificity of 86.5% (range 70.8%–91.3%). At a mean specificity of 60%, a mean sensitivity of 87.5% (range 80%–95%) was achieved by our algorithm. Among the dermatologists, the chief physicians showed the highest mean specificity of 69.2% at a mean sensitivity of 73.3%. With the same high specificity of 69.2%, the CNN had a mean sensitivity of 84.5%. Interpretation A CNN trained by open-source images exclusively outperformed 136 of the 157 dermatologists and all the different levels of experience (from junior to chief physicians) in terms of average specificity and sensitivity.

Dendritic cells (DC) play an important role as antigen-presenting cells in T cell stimulation. Interestingly, a number of recent studies also imply DC as critical accessory cells in B cell activation, isotype switching and plasma blast maintenance. Here we use the conditional in vivo ablation of CD11c(high) DC to investigate the role of these cells in T-independent type 2 immune responses. We show that CD11c(high) DC are dispensable for the initiation and maintenance of a primary immune response against the T-independent type 2 antigen (4-hydroxy-3-nirophenyl)acetyl-Ficoll. Our results suggest that support for plasma cell formation in T cell-independent immune responses can be provided by non-DC such as stromal cells, or is independent of external signals. Interestingly, we found plasma blasts to express CD11c and to be diphtheria toxin-sensitive in CD11c-diphtheria toxin receptor-transgenic mice, providing a unique tool for future analysis of in vivo aspects of plasma cell biology.