@article{SondermannUtikalEnketal.2019, author = {Sondermann, Wiebke and Utikal, Jochen Sven and Enk, Alexander H. and Schadendorf, Dirk and Klode, Joachim and Hauschild, Axel and Weichenthal, Michael and French, Lars E. and Berking, Carola and Schilling, Bastian and Haferkamp, Sebastian and Fr{\"o}hling, Stefan and von Kalle, Christof and Brinker, Titus J.}, title = {Prediction of melanoma evolution in melanocytic nevi via artificial intelligence: A call for prospective data}, series = {European Journal of Cancer}, volume = {119}, journal = {European Journal of Cancer}, doi = {10.1016/j.ejca.2019.07.009}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-239263}, pages = {30-34}, year = {2019}, abstract = {Recent research revealed the superiority of artificial intelligence over dermatologists to diagnose melanoma from images. However, 30-50\% of all melanomas and more than half of those in young patients evolve from initially benign lesions. Despite its high relevance for melanoma screening, neither clinicians nor computers are yet able to reliably predict a nevus' oncologic transformation. The cause of this lies in the static nature of lesion presentation in the current standard of care, both for clinicians and algorithms. The status quo makes it difficult to train algorithms (and clinicians) to precisely assess the likelihood of a benign skin lesion to transform into melanoma. In addition, it inhibits the precision of current algorithms since 'evolution' image features may not be part of their decision. The current literature reveals certain types of melanocytic nevi (i.e. 'spitzoid' or 'dysplastic' nevi) and criteria (i.e. visible vasculature) that, in general, appear to have a higher chance to transform into melanoma. However, owing to the cumulative nature of oncogenic mutations in melanoma, a more fine-grained early morphologic footprint is likely to be detectable by an algorithm. In this perspective article, the concept of melanoma prediction is further explored by the discussion of the evolution of melanoma, the concept for training of such a nevi classifier and the implications of early melanoma prediction for clinical practice. In conclusion, the authors believe that artificial intelligence trained on prospective image data could be transformative for skin cancer diagnostics by (a) predicting melanoma before it occurs (i.e. pre-in situ) and (b) further enhancing the accuracy of current melanoma classifiers. Necessary prospective images for this research are obtained via free mole-monitoring mobile apps.}, language = {en} } @article{BrinkerHeklerEnketal.2019, author = {Brinker, Titus J. and Hekler, Achim and Enk, Alexander H. and Berking, Carola and Haferkamp, Sebastian and Hauschild, Axel and Weichenthal, Michael and Klode, Joachim and Schadendorf, Dirk and Holland-Letz, Tim and von Kalle, Christof and Fr{\"o}hling, Stefan and Schilling, Bastian and Utikal, Jochen S.}, title = {Deep neural networks are superior to dermatologists in melanoma image classification}, series = {European Journal of Cancer}, volume = {119}, journal = {European Journal of Cancer}, doi = {10.1016/j.ejca.2019.05.023}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-220539}, pages = {11-17}, year = {2019}, abstract = {Background Melanoma is the most dangerous type of skin cancer but is curable if detected early. Recent publications demonstrated that artificial intelligence is capable in classifying images of benign nevi and melanoma with dermatologist-level precision. However, a statistically significant improvement compared with dermatologist classification has not been reported to date. Methods For this comparative study, 4204 biopsy-proven images of melanoma and nevi (1:1) were used for the training of a convolutional neural network (CNN). New techniques of deep learning were integrated. For the experiment, an additional 804 biopsy-proven dermoscopic images of melanoma and nevi (1:1) were randomly presented to dermatologists of nine German university hospitals, who evaluated the quality of each image and stated their recommended treatment (19,296 recommendations in total). Three McNemar's tests comparing the results of the CNN's test runs in terms of sensitivity, specificity and overall correctness were predefined as the main outcomes. Findings The respective sensitivity and specificity of lesion classification by the dermatologists were 67.2\% (95\% confidence interval [CI]: 62.6\%-71.7\%) and 62.2\% (95\% CI: 57.6\%-66.9\%). In comparison, the trained CNN achieved a higher sensitivity of 82.3\% (95\% CI: 78.3\%-85.7\%) and a higher specificity of 77.9\% (95\% CI: 73.8\%-81.8\%). The three McNemar's tests in 2 × 2 tables all reached a significance level of p < 0.001. This significance level was sustained for both subgroups. Interpretation For the first time, automated dermoscopic melanoma image classification was shown to be significantly superior to both junior and board-certified dermatologists (p < 0.001).}, language = {en} } @article{BrinkerHeklerHauschildetal.2019, author = {Brinker, Titus J. and Hekler, Achim and Hauschild, Axel and Berking, Carola and Schilling, Bastian and Enk, Alexander H. and Haferkamp, Sebastian and Karoglan, Ante and von Kalle, Christof and Weichenthal, Michael and Sattler, Elke and Schadendorf, Dirk and Gaiser, Maria R. and Klode, Joachim and Utikal, Jochen S.}, title = {Comparing artificial intelligence algorithms to 157 German dermatologists: the melanoma classification benchmark}, series = {European Journal of Cancer}, volume = {111}, journal = {European Journal of Cancer}, doi = {10.1016/j.ejca.2018.12.016}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-220569}, pages = {30-37}, year = {2019}, abstract = {Background Several recent publications have demonstrated the use of convolutional neural networks to classify images of melanoma at par with board-certified dermatologists. However, the non-availability of a public human benchmark restricts the comparability of the performance of these algorithms and thereby the technical progress in this field. Methods An electronic questionnaire was sent to dermatologists at 12 German university hospitals. Each questionnaire comprised 100 dermoscopic and 100 clinical images (80 nevi images and 20 biopsy-verified melanoma images, each), all open-source. The questionnaire recorded factors such as the years of experience in dermatology, performed skin checks, age, sex and the rank within the university hospital or the status as resident physician. For each image, the dermatologists were asked to provide a management decision (treat/biopsy lesion or reassure the patient). Main outcome measures were sensitivity, specificity and the receiver operating characteristics (ROC). Results Total 157 dermatologists assessed all 100 dermoscopic images with an overall sensitivity of 74.1\%, specificity of 60.0\% and an ROC of 0.67 (range = 0.538-0.769); 145 dermatologists assessed all 100 clinical images with an overall sensitivity of 89.4\%, specificity of 64.4\% and an ROC of 0.769 (range = 0.613-0.9). Results between test-sets were significantly different (P < 0.05) confirming the need for a standardised benchmark. Conclusions We present the first public melanoma classification benchmark for both non-dermoscopic and dermoscopic images for comparing artificial intelligence algorithms with diagnostic performance of 145 or 157 dermatologists. Melanoma Classification Benchmark should be considered as a reference standard for white-skinned Western populations in the field of binary algorithmic melanoma classification.}, language = {en} } @article{KrebsBehrmannKalogirouetal.2019, author = {Krebs, Markus and Behrmann, Christoph and Kalogirou, Charis and Sokolakis, Ioannis and Kneitz, Susanne and Kruithof-de Julio, Marianna and Zoni, Eugenio and Rech, Anne and Schilling, Bastian and K{\"u}bler, Hubert and Spahn, Martin and Kneitz, Burkhard}, title = {miR-221 Augments TRAIL-mediated apoptosis in prostate cancer cells by inducing endogenous TRAIL expression and targeting the functional repressors SOCS3 and PIK3R1}, series = {BioMed Research International}, volume = {2019}, journal = {BioMed Research International}, doi = {10.1155/2019/6392748}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-202480}, pages = {6392748}, year = {2019}, abstract = {miR-221 is regarded as an oncogene in many malignancies, and miR-221-mediated resistance towards TRAIL was one of the first oncogenic roles shown for this small noncoding RNA. In contrast, miR-221 is downregulated in prostate cancer (PCa), thereby implying a tumour suppressive function. By using proliferation and apoptosis assays, we show a novel feature of miR-221 in PCa cells: instead of inducing TRAIL resistance, miR-221 sensitized cells towards TRAIL-induced proliferation inhibition and apoptosis induction. Partially responsible for this effect was the interferon-mediated gene signature, which among other things contained an endogenous overexpression of the TRAIL encoding gene TNFSF10. This TRAIL-friendly environment was provoked by downregulation of the established miR-221 target gene SOCS3. Moreover, we introduced PIK3R1 as a target gene of miR-221 in PCa cells. Proliferation assays showed that siRNA-mediated downregulation of SOCS3 and PIK3R1 mimicked the effect of miR-221 on TRAIL sensitivity. Finally, Western blotting experiments confirmed lower amounts of phospho-Akt after siRNA-mediated downregulation of PIK3R1 in PC3 cells. Our results further support the tumour suppressing role of miR-221 in PCa, since it sensitises PCa cells towards TRAIL by regulating the expression of the oncogenes SOCS3 and PIK3R1. Given the TRAIL-inhibiting effect of miR-221 in various cancer entities, our results suggest that the influence of miR-221 on TRAIL-mediated apoptosis is highly context- and entity-dependent.}, language = {en} } @article{GlutschGraenWeberetal.2019, author = {Glutsch, Valerie and Gr{\"a}n, Franziska and Weber, Judith and Gesierich, Anja and Goebeler, Matthias and Schilling, Bastian}, title = {Response to combined ipilimumab and nivolumab after development of a nephrotic syndrome related to PD-1 monotherapy}, series = {Journal for ImmunoTherapy of Cancer}, volume = {7}, journal = {Journal for ImmunoTherapy of Cancer}, doi = {10.1186/s40425-019-0655-4}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-201214}, pages = {181}, year = {2019}, abstract = {Background High response rates of metastatic melanoma have been reported upon immune checkpoint inhibition by PD-1 blockade alone or in combination with CTLA-4 inhibitors. However, the majority of patients with a primary resistance to anti-PD-1 monotherapy is also refractory to a subsequent combined checkpoint inhibition. In BRAF wildtype patients with a primary resistance to PD-1 inhibitors, therapeutic options are therefore limited and immune-related adverse events (irAE) have to be taken into consideration when discussing a subsequent immunotherapy. Case presentation We report the case of a 68-year-old male patient with metastatic melanoma who experienced an acute renal failure with nephrotic syndrome due to a minimal change disease developing after a single dose of the anti-PD-1 antibody pembrolizumab. A kidney biopsy revealed a podocytopathy without signs of interstitial nephritis. Renal function recovered to almost normal creatinine and total urine protein levels upon treatment with oral steroids and diuretics. Unfortunately, a disease progression (PD, RECIST 1.1) was observed in a CT scan after resolution of the irAE. In a grand round, re-exposure to a PD-1-containing regime was recommended. Consensually, a combined immunotherapy with ipilimumab and nivolumab was initiated. Nephrotoxicity was tolerable during combined immunotherapy and a CT scan of chest and abdomen showed a deep partial remission (RECIST 1.1) after three doses of ipilimumab (3 mg/kg) and nivolumab (1 mg/kg). Conclusion This case illustrates that a fulminant response to combined checkpoint inhibition is possible after progression after anti-PD-1 monotherapy and a severe irAE.}, language = {en} }