Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists.

Background: Deep learning convolutional neural networks (CNN) may facilitate melanoma detection, but data comparing a CNN's diagnostic performance to larger groups of dermatologists are lacking. Methods: Google's Inception v4 CNN architecture was trained and validated using dermoscopic images and corresponding diagnoses. In a comparative cross-sectional reader study a 100-image test-set was used (level-I: dermoscopy only; level-II: dermoscopy plus clinical information and images). Main outcome measures were sensitivity, specificity and area under the curve (AUC) of receiver operating characteristics (ROC) for diagnostic classification (dichotomous) of lesions by the CNN versus an international group of 58 dermatologists during level-I or -II of the reader study. Secondary end points included the dermatologists' diagnostic performance in their management decisions and differences in the diagnostic performance of dermatologists during level-I and -II of the reader study. Additionally, the CNN's performance was compared with the top-five algorithms of the 2016 International Symposium on Biomedical Imaging (ISBI) challenge. Results: In level-I dermatologists achieved a mean (±standard deviation) sensitivity and specificity for lesion classification of 86.6% (±9.3%) and 71.3% (±11.2%), respectively. More clinical information (level-II) improved the sensitivity to 88.9% (±9.6%, P = 0.19) and specificity to 75.7% (±11.7%, P < 0.05). The CNN ROC curve revealed a higher specificity of 82.5% when compared with dermatologists in level-I (71.3%, P < 0.01) and level-II (75.7%, P < 0.01) at their sensitivities of 86.6% and 88.9%, respectively. The CNN ROC AUC was greater than the mean ROC area of dermatologists (0.86 versus 0.79, P < 0.01). The CNN scored results close to the top three algorithms of the ISBI 2016 challenge. Conclusions: For the first time we compared a CNN's diagnostic performance with a large international group of 58 dermatologists, including 30 experts. Most dermatologists were outperformed by the CNN. Irrespective of any physicians' experience, they may benefit from assistance by a CNN's image classification. Clinical trial number: This study was registered at the German Clinical Trial Register (DRKS-Study-ID: DRKS00013570; https://www.drks.de/drks_web/).

Nestin and SOX9 and SOX10 transcription factors are coexpressed in melanoma.

Nestin is an intermediate filament expressed in proliferating neural progenitor cells and has been considered as a stem cell marker. Nestin is also found in melanoma and we recently demonstrated that its expression in melanoma cell lines is regulated by the transcription factors SOX9 and SOX10, but not BRN2. In this study, the expression levels of nestin, BRN2, SOX9 and SOX10 were analysed in tissues of melanoma (n = 78) and melanocytic nevi (n = 26) by immunohistochemistry. All proteins were highly expressed in primary and metastatic melanomas and, apart from BRN2, showed much lower levels in melanocytic nevi. Significant coexpression of nestin with SOX9 and SOX10 was found in primary melanoma confirming our in vitro data. Correlation analysis with clinicopathological data revealed that nestin was significantly associated with presence of ulceration in primary tumors and SOX9 with more advanced stage of disease. Our data reveal that SOX9 and SOX10 are highly expressed in melanoma and seem to have a regulatory role in nestin expression. The association with ulceration and advanced-stage tumors, respectively, suggests that nestin and SOX9 may be negative prognostic markers in melanoma.

Zanolimumab, a human monoclonal antibody targeting CD4 in the treatment of mycosis fungoides and Sézary syndrome.

BACKGROUND: The most common type of primary cutaneous T cell-lymphomas (CTCLs), which are characterised by a clonal proliferation of malignant skin-homing CD4(+) lymphocytes, is mycosis fungoides (MF) and its rare leukaemic variant Sézary syndrome (SS). OBJECTIVE: Zanolimumab is a high affinity human monoclonal IgG1k antibody, targeting the CD4-molecule. It exhibits cytotoxic and antiproliferative effects and has previously shown efficacy in CTCLs. METHODS: Literature and reference research was done by using Pubmed and updates of ongoing studies were taken from American Society of Clinical Oncology (ASCO) and American Society of Hematology (ASH )annual meeting abstracts. RESULTS: This article gives an overview about efficacy, tolerability and safety as well as chemistry, pharmacodynamics and pharmacokinetics of zanolimumab in the treatment of CTCLs.

Emerging drugs in cutaneous T cell lymphoma.

BACKGROUND: Mycosis fungoides (MF) represents the most common type of primary cutaneous T cell-lymphomas (CTCL), which are characterized by a clonally proliferation of malignant CD4+ lymphocytes in the skin. OBJECTIVE: Skin-directed treatment regimens, like phototherapy and corticosteroids, are commonly used in early stages; systemic treatments and chemotherapies are used in advanced stages. Because conventional treatments usually end in a transient remission without curative results, there is a high need for new therapeutic strategies with acceptable side effects. METHODS: Literature and reference research was done by using the data bank PubMed, and updates of ongoing studies were taken out of ASCO and ASH annual meeting abstracts. RESULTS/CONCLUSIONS: This article gives an overview of the various medications in current use, with emphasis on emerging drugs with novel therapeutic targets.