No description available.

Malignant melanoma is the deadliest form of skin cancer. If correctly diagnosed in time, the expected five-year survival rate can increase up to 97 %. Therefore, exploring various methods for early detection can contribute with tools which can be used to improve detection of disease and finally to make sure that help is given in time. The purpose of this work was to investigate the performance and behavior of different convolutional neural network (CNN) architectures and to explore whether presegmenting clinical images would improve the prediction results on a binary classifier system. For the purposes of this paper, the two selected CNNs were Inception v3 and DenseNet201. The networks were pretrained on ImageNet and transfer learning techniques such as feature extraction and fine-tuning were used to extract the features of the training set. Batch size was varied and five-fold cross-validation was applied during training to find the optimal number of epochs for training. Evaluation was done on the ISIC test set, the PH2 dataset and a combined set of images from Karolinska University Hospital and FirstDerm, where the latter was also cropped to evaluate presegmentation. The achieved results for the ISIC test set were AUCs of 0.66 for Inception v3 and 0.71 for DenseNet201. For the PH2 test set, the AUCs were 0.82 and 0.73. The results for the Karolinska and FirstDerm set were 0.49 and 0.42. Presegmenting the latter test set resulted in AUCs of 0.58 and 0.51. In conclusion, quality of images could have a big impact on the classification performance. Batch size seems to affect the performance and could thus be an important hyperparameter to tune. Ultimately, the Inception v3 architecture seems to be less affected by different variability why selecting this architecture for a real-world clinical image application could be more suitable. However, the networks performed much worse than state of the art results in previous papers and the conclusions are based on rather inconclusive results. Therefore more research has to be done to verify the conclusions. / Malignt melanom är den dödligaste formen av hudcancer. Om en korrekt diagnos sätts tillräckligt tidigt kan den femåriga överlevnadsgraden uppgå till 97 %. Detta gör att forskningen efter metoder för tidigarelagd upptäckt kan bidra med verktyg som i sin tur kan användas till att upptäcka sjukdom och slutligen bidra till att hjälp sätts in i tid. Målet med detta arbete var att undersöka prestanda och beteende för olika faltningsbara neurala nätverk (CNN) och att undersöka ifall försegmentering av kliniska bilder kunde förbättra resultaten i ett binärt klassificeringssystem. De utvalda faltningsbara neurala nätverksarkitekturerna var Inception v3 och DenseNet201. Nätverken var förträanade på ImageNet och "Transfer-learning"-metoder som feature extraction och fine-tuning användes för att extrahera features från träningsuppsättningen. Batch size varierades och femtalig korsvalidering användes för att hitta det optimala antalet träningsepoker. Utvärderingen gjordes med bilder i testset från ISIC, PH2 och Karolinska och FirstDerm. Bilderna i den senare datamängden beskärdes för att utvärdera försegmenteringen av kliniska bilder. De uppnådda resultaten för ISIC testmängden var AUC-värden på 0.66 för Inception v3 och 0.71 för DenseNet201. För PH2 låg AUC-värdena på 0.82 respektive 0.73. Resultaten för testmängden med bilder frön Karolinska och FirstDerm var 0.40 och 0.42. Försegmenteringen av den sistnämnda testmängden gav AUC-värden på 0.58 och 0.51. Sammanfattningsvis kan bildkvalitet ha en stor inverkan på ett nätverks klassificeringsprestanda. Batch size verkar också påverka resultaten ochkan därför vara en viktig hyperparameter att stämma. Slutligen verkar Inception v3 vara mindre känslig för olika typer av variabiltet vilket görvalet av denna arkitektur mer lämplig ifall en riktig applikation ska byggas för detektion av exempelvis kliniska bilder. Det som bör understrykas i detta arbete är att resultaten var mycket sämre än det som bäst uppvisats i föregående rapporter och att slutasatserna är baserade på relativt ickeövertygande värden. Därför efterkrävs mer forskning för att styrka slutsatserna.

Cutaneous melanoma accounts for less than 5% of all skin cancers but over 75% of skin cancer related deaths. Prior biologic research suggests caffeine may arrest cancer cell formation and metastasis in vivo. Additionally, certain tea components exhibit anti-inflammatory, anti-oxidant, and other anti-carcinogenic effects. Prior epidemiologic studies show possible protective effect of both coffee and tea on risk of melanoma, but results remain inconsistent. We examined the association between coffee and tea intake and risk of cutaneous melanoma using the Women’s Health Initiative Observational Study. Coffee and tea intake were measured through self-administered questionnaires. Melanomas were self-reported and physician adjudicated. Cox proportional hazards models were used to evaluate associations. Of the 66,484 white post-menopausal women with no prior history of cancer (average follow up=7.8 years), 73% reported daily intake of coffee, 26% reported daily tea intake, and 398 cases of melanoma were adjudicated. Daily coffee intake (HR=0.84 95% CI=0.66-1.08) and daily tea intake (HR=1.00, 95% CI=0.78-1.29) were not significantly associated with increased risk of cutaneous melanoma compared to non-daily intake. No significant trend was observed with increased daily coffee (p-trend=0.22) or tea intake (p-trend=0.28). In conclusion, we observed insignificant inverse associations between coffee intake and cutaneous melanoma among post-menopausal Caucasian women.

Background: Most patients with high-risk melanomas develop metastasis within the first few years after diagnosis. However, late recurrence of melanoma is seen in patients that metastasize more than 10 years after the primary diagnosis; a metastasis after 15 years is considered an ultra-late recurrence. It is critical to better understand the clinical and biological characteristics of this subset of melanoma patients in order to offer an individual treatment plan and prevent metastasis. Methods: We retrospectively analyzed melanoma patients with recurrence ≥10 years after a primary diagnosis documented between 1993 and 2012 at the skin cancer center of the University Medical Center Leipzig, Germany. We conducted a comprehensive review of the literature and compared the results with our data. Available archived primary melanoma tissue was investigated with a seven-marker immunohistochemical signature (immunoprint®) previously validated to reliably identify high-risk patients within stages IB-III. Results: Out of 36 analyzed patients, a third metastasized ultra-late (≥15 years). The mean age at initial diagnosis was 51 years, with women being diagnosed comparatively younger than men. The largest proportion of patients with late recurrence had primary melanomas located on the trunk. The immunoprint® signature of the available primary melanomas allowed the accurate prediction of a high risk. However, it is difficult to draw a definitive conclusion from the small number of cases that could be analyzed with immunoprint® (n = 2) in this study. Apart from the primary tumor characteristics, the laboratory values at time of metastasis, comorbidities and outcome are also shown. Conclusion: Late and ultra-late recurrent melanomas seem not to differ from melanomas in general, apart from a distinctly higher proportion of lower leg localizations in ultra-late recurrent melanomas. The immunoprint® signature may help to identify high-risk primary tumors at the time of initial diagnosis. However, apart from the risk profile of the primary tumor, it seems that individual immune surveillance can control residual tumor cells for more than a decade. Advanced age and increasing comorbidities may contribute to a disturbed immunological balance.

We report two cases of combined cutaneous tumors composed of melanoma and carcinoma. The first tumor presented as a 5-mm pink-blue macule over the right zygomatic arch in an 85-year-old man. Shave biopsy and immunohistochemical studies revealed that the tumor was composed of melanoma (highlighted by SOX10 and MART-1, with high Ki-67 proliferative index) intermixed with nodular basal cell carcinoma (highlighted by pan-cytokeratin and Ber-EP4). The neoplastic melanocytes were confined to the basal cell carcinoma nodules, and a diagnosis of combined melanoma in situ and basal cell carcinoma was rendered. After therapeutic excision, the patient was disease-free at 9 months after the initial diagnosis. The second tumor presented as a 6-mm pink-brown crusted papule on the right forehead in an 89-year-old man. Shave biopsy and immunohistochemical studies revealed that the tumor was composed of malignant melanoma (MM) (highlighted by S100 and MART-1) intermixed with squamous cell carcinoma (SCC) (highlighted by cytokeratin and p63), and a diagnosis of combined MM-SCC was rendered. These two cases highlight the importance of recognizing these rare types of melanocytic-epithelial cutaneous neoplasms to arrive at an accurate diagnosis that may inform appropriate disease stage and therapy.

There is an increasing evidence that alterations in chromatin remodeling play an important role in tumorigenesis. The SWI/SNF chromatin remodeling complexes contribute to the regulation of gene expression by altering the local chromatin structure. Depending on the context, they can act as either transcriptional activators or repressors. All SWI/SNF subcomplexes contain one of two ATPase subunits, Brm (Brahma) or Brg1 (Brahma related gene 1), which provide the energy for remodeling. Malignant melanoma is an aggressive cancer and is known for its notorious resistance to conventional anticancer therapies. MITF (microphthalmia-associated transcription factor) plays an essential role in melanoma biology and is placed on the central crossroad in the regulation of melanocyte development, differentation, maintenance of lineage identity, and survival of both normal and malignant melanocytes. Our results show that the active SWI/SNF complex is strictly required for the expression of MITF. This complex is also required for expression of some transcriptional MITF targets. The survival of melanoma cells is absolutely dependent on functional SWI/SNF complex and all subunits of this complex are expressed at high levels in melanoma cell lines. Primarily, Brg1-containing subcomplexes are more important for MITF...

No description available.

The Hippo tumor suppressor pathway is a highly conserved signaling pathway that regulates cell proliferation, differentiation, and organ size. Activation of the Hippo pathway leads to the phosphorylation and cytoplasmic sequestration of the pro-growth transcriptional co-activators YAP/TAZ; by contrast, impairment of the Hippo pathway enables YAP/TAZ to enter the nucleus where they bind to the TEAD transcription factors and induce the expression of genes involved in cell proliferation. Functional impairment of the Hippo pathway, and subsequent hyperactivation of YAP/TAZ, is common in many human malignancies, including melanoma. Recently, small molecule inhibitors that disrupt YAP/TAZ-TEAD binding, and thus reduce oncogenic transcriptional signaling have been discovered, but their efficacy in preventing cancer cell growth has not yet been well characterized. Moreover, no simple biomarker has been identified that can predict sensitivity to such inhibitors. We hypothesized that cells in which YAP/TAZ are enriched in the nucleus relative to the cytoplasm, indicative of an impaired Hippo pathway, would be more susceptible to TEAD inhibition. This would provide a useful biomarker to identify cancer cell lines most likely to respond to TEAD inhibition. We therefore developed and validated an automated quantification method to score nuclear:cytoplasmic YAP/TAZ localization in melanoma cell lines. This enabled us to identify “Hippo-On” and “Hippo-Off” signatures. We then treated these lines with the TEAD inhibitor MGH-CP1 and performed cell viability assays. Results from these data demonstrated that cell lines that have greater nuclear localization of YAP/TAZ are more susceptible to MGH-CP1 inhibition, suggesting that YAP/TAZ nuclear localization may be a biomarker to identify candidates for TEAD inhibitor treatment.

No description available.

Genome-wide microarray technology has facilitated the systematic discovery of diagnostic biomarkers of cancers and other pathologies. However, meta-analyses of published arrays using melanoma as a test cancer has uncovered significant inconsistences that hinder advances in clinical practice. In this study a computational model for the integrated analysis of microarray datasets is proposed in order to provide a robust ranking of genes in terms of their relative significance; both genome-wide relative significance (GWRS) and genome-wide global significance (GWGS). When applied to five melanoma microarray datasets published between 2000 and 2011, a new 12-gene diagnostic biomarker signature for melanoma was defined (i.e., EGFR, FGFR2, FGFR3, IL8, PTPRF, TNC, CXCL13, COL11A1, CHP2, SHC4, PPP2R2C, and WNT4). Of these, CXCL13, COL11A1, PTPRF and SHC4 are components of the MAPK pathway and were validated by immunocyto- and immunohisto-chemistry. These proteins were found to be overexpressed in metastatic and primary melanoma cells in vitro and in melanoma tissue in situ compared to melanocytes cultured from healthy skin epidermis and normal healthy human skin. One challenge for the integrated analysis of microarray data is that the microarray data are produced using different platforms and bio-samples, e.g. including both cell line- and biopsy-based microarray datasets. In order to address these challenges, the computational model was further enhanced the stratification of datasets into either biopsy or cell line derived datasets, and via the weighting of microarray data based on quality criteria of data. The methods enhancement was applied to 14 microarray datasets of three cancers (breast, prostate, and melanoma) based on classification accuracy and on the capability to identify predictive biomarkers. Four novel measures for evaluating the capability to identify predictive biomarkers are proposed: (1) classifying independent testing data using wrapper feature selection with machine leaning, (2) assessing the number of common genes with the genes retrieved in independent testing data, (3) assessing the number of common genes with the genes retrieved in across multiple training datasets, (4) assessing the number of common genes with the genes validated in the literature. This enhancement of computational approach (i) achieved reliable classification performance across multiple datasets, (ii) recognized more significant genes into the top-ranked genes as compared to the genes detected by the independent test data, and (iii) detected more meaningful genes than were validated in previous melanoma studies in the literature.