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.
Previous studies suggest an impact of body composition on outcome in melanoma patients. We aimed to determine the prognostic value of CT-based body composition assessment in patients receiving immune checkpoint inhibitor therapy for treatment of metastatic disease using a deep learning approach. One hundred seven patients with staging CT examinations prior to initiation of checkpoint inhibition between January 2013 and August 2019 were retrospectively evaluated. Using an automated deep learning-based body composition analysis pipeline, parameters for estimation of skeletal muscle mass (skeletal muscle index, SMI) and adipose tissue compartments (visceral adipose tissue index, VAI; subcutaneous adipose tissue index, SAI) were derived from staging CT. The cohort was binarized according to gender-specific median cut-off values. Patients below the median were defined as having low SMI, VAI, or SAI, respectively. The impact on outcome was assessed using the Kaplan–Meier method with log-rank tests. A multivariable logistic regression model was built to test the impact of body composition parameters on 3-year mortality. Patients with low SMI displayed significantly increased 1-year (25% versus 9%, p = 0.035), 2-year (32% versus 13%, p = 0.017), and 3-year mortality (38% versus 19%, p = 0.016). No significant differences with regard to adipose tissue compartments were observed (3-year mortality: VAI, p = 0.448; SAI, p = 0.731). On multivariable analysis, low SMI (hazard ratio (HR), 2.245; 95% confidence interval (CI), 1.005–5.017; p = 0.049), neutrophil-to-lymphocyte ratio (HR, 1.170; 95% CI, 1.076–1.273; p < 0.001), and Karnofsky index (HR, 0.965; 95% CI, 0.945–0.985; p = 0.001) remained as significant predictors of 3-year mortality. Lowered skeletal muscle index as an indicator of sarcopenia was associated with worse outcome in patients with metastatic melanoma receiving immune checkpoint inhibitor therapy.
Background TIGIT is an immune checkpoint under investigation as therapeutic target. Understanding the regulation of TIGIT on an epigenetic level might support the development of companion biomarkers. Methods We correlated TIGIT DNA methylation of single CpG sites with gene expression, signatures of immune infiltrates and interferon-γ, and survival in melanoma. We further analyzed methylation levels in immune cell subsets, melanocyte and melanoma cell lines. TIGIT expression patterns within components of the melanoma microenvironment were analyzed by single cell sequencing. We used quantitative methylation-specific PCR, flow cytometry, and immunohistochemistry for correlations between expression and methylation and to assess the effect of pharmacological demethylation of melanoma cells treated with 5‐aza‐2‐deoxycytidine (decitabine). Finally, we investigated the association of patients’ survival with TIGIT mRNA and methylation. Results Depending on the sequence context of the analyzed CpG site, we found a cell type-specific TIGIT gene locus methylation pattern and significant correlations of TIGIT methylation with mRNA expression, an interferon γ signature, and distinct immune cell infiltrates, including TIGIT+ lymphocytes. We detected a melanoma cell-intrinsic TIGIT protein expression. Pharmacological demethylation of the A375 melanoma cell line led to a constitutive TIGIT expression. Low promoter flank methylation and high mRNA expression was associated with patients’ prognosis and predicted progression-free survival in patients treated with anti-PD-1 immunotherapy. A high TIGIT+ lymphocyte score was associated with better progression-free survival under anti-PD-1 immunotherapy. Conclusions Our data demonstrate an epigenetic regulation of TIGIT expression via DNA methylation within the melanoma microenvironment. TIGIT DNA methylation and expression may serve as predictive biomarkers in the context of immunotherapies in melanoma.
Summary Kaposi’s sarcoma (KS) is a rare, malignant, multilocular vascular disease originating from lymphatic endothelial cells that can primarily affect the skin and mucous membranes, but also the lymphatic system and internal organs such as the gastrointestinal tract, lungs or liver. Five epidemiological subtypes of KS with variable clinical course and prognosis are distinguished, with increased incidence in specific populations: (1) Classical KS, (2) Iatrogenic KS in immunosuppression, (3) Endemic (African) lymphadenopathic KS, (4) Epidemic, HIV‐associated KS and KS associated with immune reconstitution inflammatory syndrome (IRIS), and (5) KS in men who have sex with men (MSM) without HIV infection. This interdisciplinary guideline summarizes current practice‐relevant recommendations on diangostics and therapy of the different forms of KS. The recommendations mentioned in this short guideline are elaborated in more detail in the extended version of the guideline (online format of the JDDG).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.