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.
Background: In recent studies, convolutional neural networks (CNNs) outperformed dermatologists in distinguishing dermoscopic images of melanoma and nevi. In these studies, dermatologists and artificial intelligence were considered as opponents. However, the combination of classifiers frequently yields superior results, both in machine learning and among humans. In this study, we investigated the potential benefit of combining human and artificial intelligence for skin cancer classification. Methods: Using 11,444 dermoscopic images, which were divided into five diagnostic categories, novel deep learning techniques were used to train a single CNN. Then, both 112 dermatologists of 13 German university hospitals and the trained CNN independently classified a set of 300
BackgroundNivolumab combined with ipilimumab have shown activity in melanoma brain metastasis (MBM). However, in most of the clinical trials investigating immunotherapy in this subgroup, patients with symptomatic MBM and/or prior local brain radiotherapy were excluded. We studied the efficacy of nivolumab plus ipilimumab alone or in combination with local therapies regardless of treatment line in patients with asymptomatic and symptomatic MBM.MethodsPatients with MBM treated with nivolumab plus ipilimumab in 23 German Skin Cancer Centers between April 2015 and October 2018 were investigated. Overall survival (OS) was evaluated by Kaplan-Meier estimator and univariate and multivariate Cox proportional hazard analyses were performed to determine prognostic factors associated with OS.ResultsThree hundred and eighty patients were included in this study and 31% had symptomatic MBM (60/193 with data available) at the time of start nivolumab plus ipilimumab. The median follow-up was 18 months and the 2 years and 3 years OS rates were 41% and 30%, respectively. We identified the following independently significant prognostic factors for OS: elevated serum lactate dehydrogenase and protein S100B levels, number of MBM and Eastern Cooperative Oncology Group performance status. In these patients treated with checkpoint inhibition first-line or later, in the subgroup of patients with BRAFV600-mutated melanoma we found no differences in terms of OS when receiving first-line either BRAF and MEK inhibitors or nivolumab plus ipilimumab (p=0.085). In BRAF wild-type patients treated with nivolumab plus ipilimumab in first-line or later there was also no difference in OS (p=0.996). Local therapy with stereotactic radiosurgery or surgery led to an improvement in OS compared with not receiving local therapy (p=0.009), regardless of the timepoint of the local therapy. Receiving combined immunotherapy for MBM in first-line or at a later time point made no difference in terms of OS in this study population (p=0.119).ConclusionImmunotherapy with nivolumab plus ipilimumab, particularly in combination with stereotactic radiosurgery or surgery improves OS in asymptomatic and symptomatic MBM.
This open-label, pilot study enrolled men and women (18years) with acne vulgaris. In 14 enrolled patients, skin microbiome composition shifted towards study formulations. No untoward tolerability, visible irritation, or significant flare-ups were observed. Non-inflamed lesions and skin pH were reduced. Modulation of Cutibacterium acnes towards the non-acne causing strains on the skin of patients with acne was safe. C. acnes was formerly thought to be the cardinal cause of acne; however, recently some, but not all, strains of C. acnes were found to be responsible. This microbiome modulation approach as therapy requires validation in future clinical studies. Imbalance in skin microflora, particularly related to certain Cutibacterium acnes strains, may trigger acne. Application of non-acne-causing strains to the skin may modulate the skin microbiome and thereby lead to a reduction in acne. This pilot study evaluates the safety and efficacy of microbiome modulation on acneprone skin. The study had 2 phases: active induction (5% benzoyl peroxide gel, 7 days) and interventional C. acnes strains treatment (5 weeks). Patients were randomized to either topical skin formulations PT1 (2 strains of C. acnes Single Locus Sequence Typing [SLST] type C3 and K8, 50% each) or PT2 (4 strains of C. acnes SLST type C3 [55%], K8 [5%], A5 [30%] and F4 [10%]). Safety and efficacy was evaluated in 14 patients (PT1=8/14, PT2=6/14). Skin microbiome composition shifted towards study formulations. No untoward adverse events, visible irritation, or significant flare-up were observed. Non-inflamed lesions and skin pH were reduced. Comedone counts improved clinically with no deterioration in inflammatory lesions.
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.