Search

Here, we present a rare case of a patient who developed multiple primary melanomas within the boundaries of two nevi depigmentosa. The melanomas were excised, and as a preventive measure, the remainder of the nevi depigmentosa were removed. We performed whole-exome sequencing on excised tissue from the nevus depigmentosus, adjacent normal skin, and saliva to explain this intriguing phenomenon. We also performed a GeneTrails Comprehensive Solid Tumor Panel analysis on one of the melanoma tissues. Genetic analysis revealed germline MC1R V92M and TYR R402Q polymorphisms and a MET E168D germline mutation that may have increased the risk of melanoma development. This genetic predisposition, combined with a patient-reported history of substantial sun exposure and sunburns, which were more severe within the boundaries of the nevi depigmentosa due to the lack of photoprotective melanin, produced numerous somatic mutations in the melanocytes of the nevi depigmentosa. Fitting with this paradigm for melanoma development in chronically sun-damaged skin, the patient's melanomas harbored somatic mutations in CDKN2A (splice site), NF1, and ATRX and had a tumor mutation burden in the 90-95th percentile for melanoma.

Background Since 2011, the therapeutic landscape of melanoma has changed dramatically because of the adoption of immune checkpoint inhibitor and targeted therapies. The authors sought to quantify the effects of these changes on short-term treatment costs by comparing the first-year cancer-attributable costs in novel (2011-2015) and historical (2004-2010) treatment eras. Methods The authors estimated the first-year cancer-attributable and out-of-pocket (OOP) costs by cancer stage at diagnosis by using a case-control approach. Patients aged ≥67 years with melanoma results were used to calculate the total direct costs of treatment during the first year after the diagnosis of melanoma in the US Medicare population older than 65 years. Costs were reported in 2018 dollars. Results Costs increased with the stage at diagnosis. Average first-year cancer-attributable costs per patient for stage IV patients increased significantly by 61.7% from $45,952 to $74,297 after the adoption of novel treatments. Per-patient OOP responsibility decreased by almost 30.8% across all stages of cancer but increased by 16.5% for stage IV patients from 2004 ($7646) to 2015 ($8911). The total direct cost of treatment for persons with melanoma older than 65 years increased by $16.03 million (4.93%) from $324.68 million in 2010 to $340.71 million in 2015. The largest increase in yearly total cost, $23.64 million (56.53%), was observed among stage IV patients. Conclusions The direct cost of melanoma increased significantly in the Medicare population, particularly for advanced-stage disease. Prevention and early detection initiatives may reduce the economic burden of melanoma.

Background Many classifiers have been developed that can distinguish different types of skin lesions (e.g., benign nevi, melanoma) with varying degrees of success.1–5 However, even successfully trained classifiers may perform poorly on images that include artefacts. While problems created by hair and ink markings have been published, quantitative measurements of blur, colour and lighting variations on classification accuracy has not yet been reported to our knowledge. Objectives We created a system that measures the impact of various artefacts on machine learning accuracy. Our objectives were to (1) quantitatively identify the most egregious artefacts and (2) demonstrate how to assess a classification algorithm's accuracy when input images include artefacts. Methods We injected artefacts into dermatologic images using techniques that could be controlled with a single variable. This allows us to quantitatively evaluate the impact on the accuracy. We trained two convolutional neural networks on two different binary classification tasks and measured the impact on dermoscopy images over a range of parameter values. The area under the curve and specificity‐at‐a‐given‐sensitivity values were measured for each artefact induced at each parameter. Results General blur had the strongest negative effect on the melanoma versus other task. Conversely, shifting the hue towards blue had a more pronounced effect on the suspicious versus follow task. Conclusions Classifiers should either mitigate artefacts or detect them. Images should be excluded from diagnosis/recommendation when artefacts are present in amounts outside the machine perceived quality range. Failure to do so will reduce accuracy and impede approval from regulatory agencies.

Introduction: Dermoscopic understanding of naevus characteristics is essential baseline knowledge for identifying early malignant changes.