Deep Convolutional Neural Support Vector Machines for the Classification of Basal Cell Carcinoma Hyperspectral Signatures.

Non-melanoma skin cancer, and basal cell carcinoma in particular, is one of the most common types of cancer. Although this type of malignancy has lower metastatic rates than other types of skin cancer, its locally destructive nature and the advantages of its timely treatment make early detection vital. The combination of multispectral imaging and artificial intelligence has arisen as a powerful tool for the detection and classification of skin cancer in a non-invasive manner. The present study uses hyperspectral images to discern between healthy and basal cell carcinoma hyperspectral signatures. Upon the combined use of convolutional neural networks, with a final support vector machine activation layer, the present study reaches up to 90% accuracy, with an area under the receiver operating characteristic curve being calculated at 0.9 as well. While the results are promising, future research should build upon a dataset with a larger number of patients.

Hyperspectral imaging and robust statistics in non-melanoma skin cancer analysis.

Non-Melanoma skin cancer is one of the most frequent types of cancer. Early detection is encouraged so as to ensure the best treatment, Hyperspectral imaging is a promising technique for non-invasive inspection of skin lesions, however, the optimal wavelengths for these purposes are yet to be conclusively determined. A visible-near infrared hyperspectral camera with an ad-hoc built platform was used for image acquisition in the present study. Robust statistical techniques were used to conclude an optimal range between 573.45 and 779.88 nm to distinguish between healthy and non-healthy skin. Wavelengths between 429.16 and 520.17 nm were additionally found to be optimal for the differentiation between cancer types.

Spectrum of Clinicopathologic Findings in COVID-19-induced Skin Lesions: Demonstration of Direct Viral Infection of the Endothelial Cells.

The novel coronavirus disease (COVID-19) is a rapidly spreading pandemic, secondary to severe acute respiratory syndrome coronavirus 2. The severity and the little knowledge that we have of the disease have made us focus mostly on the respiratory symptoms. As we bend the curve, other findings reported in association with COVID-19 become of importance for specialists to recognize. We describe the spectrum of clinicopathologic lesions in the skin that can be the only symptom or the first manifestation of COVID-19 and demonstrate the origin of the virus. We collected 25 patients with skin lesions in this context. We recognized 5 types of cutaneous manifestations including acute acroischemic or chilblain-like lesions (11), purpura palpable (2), exanthemas (9), urticarial eruptions (1), and other lesions (2) that might appear with more unspecific pictures. Chilblain-like lesions were the most common form of presentation, which tend to appear as self-healing, erythematous-necrotic plaques mostly on the feet, in young patients with no systemic symptoms associated. Importantly, we visualized viral particles with electron microscopy in 5 of 13 cases analyzed. In this study, we seek to draw a picture of the spectrum of clinicopathologic lesions that may appear in the skin in the context of COVID-19. Although apparently skin lesions are not correlated with disease severity, it may help in some cases to recognize and control the spread of the infection sooner.

Maculopapular eruptions associated to COVID-19: A subanalysis of the COVID-Piel study.

A previous study has defined the maculopapular subtype of manifestations of COVID-19. The objective of our study was to describe and classify maculopapular eruptions associated with COVI-19. We carried out a subanalysis of the maculopapular cases found in the previous cross-sectional study. Using a consensus, we defined seven clinical patterns. We described patient demographics, the therapy received by the patient and the characteristics of each pattern. Consensus lead to the description of seven major maculopapular patterns: morbilliform (45.5%), other maculopapular (20.0%), purpuric (14.2%), erythema multiforme-like (9.7%), pytiriasis rosea-like (5.7%), erythema elevatum diutinum-like (2.3%), and perifollicular (2.3%). In most cases, maculopapular eruptions were coincident (61.9%) or subsequent (34.1%) to the onset of other COVID-19 manifestations. The most frequent were cough (76%), dyspnea (72%), fever (88%), and astenia (62%). Hospital admission due to pneumonia was frequent (61%). Drug intake was frequent (78%). Laboratory alterations associated with maculo-papular eruptions were high C-reactive protein, high D-Dimer, lymphopenia, high ferritin, high LDH, and high IL-6. The main limitation of our study was the impossibility to define the cause-effect relationship of each pattern. In conclusion, we provide a description of the cutaneous maculopapular manifestations associated with COVID-19. The cutaneous manifestations of COVID-19 are wide-ranging and can mimic other dermatoses.

Cutaneous collagenous vasculopathy: papular form.

Cutaneous collagenous vasculopathy is a rare clinicopathological entity, first described in 2000. Cutaneous collagenous vasculopathy has been considered a form of microangiopathy of superficial dermal vessels and produce lesions that appear as telangiectasia. We present a patient with histopathologic features of cutaneous collagenous vasculopathy and scattered erythematous papules on the trunk with a striking dermatoscopic finding. We propose the term of 'cutaneous papular collagenous vasculopathy' as a new clinical manifestation of this disease.