Dermoscopy of haemosiderotic/aneurysmal dermatofibroma: A morphological study of 110 cases.

BACKGROUND: Haemosiderotic and aneurysmal dermatofibromas are uncommon and frequently misdiagnosed lesions, which can be considered as different histopathological stages of the same tumour. A dermoscopic diagnosis testing accuracy has not been performed for these tumours to date. OBJECTIVES: To determine the diagnostic significance of dermoscopic structures and patterns associated with haemosiderotic/ aneurysmal dermatofibromas in a large series. METHODS: Dermoscopic images of histopathologically proven cases of 110 haemosiderotic/ aneurysmal dermatofibromas and 501 other tumours were collected. The frequency, sensitivity, specificity, positive predictive value and negative predictive value of the dermoscopic structures and patterns associated with these lesions were calculated. RESULTS: Haemosiderotic/ aneurysmal dermatofibromas are mostly symmetric lesions (86.5%), and a prominent homogeneous area was present in 100% of them. The presence of vascular structures was very common (86.4%), and dotted vessels were predominant (58.2%). Shiny white structures were seen in 85.5% of lesions, while a peripheral delicate pigment network was present in 69.1%. The most significant pattern was the one composed of a prominent homogeneous area and peripheral delicate pigment network, which showed a specificity of 100% with a relatively good sensitivity (69.1%). All the patterns containing a peripheral delicate pigment network showed very good specificities, positive predictive values and negative predictive values. Those patterns without a peripheral delicate pigment network showed the highest sensitivities, but they showed a significant overlap with other tumours, mainly with melanoma. CONCLUSIONS: Dermoscopy is helpful in improving the diagnostic accuracy of haemosiderotic/ aneurysmal dermatofibromas. However, there is a considerable dermoscopic overlap between these tumours and melanoma, specifically when the peripheral delicate pigment network is absent.

Effects of COVID-19 Lockdown on Tumour Burden of Melanoma and Cutaneous Squamous Cell Carcinoma.

The aim of this study was to compare tumour burden in patients who underwent surgery for melanoma and cutaneous squamous cell carcinoma during nationwide lockdown in Spain due to COVID-19 (for the period 14 March to 13 June 2020) and during the same dates in 2019 before the COVID-19 pandemic. In addition, associations between median tumour burden (Breslow thickness for melanoma and maximum clinical diameter for cutaneous squamous cell carcinoma) and demographic, clinical, and medical factors were analysed, building a multivariate linear regression model. During the 3 months of lockdown, there was a significant decrease in skin tumours operated on (41% decrease for melanoma (n = 352 vs n = 207) and 44% decrease for cutaneous squamous cell carcinoma (n = 770 vs n = 429)) compared with the previous year. The proportion of large skin tumours operated on increased. Fear of SARS-CoV-2 infection, with respect to family member/close contact, and detection of the lesion by the patient or doctor, were related to thicker melanomas; and fear of being diagnosed with cancer, and detection of the lesion by the patient or relatives, were related to larger size cutaneous squamous cell carcinoma. In conclusion, lockdown due to COVID-19 has resulted in a reduction in treatment of skin cancer.

A novel approach for skin lesion symmetry classification with a deep learning model.

Skin cancer has become a public health problem due to its increasing incidence. However, the malignancy risk of the lesions can be reduced if diagnosed at an early stage. To do so, it is essential to identify particular characteristics such as the symmetry of lesions. In this work, we present a novel approach for skin lesion symmetry classification of dermoscopic images based on deep learning techniques. We use a CNN model, which classifies the symmetry of a skin lesion as either "fully asymmetric", "symmetric with respect to one axis", or "symmetric with respect to two axes". Moreover, we introduce a new dataset of labels for 615 skin lesions. During the experimentation framework, we also evaluate whether it is beneficial to rely on transfer learning from pre-trained CNNs or traditional learning-based methods. As a result, we present a new simple, robust and fast classification pipeline that outperforms methods based on traditional approaches or pre-trained networks, with a weighted-average F1-score of 64.5%.

Acute generalized exanthematous pustulosis induced by terbinafine.

Terbinafine is an allylamine fungicidal agent that is widely used for the treatment of onychomycoses and other fungal infections. Adverse effects may occur in more than 10% of patients receiving oral terbinafine, with cutaneous reactions in 2.7%. We describe the development of acute generalized exanthematous pustulosis in a 36-year-old woman who took oral terbinafine.