Collective human intelligence outperforms artificial intelligence in a skin lesion classification task.

Background And Objectives: Convolutional neural networks (CNN) enable accurate diagnosis of medical images and perform on or above the level of individual physicians. Recently, collective human intelligence (CoHI) was shown to exceed the diagnostic accuracy of individuals. Thus, diagnostic performance of CoHI (120 dermatologists) versus individual dermatologists versus two state-of-the-art CNN was investigated.

Five patients with melanosis of the nipple and areola clinically mimicking melanoma.

Background: Pigmented lesions on the nipple and areola concern patients and physicians as melanoma and pigmented mammary Paget's disease must be considered in the differential diagnoses. There have been only six case reports of melanosis of the nipple and areola in the medical literature yet five cases presented to our department in a 26-month period.

Method: Five women aged between 26 and 34 years presented with pigmentation of the areola and/or nipple.

Development of a targeted risk-group model for skin cancer screening based on more than 100,000 total skin examinations.

Background: Skin cancer screening aims to detect potentially metastasizing skin cancers at an early and surgically curable stage. This may take the form of mass screening, as currently occurs in Germany, or of targeted screening of those at greatest risk.

Objective: To develop a model to identify patients at high risk of developing skin cancer who would benefit from regular skin cancer screening.