Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists.

Background: Deep learning convolutional neural networks (CNN) may facilitate melanoma detection, but data comparing a CNN's diagnostic performance to larger groups of dermatologists are lacking. Methods: Google's Inception v4 CNN architecture was trained and validated using dermoscopic images and corresponding diagnoses. In a comparative cross-sectional reader study a 100-image test-set was used (level-I: dermoscopy only; level-II: dermoscopy plus clinical information and images). Main outcome measures were sensitivity, specificity and area under the curve (AUC) of receiver operating characteristics (ROC) for diagnostic classification (dichotomous) of lesions by the CNN versus an international group of 58 dermatologists during level-I or -II of the reader study. Secondary end points included the dermatologists' diagnostic performance in their management decisions and differences in the diagnostic performance of dermatologists during level-I and -II of the reader study. Additionally, the CNN's performance was compared with the top-five algorithms of the 2016 International Symposium on Biomedical Imaging (ISBI) challenge. Results: In level-I dermatologists achieved a mean (±standard deviation) sensitivity and specificity for lesion classification of 86.6% (±9.3%) and 71.3% (±11.2%), respectively. More clinical information (level-II) improved the sensitivity to 88.9% (±9.6%, P = 0.19) and specificity to 75.7% (±11.7%, P < 0.05). The CNN ROC curve revealed a higher specificity of 82.5% when compared with dermatologists in level-I (71.3%, P < 0.01) and level-II (75.7%, P < 0.01) at their sensitivities of 86.6% and 88.9%, respectively. The CNN ROC AUC was greater than the mean ROC area of dermatologists (0.86 versus 0.79, P < 0.01). The CNN scored results close to the top three algorithms of the ISBI 2016 challenge. Conclusions: For the first time we compared a CNN's diagnostic performance with a large international group of 58 dermatologists, including 30 experts. Most dermatologists were outperformed by the CNN. Irrespective of any physicians' experience, they may benefit from assistance by a CNN's image classification. Clinical trial number: This study was registered at the German Clinical Trial Register (DRKS-Study-ID: DRKS00013570; https://www.drks.de/drks_web/).

[Axillary and perimamillary Fox-Fordyce disease (apocrine miliaria) in a 19-year-old woman]. / Axilläre und perimamilläre Fox-Fordyce-Erkrankung (apokrine Miliaria) bei einer 19-jährigen Patientin.

Fox-Fordyce disease (FFD), also known as apocrine miliaria, is a rare and chronic skin disease characterized by itching and skin-colored, light brown or yellowish papules. FFD typically affects postpubertal young women between 13 and 35 years. The etiology is not completely known, but a hormonal component is in discussion. Furthermore, exacerbating factors like laser hair removal and hyperhidrosis have been described. Treatment of FFD is quite challenging, as the reported modalities mostly show limited success.

At first sight or second glance: clinical presentation of mosaic manifestations of autosomal dominant skin disorders - a case series.

BACKGROUND: Several autosomal dominant disorders may manifest in mosaic patterns with cutaneous involvement. Genomic mosaicism results from postzygotic autosomal mutations, giving rise to clonal proliferation of two genetically distinct cell groups, which clinically present as lesions following the lines of Blaschko. OBJECTIVE: To increase the awareness of the clinical variability of mosaic manifestations in autosomal dominant skin disorders in order to avoid delayed diagnosis. METHODS: Clinicopathologic correlation in a case series including three patients with mosaic manifestations of different autosomal dominant skin diseases. RESULTS: Here, we describe a patient with type 1 segmental mosaicism of epidermolytic ichthyosis (case 1) and two patients with either type 1 (case 2) or type 2 (case 3) segmental neurofibromatosis 1 (NF1). CONCLUSION: Dermatologists should be familiar with mosaic manifestations of autosomal dominant skin diseases to ensure appropriate guidance of the affected patient. Genetic counselling is mandatory as even limited forms of mosaicism may involve the patient's germline with a moderately increased risk to transmit the mutation to their offspring, resulting in a more severe, generalized form of the respective disease.