Lali Mekokishvili

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/).

BACKGROUND: When used correctly, dermoscopy is an essential tool for helping clinicians in the diagnosis of skin diseases and the early detection of skin cancers. Despite its proven benefits, there is a lack of data about how European dermatologists use dermoscopy in everyday practice. OBJECTIVES: To identify the motivations, obstacles and modifiable factors influencing the use of dermoscopy in daily dermatology practice across Europe. METHODS: All registered dermatologists in 32 European countries were invited to complete an online survey of 20 questions regarding demographic and practice characteristics, dermoscopy training and self-confidence in dermoscopic skills, patterns of dermoscopy use, reasons for not using dermoscopy and attitudes relating to dermoscopy utility. RESULTS: We collected 7480 valid answers, of which 89% reported use of dermoscopy. The main reasons for not using dermoscopy were lack of equipment (58% of nonusers) and lack of training (42%). Dermoscopy training during residency was reported by 41% of dermoscopy users and by 12% of nonusers (P < 0·001). Dermatologists working in public hospitals were the least likely to use dermoscopy. High use of dermoscopy across the spectrum of skin diseases was reported by 62% of dermoscopy users and was associated with dermoscopy training during residency, the use of polarized light and digital dermoscopy devices, longer dermoscopy practice, younger age and female gender. CONCLUSIONS: Expanding access to dermoscopy equipment, especially in public healthcare facilities and establishing dermoscopy training during dermatology residency would further enhance the substantially high dermoscopy use across European countries.

Acne scars are the ultimate outcome of acne vulgaris, a prevalent skin disorder affecting the pilo-sebaceous unit. Laser resurfacing has been demonstrated to be an efficient therapy option for acne scars. Hence, we adopted this concept and conducted a study to evaluate the safety and efficacy of low-energy double-pass 1450-nm diode laser on acne scars. This study was conducted on 48 patients with acne scars, treated at 4-week interval with low-energy double-pass 1450-nm diode laser. Patients were evaluated clinically and with photographs, at day 0, first month and third month post the final treatment and during follow-up visit. Five treatment sessions were completed by all patients. Approximately, 79.2% of patients showed around 30% improvement. At the end of third month follow-up, 92.9% of the patients demonstrated >30% improvement. Vesicle formation was observed in two cases, with no post-inflammatory hyperpigmentation and transient hyperpigmentation was observed in one case, which vanished within 2 months. Our study showed that 1450-nm diode laser treatment was efficient and well endured in facial acne scars when used with double-pass at low-energy.