Inequalities in the patterns of dermoscopy use and training across Europe: conclusions of the Eurodermoscopy pan-European survey.

BACKGROUND: Dermoscopy is a widely used technique, recommended in clinical practice guidelines worldwide for the early diagnosis of skin cancers. Intra-European disparities are reported for early detection and prognosis of skin cancers, however, no information exists about regional variation in patterns of dermoscopy use across Europe. OBJECTIVE: To evaluate the regional differences in patterns of dermoscopy use and training among European dermatologists. MATERIALS & METHODS: An online survey of European-registered dermatologists regarding dermoscopy training, practice and attitudes was established. Answers from Eastern (EE) versus Western European (WE) countries were compared and their correlation with their respective countries' gross domestic product/capita (GDPc) and total and government health expenditure/capita (THEc and GHEc) was analysed. RESULTS: We received 4,049 responses from 14 WE countries and 3,431 from 18 EE countries. A higher proportion of WE respondents reported dermoscopy use (98% vs. 77%, p<0.001) and training during residency (43% vs. 32%) or anytime (96.5% vs. 87.6%) (p<0.001) compared to EE respondents. The main obstacles in dermoscopy use were poor access to dermoscopy equipment in EE and a lack of confidence in one's skills in WE. GDPc, THEc and GHEc correlated with rate of dermoscopy use and dermoscopy training during residency (Spearman rho: 0.5-0.7, p<0.05), and inversely with availability of dermoscopy equipment. CONCLUSION: The rates and patterns of dermoscopy use vary significantly between Western and Eastern Europe, on a background of economic inequality. Regionally adapted interventions to increase access to dermoscopy equipment and training might enhance the use of this technique towards improving the early detection of skin cancers.

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/).