Search

Background Recent studies have successfully demonstrated the use of deep-learning algorithms for dermatologist-level classification of suspicious lesions by the use of excessive proprietary image databases and limited numbers of dermatologists. For the first time, the performance of a deep-learning algorithm trained by open-source images exclusively is compared to a large number of dermatologists covering all levels within the clinical hierarchy. Methods We used methods from enhanced deep learning to train a convolutional neural network (CNN) with 12,378 open-source dermoscopic images. We used 100 images to compare the performance of the CNN to that of the 157 dermatologists from 12 university hospitals in Germany. Outperformance of dermatologists by the deep neural network was measured in terms of sensitivity, specificity and receiver operating characteristics. Findings The mean sensitivity and specificity achieved by the dermatologists with dermoscopic images was 74.1% (range 40.0%–100%) and 60% (range 21.3%–91.3%), respectively. At a mean sensitivity of 74.1%, the CNN exhibited a mean specificity of 86.5% (range 70.8%–91.3%). At a mean specificity of 60%, a mean sensitivity of 87.5% (range 80%–95%) was achieved by our algorithm. Among the dermatologists, the chief physicians showed the highest mean specificity of 69.2% at a mean sensitivity of 73.3%. With the same high specificity of 69.2%, the CNN had a mean sensitivity of 84.5%. Interpretation A CNN trained by open-source images exclusively outperformed 136 of the 157 dermatologists and all the different levels of experience (from junior to chief physicians) in terms of average specificity and sensitivity.

Background: Recent studies have demonstrated the use of convolutional neural networks (CNNs) to classify images of melanoma with accuracies comparable to those achieved by board-certified dermatologists. However, the performance of a CNN exclusively trained with dermoscopic images in a clinical image classification task in direct competition with a large number of dermatologists has not been measured to date. This study compares the performance of a convolutional neuronal network trained with dermoscopic images exclusively for identifying melanoma in clinical photographs with the manual grading of the same images by dermatologists. Methods: We compared automatic digital melanoma classification with the performance of 145 dermatologists of 12 German university hospitals. We used methods from enhanced deep learning to train a CNN with 12,378 open-source dermoscopic images. We used 100 clinical images to compare the performance of the CNN to that of the dermatologists. Dermatologists were compared with the deep neural network in terms of sensitivity, specificity and receiver operating characteristics. Findings: The mean sensitivity and specificity achieved by the dermatologists with clinical images was 89.4% (range: 55.0%-100%) and 64.4% (range: 22.5%-92.5%). At the same sensitivity, the CNN exhibited a mean specificity of 68.2% (range 47.5%-86.25%). Among the dermatologists, the attendings showed the highest mean sensitivity of 92.8% at a mean specificity of 57.7%. With the same high sensitivity of 92.8%, the CNN had a mean specificity of 61.1%. Interpretation: For the first time, dermatologist-level image classification was achieved on a clinical image classification task without training on clinical images. The CNN had a smaller variance of results indicating a higher robustness of computer vision compared with human assessment for dermatologic image classification tasks. (C) 2019 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Purpose Recent studies highlighted that early diabetic neurodegeneration is present before microvascular changes are visible. Retinal neurodegeneration can decrease retinal layer thickness. We aimed to determine whether decreased retinal layer thickness is present already in the early time course of disease. Methods A cross-sectional analysis of patients and healthy adults from the German Diabetes Study (GDS, ClinicalTrials.gov Identifier number: CT01055093, https://clinicaltrials.gov/ct2/show/NCT01055093). Inclusion criteria were a diagnosis of diabetes mellitus (DM) within the last 12 months. Retinal layers thickness in the nasal pericentral segment was measured by spectral domain ocular coherence tomography (SD-OCT). For statistical analysis proc mixed (sas-version 9.4) was used. Results One hundred and seventy-eight eyes of 89 patients with type 1 DM (58 males, age 36 ± 11 years, BMI 25.5 ± 4.2 kg/m²) and 242 eyes of 121 patients with type 2 DM (84 males, age 53 ± 10 years, BMI 31.9 ± 6.3 kg/m²) with a disease duration of less than 1 year were compared to 76 eyes of 38 controls (27 males, age 41 ± 16 years, BMI 27.3 ± 6.4 kg/m²). Analysis of retinal layer thickness and visual function did not reveal a significant difference between patients and controls. Conclusion In the early course of DM potential, neurodegeneration does not relate to measureable changes of retinal layer thickness.