Convolutional neural network (CNN) has shown expert-level performance in the fields of ophthalmology, dermatology, and radiology.^1-9 Convolutional neural networks showed successful results in ophthalmologic emergency determination,¹⁰ brain hemorrhage detection with computed tomographic scan,⁴ and multiple-class cardiopulmonary disease classification with radiographic images.⁷ In ophthalmology, the IDx-DR diagnostic system (IDx Technologies Inc)¹¹ was approved by the US Food and Drug Administration to be used independently in screening for diabetic retinopathy.

Background: The diagnostic performance of convolutional neural networks (CNNs) for diagnosing several types of skin neoplasms has been demonstrated as comparable with that of dermatologists using clinical photography. However, the generalizability should be demonstrated using a large-scale external dataset that includes most types of skin neoplasms. In this study, the performance of a neural network algorithm was compared with that of dermatologists in both real-world practice and experimental settings. Methods and findings: To demonstrate generalizability, the skin cancer detection algorithm (https://rcnn.modelderm.com) developed in our previous study was used without modification. We conducted a retrospective study with all single lesion biopsied cases (43 disorders; 40,331 clinical images from 10,426 cases: 1,222 malignant cases and 9,204 benign cases); mean age (standard deviation [SD], 52.1 [18.3]; 4,701 men [45.1%]) were obtained from the Department of Dermatology, Severance Hospital in Seoul, Korea between January 1, 2008 and March 31, 2019. Using the external validation dataset, the predictions of the algorithm were compared with the clinical diagnoses of 65 attending physicians who had recorded the clinical diagnoses with thorough examinations in real-world practice. In addition, the results obtained by the algorithm for the data of randomly selected batches of 30 patients were compared with those obtained by 44 dermatologists in experimental settings; the dermatologists were only provided with multiple images of each lesion, without clinical information. With regard to the determination of malignancy, the area under the curve (AUC) achieved by the algorithm was 0.863 (95% confidence interval [CI] 0.852–0.875), when unprocessed clinical photographs were used. The sensitivity and specificity of the algorithm at the predefined high-specificity threshold were 62.7% (95% CI 59.9–65.1) and 90.0% (95% CI 89.4–90.6), respectively. Furthermore, the sensitivity and specificity of the first clinical impression of 65 attending physicians were 70.2% and 95.6%, respectively, which were superior to those of the algorithm (McNemar test; p < 0.0001). The positive and negative predictive values of the algorithm were 45.4% (CI 43.7–47.3) and 94.8% (CI 94.4–95.2), respectively, whereas those of the first clinical impression were 68.1% and 96.0%, respectively. In the reader test conducted using images corresponding to batches of 30 patients, the sensitivity and specificity of the algorithm at the predefined threshold were 66.9% (95% CI 57.7–76.0) and 87.4% (95% CI 82.5–92.2), respectively. Furthermore, the sensitivity and specificity derived from the first impression of 44 of the participants were 65.8% (95% CI 55.7–75.9) and 85.7% (95% CI 82.4–88.9), respectively, which are values comparable with those of the algorithm (Wilcoxon signed-rank test; p = 0.607 and 0.097). Limitations of this study include the exclusive use of high-quality clinical photographs taken in hospitals and the lack of ethnic diversity in the study population. Conclusions: Our algorithm could diagnose skin tumors with nearly the same accuracy as a dermatologist when the diagnosis was performed solely with photographs. However, as a result of limited data relevancy, the performance was inferior to that of actual medical examination. To achieve more accurate predictive diagnoses, clinical information should be integrated with imaging information.

Background: Botulinum toxin type A (BoNTA) is known to prevent fibroblast proliferation and expression of transforming growth factor beta 1 (TGF-β1). It also induces temporary muscle paralysis and decreases tension vectors. Fibroblasts induce scar contracture and hypertrophy by producing collagen fibers in wound healing processes. The aim of this study is to identify the effect of BoNTA on the scar formation. Methods: Forty-five patients with forehead laceration were enrolled in this study and randomized into 2 groups with or without injection of BoNTA. When the patients presented to the clinic to remove the stitches, BoNTA was injected to the BoNTA group with 24 patients and saline was injected to the control group with 21 patients. The BoNTA was injected on dermal layer with 5 IU/cm. After that, follow-up was done in 1, 3, and 6 months. The scars were analyzed with the patient and observer scar assessment scale, Stony Brook scar evaluation scales (SBSESs), and visual analog scale (VAS) and analyzed with independent T-test, along with clinical photographs, cutometer, and biopsies. Results: In all scar scales, the scores changed into favorable direction in both groups and the changes were larger in BoNTA group compared with the control group. On SBSES and VAS, better improvements on BoNTA group showed statistical significance. Skin biopsy showed less collagen deposition on dermal layer in BoNTA group. Conclusion: Improvement of aesthetic, functional, and emotional aspect of the scar formation in the groups treated with BoNTA was illustrated. The application of BoNTA may be expanded to prevent hypertrophic scar after trauma, burns, or operations.

Age-related changes in facial skin is a major concern in women. This study aimed to objectively evaluate normal skin elasticity and age-related differences in the faces of East Asian women. There are no standard values for data related to normal skin on East Asian women. We studied 129 healthy East Asian women without a history of cosmetic procedures or surgeries. Skin elasticity was assessed at the cheek and lower eyelid points, which were assessed on both the right and left sides of the face. The age of the subjects showed significant negative correlations with the R2 and R7 parameters, which represent skin elasticity after deformation. We therefore concluded that the primary decrease in skin elasticity in East Asian women occurs in the midface region.