This study presents the first application of convolutional neural networks to high-frequency ultrasound skin image classification. This type of imaging opens up new opportunities in dermatology, showing inflammatory diseases such as atopic dermatitis, psoriasis, or skin lesions. We collected a database of 631 images with healthy skin and different skin pathologies to train and assess all stages of the methodology. The proposed framework starts with the segmentation of the epidermal layer using a DeepLab v3+ model with a pre-trained Xception backbone. We employ transfer learning to train the segmentation model for two purposes: to extract the region of interest for classification and to prepare the skin layer map for classification confidence estimation. For classification, we train five models in different input data modes and data augmentation setups. We also introduce a classification confidence level to evaluate the deep model’s reliability. The measure combines our skin layer map with the heatmap produced by the Grad-CAM technique designed to indicate image regions used by the deep model to make a classification decision. Moreover, we propose a multicriteria model evaluation measure to select the optimal model in terms of classification accuracy, confidence, and test dataset size. The experiments described in the paper show that the DenseNet-201 model fed with the extracted region of interest produces the most reliable and accurate results.

Understanding the topography of facial skin thickness is crucial in plastic surgery and underpins the success of numerous reconstructive, oncological, transplant, volumetric, and aesthetic procedures. Objective: This study aims to assess facial skin thickness using high-frequency ultrasound, evaluate its correlation with age, anatomical location, and physical parameters, and create a comprehensive facial skin thickness map. Methods: High-frequency ultrasound (75 MHz, axial resolution 21 μm) was used to scan 38 anatomical sites on the faces of 45 patients aged 22–73 years from esthetic medicine clinics. Measurements were performed manually within the device software. Extensive statistical analysis was conducted to determine dominant thickness values, assess variations by location and age, and evaluate correlations between biometric variables (age, weight, height, BMI) and skin thickness at various facial sites. Based on these findings, a relative thickness index and detailed topographic map of facial skin were developed. Results: The thickest skin was observed in the lower third of the nose, particularly at the nasal apex (median: 1907 μm, IQR: 455.75 μm, p < 0.001), while the thinnest skin was on the upper eyelid (median: 573.50 μm, IQR: 128.75 μm, p < 0.001). Skin thickness was significantly influenced by anatomical location (p < 0.001, η² = 0.52), age (p < 0.001, η² < 0.01), and their interaction (p < 0.001, η² = 0.04), collectively accounting for approximately 57% of variance in skin thickness. Correlations between biometric parameters and skin thickness were generally weak, though a few strong correlations were found between specific facial sites. Conclusions: A detailed facial skin thickness map, including a relative thickness index, was developed.