Segmentation of skin layers on HFUS images using the attention mechanism - exper masks

The database is associated with the publication:
A. Slian, K. Korecka, A. Polanska, and J. Czajkowska, “Segmentation of skin layers on HFUS images using the attention mechanism,” Computer Methods and Programs in Biomedicine, vol. 263, pp. 1–11, 2025, doi: 10.1016/j.cmpb.2025.108668.
The dataset consists of high-frequency ultrasound (HFUS) images acquired using the DermaScan C device (Cortex Technology) with a 20 MHz probe. Each image has a resolution of 224 × 224 pixels. The images were collected from patients diagnosed with atopic dermatitis (AD).

The dataset contains the following components:
1. Original images – input HFUS images (224 × 224 px)
2. Entry echo layer masks – segmentation masks of the entry echo layer (224 × 224 px)
3. SLEB masks – segmentation masks of the subepidermal low echogenic band (SLEB), if present (224 × 224 px)
4. Dermis masks – segmentation masks of the dermis (224 × 224 px)

The file names are encoded as follows:
patientID_imageID.png, where imageID values 1 and 2 correspond to different time points.
Experts manually annotated the following skin layers (each covering half of the image height): the entry echo, the SLEB (if present), and the dermis.