Epidermal segmentation in high-definition optical coherence tomography.

Area of Science:

• Dermatology
• Medical Imaging
• Biomedical Engineering

Background:

• Accurate epidermis segmentation is vital for dermatological applications.
• High-definition optical coherence tomography (HD-OCT) offers advanced subsurface skin imaging.
• Existing segmentation methods may lack precision or efficiency.

Purpose of the Study:

• To propose a novel, automated method for epidermis segmentation using HD-OCT.
• To validate the proposed method against manual segmentation techniques.
• To establish an effective and rapid tool for clinical and research use.

Main Methods:

• A three-step segmentation process was developed: weighted least square pre-processing, graph-based skin surface detection, and local integral projection-based dermal-epidermal junction detection.
• The method utilizes high-definition optical coherence tomography (HD-OCT) for subsurface skin imaging.
• Validation was performed using a dataset of five 3D volumes.

Main Results:

• The proposed HD-OCT based segmentation method demonstrated strong correlation with manual segmentation.
• The method effectively and rapidly delineated the epidermis.
• Quantitative and qualitative assessments confirmed the accuracy of the segmentation.

Conclusions:

• The novel epidermis segmentation method using HD-OCT is accurate and efficient.
• This technique provides a valuable tool for the study and clinical management of skin diseases.
• The method facilitates precise delineation of skin layers in dermatological imaging.