OCT in dermatology: a process for determining whether a fully diversified dataset is needed for AI model-building

Optical coherence tomography (OCT) has sufficient depth penetration for detection of skin pathologies, but its detection effectiveness can be aided by the assistance of artificial intelligence (AI) modeling. AI model-building identifies pathologies by comparing images from healthy and diseased tissues, but healthy skin can present as quite variable across skin types and ages. Here, we selected a commonly used parameter for skin analysis and attenuation coefficient and analyzed how it varied in the dermis and epidermis, and in skin-exposed and skin-protected regions, for 100 subjects from a wide range of skin types (Fitzpatrick types I-V) and ages (13-83). For the statistical analysis, we report whether comparisons of the dermis and epidermis and sun-exposed and sun-protected areas across age and skin type are statistically significant, indeterminate, or not statistically significant and present 95% confidence intervals for this parameter as it ranges across different ages and skin types. This process of pre-analyzing features using healthy images provides a roadmap for how to ease the recruitment process while acquiring a sufficient range of images for effective AI model-building. We expect this type of analysis can have the effect of accelerating translation of AI-based OCT image analysis to the clinic.