A joint learning approach for automated diagnosis of keratinocyte carcinoma using optical attenuation coefficients

Keratinocyte carcinoma, such as Actinic Keratosis (AK) and Basal Cell Carcinoma (BCC), share similar clinical presentations but differ significantly in prognosis and treatment, highlighting the importance of effective screening. Optical coherence tomography (OCT) shows promise for diagnosing AK and BCC using signal intensity and skin layer thickness, but variability due to skin characteristics and system settings underscores the need for a standardized diagnostic method. Here, we propose an automated diagnostic method using the optical attenuation coefficient (OAC) and a joint learning strategy to classify AK, BCC, and normal skin. OAC images extracted from OCT data revealed notable disparities between normal and cancerous tissues. By incorporating probability distribution function (PDF) information alongside OAC images, the model achieved an accuracy of over 80% and approaching 100% by utilizing 3D OAC data to enhance robustness. This approach highlights the potential of OAC-based analysis for automated, intelligent diagnosis of early-stage non-melanoma skin cancers.