Cutaneous lymphomas (CLs) are a rare group of hematological skin cancers with a wide variety in clinical presentation, histopathology, and disease course. Due to the rarity of CLs, experience is mostly limited to expert centers. In order to improve clinical care and outcome of this rare patient population, adjunct diagnostic and prognostic tools are welcomed, especially by clinicians/pathologists without expertise in this field or with limited access to a specialized center.

Artificial Intelligence (AI)-based deep-learning techniques have demonstrated to be capable of identifying biomarkers that are both affordable and easy to translate into digital pathology worldwide. Deep learning can be used to extract subtle patterns from whole-slide pathology images (WSIs) that can aid in detecting specific subclasses and can be applied for complex diagnostic tasks. Especially rare diseases, like CLs, may benefit from these adjunct techniques. Currently, AI-based research within CLs is still in its infancy, partly due to the rarity of the diseases. To go along with these innovations in clinical care of CL patients, only a large international dataset would be sufficient to perform and validate meaningful AI-based research within this rare patient population. For this purpose, we founded the Cutaneous Lymphoma International Digital Pathology (CLIDIPA) Registry.