Abstract Timely management of patients referred with suspected skin cancer remains challenging due to demand that exceeds the capacity of dermatology departments. Encouraging the attachment of images and key metadata along with referrals from primary care helps promote enhanced clinical referral triage. We describe the process of establishing Community and Locality Imaging Centres (CLICs) that seek not only to promote efficient triage, but also to establish a national pipeline of anonymized images, with linked Digital Imaging and Communications in Medicine (DICOM®) data, to assess the potential for future use of artificial intelligence (AI) algorithms in clinical practice. General practitioners (GPs) can request a CLIC appointment at the time of referral, removing the time pressure and potential technical barriers associated with photography and image attachment. Each centre follows the same standardized image capture and hardware operating procedure, ensuring that high-quality, in-focus digital images are consistently acquired. The CLIC appointments take an average of 15 min, during which a suitably trained healthcare professional obtains written patient consent and, using a National Health Service-approved mobile phone with a dermatoscope attachment, takes paired macroscopic and dermoscopic views of each lesion. Relevant metadata, in line with the recently agreed DICOM standards for dermatology, are recorded for individual lesions, enhancing the utility of each photograph. Paired images and metadata are regularly archived to a secure medical image management system and are linked with the referral, allowing dermatologists to perform enhanced clinical triage and communicate one of the following outcomes directly to the referring GP: routine dermatology appointment, urgent dermatology appointment, direct to biopsy or benign lesion–reassurance and discharge. This process aims to streamline the primary care referral pathway and promote immediate benefits to patient care by reducing unnecessary travel for face-to-face outpatient appointments. The establishment of CLICs in Scotland supports referral optimization by providing an efficient, convenient option for GPs and patients to obtain high-quality clinical photography. This model allows for flexible integration into local services: hospital-based with medical photographers, intermediate secondary care-led centres or community-based primary care hubs. Suspected skin cancer referrals can be efficiently triaged by dermatologists when paired with macroscopic and dermoscopic images and relevant patient metadata compliant with DICOM standards. The same images and metadata, once anonymized, can be securely transferred to a nationwide database for deep learning AI algorithm development. Validated AI programs, with the aim of being deployed at the primary care level, inform opportunities for further enhancement of the referral pathway.
Read full abstract