The main method of skin cancer detection continues to be direct examination of the skin by a trained professional. Dermatologists are the most skilled at skin examination but there is a shortage of dermatologists in the US and other countries, a situation that could influence timely diagnosis and management of skin cancer.
The use of teledermatology and teledermoscopy could overcome some of these barriers, particularly barriers of geographic distance, availability of dermatologists, poor communication with specialists, and coordination of care. The problem is that although some dermatology resident programs do train their residents in teledermatology and the practice guidelines associated with this modality 9.f care, the majority of dermatologists have not been trained in the interpretation of images associated with a teledermatologic exam.
In order to develop appropriate and effective training programs, we first need to better understand how dermatologists typically view digital skin images in the process of rendering a diagnostic and/or treatment decision, and whether training impacts this interpretation process. For more than 25 years, we have been studying how expertise develops in those interpreting medical images. Much of the work has been done in radiology and in the past 10 years we have conducted a number of pathology studies, as well.
A key tool in these studies has been the use of eye-tracking technology that allows us to observe and record exactly how a clinician visually examines an image -where they look, how long they look at a given location, and whether and how long they look at a lesion/area of interest. Our goal in this study is to obtain pilot data for submitting an R21 or R01 to the NIH. We will characterize the visual search patterns of dermatologists evaluating images corresponding to single pigmented skin lesions (close-ups and dermoscopy), have each reader undergo on-line ceroscopy training, then repeat the visual assessment for changes in search behavior.