Artificial intelligence (AI) could help in the early detection of skin cancers, according to a study from Dalhousie University in Halifax. That is particularly important in Nova Scotia, which has one of the highest rates of skin cancer in Canada, as well as a lack of access to both primary healthcare providers and specialists.
In an article published in the Journal of Cutaneous Medicine and Surgery, researchers recruited 318 people over the age of 18 years who had self-identified one or more skin lesions (total lesion count, 381) that were of concern for cancer.
These lesions of concern were initially examined by a trained medical student and then scanned using the FotoFinder mole analysis system. The images were analyzed using FotoFinder’s proprietary computer software. Macroscopic and dermoscopic images were also evaluated by three experienced dermatologists and a senior dermatology resident, all blinded to the AI results. Suspicious lesions that were identified by AI or any of the three dermatologists were excised, and a total of 17 cancers were identified, 11 of which were melanoma.
The study found “the ability for the FotoFinder [AI] to be able to … detect skin cancers like melanoma was comparable and adequate to that of experienced dermatologists,” Madeleine Crawford, the paper's lead author and a third-year Dalhousie medical student, told CBC News.
The researchers noted there are limitations with the FotoFinder system—it cannot accurately assess lesions on patients with darker skin tones or on hairy parts of the body.
“We hope that this technology will continue to improve and be able to scan those darker skin tones as well because we are very diverse here in Nova Scotia,” added Rachel Dorey, also a third-year Dalhousie medical student and co-author of the paper.