TUESDAY, Nov. 3, 2026 (HealthDay News) -- An artificial intelligence (AI) tool may help dermatologists determine whether skin lesions are cancerous and inform clinical decisions about whether to biopsy or monitor them, according to a study published online Oct. 21 in Mayo Clinic Proceedings.Katherine Holder, M.D., from the Mayo Clinic in Rochester, Minnesota, and colleagues assessed the correlation between the Dermoscopy Explainable Intelligence (DEXI) score (trained on more than 66,000 annotated dermoscopy images) and histopathologically confirmed melanoma and nonmelanoma skin cancer. The analysis included 178 patients who underwent total body photography by the Vectra WB360 system (Canfield Scientific Inc.), sequential digital dermoscopy imaging, and subsequent biopsy of one or more skin lesions between May 1, 2023, and Aug. 30, 2024.The researchers reported that of the 261 lesions, 160 were benign with an average corresponding DEXI score of 2.5, 65 cases were nonmelanoma skin cancer with an average DEXI score of 7.8, and 14 cases were melanoma with an average DEXI score of 6.0. Compared with benign lesions, DEXI scores from malignant lesions were statistically significantly higher. With a DEXI score cutoff of 3.0 points, sensitivity was 93.7 percent and specificity was 75 percent for differentiating benign from malignant disease."We identified 3.0 as a potential DEXI score threshold that could provide useful information when dermatologists are considering whether to monitor a lesion or perform a biopsy," lead author Jenny Link, M.D., also from the Mayo Clinic, said in a statement. "The score must be interpreted alongside clinical findings and patient-specific factors, and the tool requires further validation and refinement."Abstract/Full Text (subscription or payment may be required).Sign up for our weekly HealthDay newsletter