Automated Skin Lesion and Cancer Detection Using Computer Vision: A Comprehensive Review

Detection of skin cancer has become an increasingly prevalent health issue for which there is a need for reliable methods of detection to improve patient outcomes, minimize delays in diagnosis, and ensure clinical referral. Advances in computer vision and artificial intelligence have allowed automatic analyses of dermoscopic, clinical, and smartphone imaging of skin lesions. While numerous models have been found to perform very well on the basis of curated benchmark datasets, their accuracy in practical settings still needs to be evaluated. This review critically evaluates the literature from 2015 to 2025. Rather than considering the Dice, Jaccard, AUC, sensitivity, and specificity metrics on an absolute basis, this review evaluates them relative to dataset quality, validation process, external testing, statistical analysis, and risk of bias. Key areas of focus include dataset imbalance, lack of coverage of darker skin, poor external validation, explainability, uncertainty quantification, and barriers to clinical adoption. This review provides valuable insights for researchers, practitioners, dataset producers, and healthcare providers involved in developing AI-enabled dermatology tools.