Can AI diagnose skin cancer from a photo at dermatologist accuracy ?
Cast your vote — then read what our editor and the AI models found.
Esteva et al. showed in Nature that a CNN could classify dermatology images at the level of board-certified dermatologists.
Current AI systems can analyze images of skin lesions and provide a diagnosis, but their accuracy is not yet on par with that of human dermatologists. Some studies have shown that deep learning-based systems can achieve high sensitivity and specificity in detecting skin cancer from images, but these results are often based on controlled datasets and may not generalize to real-world clinical settings. Additionally, AI systems may struggle with variability in image quality, lighting, and other factors that can affect diagnosis. While AI has the potential to augment dermatological diagnosis, it is not yet a replacement for human expertise.
— Enriched May 9, 2026 · Source: National Institute of Biomedical Imaging and Bioengineering — https://www.nibib.nih.gov
Gallery
No images yet — upload one below to start the gallery.
Disagree? Post your comment below.