Connect the Dots

Without looking, is there a small freckle on the back of your hand? Are you sure? Small, innocuous flourishes on the skin are easy to miss, and hard to keep track of. But accurately assessing skin marks is important to dermatologists, and a new computer vision technology could reduce reliance on subjective visual assessments. The approach identifies target regions of skin, generates an energy map that makes freckles stand out, enhances contrast and then segments (partitions the images into regions) freckles. Compared to standard colour-based segmentation (left), the technology showed improved accuracy (right, with greater overlap (green) between the model’s predictions (red) and the actual freckle pattern (blue)). Software that can identify details as subtle as freckles could improve non-invasive assessment for automated screening of skin diseases, monitoring skin changes over time, or even be applied to identifying important subtle differences in contrast between other types of tissue, such as when analysing wound healing.

Written by Anthony Lewis

Anthony Lewis

Writer

Ant was the web editor in the early days of BPoD, and has since worked with the UK’s top science organisations as a writer and multimedia producer. He now splits his time between freelance work and managing multimedia at The Lancet.

Website

• Image from work by Yeong-Su Lim, Myeong Jin Ju & Hee-Jae Jeon
• Department of Smart Health Science and Technology, Kangwon National University, Chuncheon, Korea
• Image originally published with a Creative Commons Attribution – NonCommercial – NoDerivs (CC BY-NC-ND 4.0)
• Published in Scientific Reports, October 2025