Deep learning segments hair and analyzes skin for laser treatments
Hair Segmentation and Skin Characterization on Macroscopic Dermatological Images for Laser Treatment Parameterization
Computer Vision and Pattern Recognition
Summary
Setting the right laser settings for skin treatments often depends on guessing skin and hair features, which can be unreliable. The authors created a method that uses AI and image processing to accurately identify hair and skin characteristics from regular photos, not just special controlled ones. This includes measuring hair thickness, density, and skin color type, which can help make laser treatments safer and more effective. Their approach also adjusts for lighting differences to keep measurements consistent.
What this means in practice
- •For clinical dermatology teams: Use automatic hair and skin analysis to set laser treatment parameters more objectively and consistently.
- •For medical device manufacturers: Integrate calibrated image-based hair and skin feature detection to improve light-based medical device automation and personalization.$Commercial implications: This enables development of laser systems that automatically tune settings per patient, improving ease of use and treatment outcomes.
Authors
Alex Navarro Navarro, Marc Arriaga Hidalgo, Carlos Moreno Rubio, Maxime Talarmain, Noelia Vaquero Gallardo
Abstract
Current light-based devices, such as laser hair removal, intense pulsed light (IPL), vascular laser therapy, and dermatologic phototherapy, are widely used in clinical dermatology but rely heavily on subjective manual parameterization or uncalibrated point-based colorimeters. To overcome these limitations, this work presents a unified system for hair segmentation and skin characterization in macroscopic dermatological images. Unlike most existing literature that relies on dermoscopic datasets captured under highly controlled conditions, our approach is specifically designed for macroscopic images that replicate real clinical laser treatments. The proposed pipeline integrates a custom-trained variant of the YOLOv9 deep learning architecture for instance segmentation and classical image processing within a single workflow to extract objective skin and hair parameters such as phototype, hair density, color, and thickness. A color calibration stage using spectrophotometric measurements ensures accurate feature estimation regardless of illumination conditions. Experimental results show competitive segmentation metrics (mAP@50 $\approx$ 0.80) on a custom dataset featuring short, shaved hairs, typical of pre-treatment scenarios. These findings demonstrate the feasibility of the proposed pipeline in providing the objective, foundational skin and hair features required for future automated laser parameterization, paving the way for its extension to broader light-based medical therapies.