Making Light Work

Like noise-cancelling headphones that strip away background hum to reveal the music, a new imaging framework called WaveOrder cleans up blurry microscope data to recover clearer views of cells and tissues. Instead of simply sharpening images, it models how light travels through a sample and how a microscope distorts that signal, then works backwards to estimate the underlying structure in a feat of machine learning and physics computation. The approach can enhance contrast, reduce noise, and recover information such as cell organisation or molecular alignment (pictured, human lung cancer cells with information about tissue orientation clarified in colour) across several imaging techniques at once. The tool aims to turn messy images into more quantitative data and reveal features that would be otherwise hard to detect, which could help scientists study health and disease, improve the reliability of imaging, and ultimately push research forward.

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 Talon Chandler and colleagues
• Biohub, San Francisco, CA, USA
• Image originally published with a Creative Commons Attribution 4.0 International (CC BY 4.0)
• Published in Physics Optics arXiv, December 2025