Researchers at HHMI's Janelia Research Campus have developed an innovative AI method to produce sharp microscopy images of thick biological samples. This new technique addresses the common issue of depth degradation in microscopy, where images become increasingly fuzzy as the depth of the sample increases. By utilizing a neural network, the team successfully reversed image distortions without the need for additional hardware or complex adaptive optics.
The method, known as DeAbe, not only improves image clarity but also enhances the accuracy of biological assessments, such as counting cells in worm embryos and examining structures in mouse tissues. This deep learning-based approach is more accessible than traditional methods, requiring only a standard microscope and a computer with a graphics card. The Shroff Lab plans to further refine the model to broaden its applicability to various sample types.
• New AI method enhances microscopy images without additional hardware.
• DeAbe technique improves biological sample analysis accuracy significantly.
Deep learning is a subset of machine learning that uses neural networks to analyze data patterns.
A neural network is a computational model inspired by the human brain, used for pattern recognition.
Aberration compensation refers to techniques used to correct distortions in optical imaging.
Howard Hughes Medical Institute is a nonprofit medical research organization that supports innovative research in biology and medicine.
Microsoft is reportedly eyeing more of its own AI models into Copilot and reduce dependency on OpenAI. It's also exploring rivals such as DeepSeek and Meta.
The US Department of Justice is still calling for Google to sell its web browser Chrome, according to a Friday court filing. The DOJ first proposed
At SXSW, Signal President Meredith Whittaker warned about the 'profound' security risks to user privacy posed by agentic AI.
Producing high-performance titanium alloy parts -- whether for spacecraft, submarines or medical devices -- has long been a slow, resource-intensive process. Even with advanced metal 3D-printing techniques,