Researchers developed a physics-based machine learning imaging system that enhances visibility through complex media, holding promise for biomedical imaging.
Key Details
- 1Team from UCLA and University of Rochester improved a light-scattering imaging system using AI (DeepTimeGate).
- 2The new method more than doubled the signal-to-noise ratio versus previous technologies.
- 3Creates images in real time (thousandths of a second) using standard silicon-based cameras.
- 4System reconstructed images with fewer artifacts and broader field of view.
- 5Potential biomedical uses include guiding surgeries and analyzing cloudy blood samples without dilution.
- 6Published in Nature Light: Science & Applications; funded by ONR, NSF, DOE.
Why It Matters
Real-time, affordable imaging through complex media can enable safer, more accessible biomedical diagnostics and surgical guidance using widely available camera hardware. This intersection of physics-based AI and radiology opens new frontiers in tissue imaging and laboratory workflows.
Source
EurekAlert
Related News
•EurekAlert
NYU AI Model Improves 5-Year Breast Cancer Risk Prediction via 3D Mammograms
NYU researchers developed an AI model using longitudinal 3D mammograms that outperforms single-scan and 2D-based tools in predicting 5-year breast cancer risk.
•EurekAlert
AI Framework Accelerates Aortic Aneurysm Risk Prediction from Imaging
Researchers developed BioPINN-LM, combining physics-informed neural networks and multimodal large language models to deliver fast, interpretable risk assessments for ascending thoracic aortic aneurysms.
•EurekAlert
Study Finds Patient Voices Missing in Generative AI Design for Oncology
A Flinders University-led review found patients and carers are rarely involved in shaping generative AI tools used in oncology.