Design method and device of super-resolution microscopic imaging equipment based on light field coding
By combining light field coding and neural networks, the problem of balancing resolution and field of view in traditional fluorescence microscopy has been solved, achieving efficient and portable high-throughput fluorescence imaging, restoring high-frequency information, and improving imaging quality.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- NANJING UNIV
- Filing Date
- 2026-05-21
- Publication Date
- 2026-07-17
AI Technical Summary
Traditional fluorescence microscopy is limited by the trade-off between spatial resolution and field of view, resulting in high-quality imaging relying on complex optical architectures, which limits portable, cost-effective and high-throughput applications, especially in resource-constrained environments.
A super-resolution lensless fluorescence imaging technique based on light field coding is employed. By separating fluorescence and excitation light through temporally staggered illumination and exposure, combined with spatial coding to modulate the fluorescence signal, and utilizing an end-to-end training framework of a differentiable imaging model and a super-resolution reconstruction neural network, high-resolution images are reconstructed.
It achieves high-resolution fluorescence imaging, surpasses the limitations of sensor pixel size, recovers high-frequency information that cannot be collected, improves imaging quality and throughput, and is suitable for resource-constrained environments.
Smart Images
Figure CN122410818A_ABST