Our team has developed an AI-powered varifocal meta-optical endo-microscopy system that integrates a deep learning-based HiLo sectioning algorithm with a telecentric metalens design. By using a single input image, the system can reconstruct high-contrast optical sectioning images in real time, achieving a 50-fold improvement in processing efficiency. It has been successfully applied to in vivo microvascular imaging, demonstrating high resolution and real-time performance.

This system integrates a rotatable Moiré metalens with AI deep learning algorithms to achieve high-contrast, multi-depth, real-time 3D optical sectioning. The metalens features a telecentric design and compact structure, providing stable, high-quality images at various depths. Combined with an RCNN model, it enables HiLo section reconstruction from a single image, improving processing efficiency by up to 50 times.

Developed the “AI-powered Varifocal Meta-optics Endomicroscopy System,” which offers high-resolution, real-time imaging with minimal invasiveness, making it suitable for neurosurgical, cerebral vascular observation in high-precision clinical settings. Compared to confocal and multiphoton endoscopes, this system excels in compactness, imaging speed, and operational simplicity. With AI-based image reconstruction and a modular optical design, it holds strong potential for commercialization.