Physics-informed generative real-time lens-free imaging
This work addresses the need for real-time, large field-of-view imaging in high-throughput biomedical applications, representing a significant advancement over incremental improvements.
The paper tackles the limitations of current lens-free imaging systems, such as time-consuming measurements and strict optical parameterization, by introducing GenLFI, a generative unsupervised physics-informed neural network that enables real-time 2D imaging for 3D samples with a field-of-view exceeding 550 mm², over 20 times larger than existing real-time systems.
Advancements in high-throughput biomedical applications require real-time, large field-of-view (FOV) imaging. While current 2D lens-free imaging (LFI) systems improve FOV, they are often hindered by time-consuming multi-position measurements, extensive data pre-processing, and strict optical parameterization, limiting their application to static, thin samples. To overcome these limitations, we introduce GenLFI, combining a generative unsupervised physics-informed neural network (PINN) with a large FOV LFI setup for straightforward holographic image reconstruction, without multi-measurement. GenLFI enables real-time 2D imaging for 3D samples, such as droplet-based microfluidics and 3D cell models, in dynamic complex optical fields. Unlike previous methods, our approach decouples the reconstruction algorithm from optical setup parameters, enabling a large FOV limited only by hardware. We demonstrate a real-time FOV exceeding 550 mm$^2$, over 20 times larger than current real-time LFI systems. This framework unlocks the potential of LFI systems, providing a robust tool for advancing automated high-throughput biomedical applications.