Generalizable Deep Learning Approach for 3D Particle Imaging using Holographic Microscopy

Despite its potential for label-free particle diagnostics, holographic microscopy is limited by specialized processing methods that struggle to generalize across diverse settings. We introduce a deep learning architecture leveraging human perception of longitudinal variation of diffracted patterns of particles, which enables highly generalizable analysis of 3D particle information with orders of magnitude improvement in processing speed. Trained with minimal synthetic and real holograms of simple particles, our method demonstrates exceptional performance on various challenging cases including those with high particle concentrations and noises and a wide range of particle sizes, complex shapes, and optical properties exceeding the diversity of the training datasets.