Deep-learning-augmented computational miniature mesoscope

Fluorescence microscopy is essential to study biological structures and dynamics. However, existing systems suffer from a trade-off between field of view (FOV), resolution, and system complexity, and thus cannot fulfill the emerging need for miniaturized platforms providing micron-scale resolution across centimeter-scale FOVs. To overcome this challenge, we developed a computational miniature mesoscope (CM²) that exploits a computational imaging strategy to enable single-shot, 3D high-resolution imaging across a wide FOV in a miniaturized platform. Here, we present CM² V2, which significantly advances both the hardware and computation. We complement the 3 × 3 microlens array with a hybrid emission filter that improves the imaging contrast by 5×, and design a 3D-printed free-form collimator for the LED illuminator that improves the excitation efficiency by 3×. To enable high-resolution reconstruction across a large volume, we develop an accurate and efficient 3D linear shift-variant (LSV) model to characterize spatially varying aberrations. We then train a multimodule deep learning model called CM²Net, using only the 3D-LSV simulator. We quantify the detection performance and localization accuracy of CM²Net to reconstruct fluorescent emitters under different conditions in simulation. We then show that CM²Net generalizes well to experiments and achieves accurate 3D reconstruction across a ~7-mm FOV and 800-μm depth, and provides ~6-μm lateral and ~25-μm axial resolution. This provides an ~8× better axial resolution and ~1400× faster speed compared to the previous model-based algorithm. We anticipate this simple, low-cost computational miniature imaging system will be useful for many large-scale 3D fluorescence imaging applications.