Lei Tian

The paper introduces dual-mode Bio-CM2, a miniature mesoscope that captures fluorescence and label-free imaging simultaneously, demonstrating its use across different organisms and biological contexts.

Four miniature lenses sharing one CMOS sensor, with computational stitching, give cellular-resolution imaging over 7.5 × 10 mm^2 at video rate, resolving 3,474 mouse cortical neurons.

This paper introduces Dual-Channel Event Microscopy (DEM) for ultrafast, volumetric imaging of biological processes, demonstrating its ability to capture fast dynamics in zebrafish with high temporal resolution and spectral separation.

This paper introduces a self-adaptive oblique plane microscopy technique that enables high-speed volumetric imaging across microscopic to macroscopic scales in multi-cellular systems.

This paper introduces an age-informed attention-based MIL model to predict AT8 density in neuropathological images, improving diagnostic accuracy and interpretability.

DeepVID v2 improves low-photon voltage imaging by resolving spatial and temporal noise through self-supervised denoising with decoupled enhancement.

The paper shows that hemodynamic responses in the cortex are influenced by neuromodulators like norepinephrine, with distinct impulse response functions for different neuromodulatory signals.

The paper develops tools for high-speed, low-light two-photon voltage imaging of large neuronal populations in awake mice, achieving stable imaging of over 100 neurons for an hour.

This paper develops a deep learning method for segmenting brain vasculature from two-photon microscopy images, achieving faster computation and better generalization across imaging systems.