We introduce reflective Fourier light field computed tomography (ReFLeCT), a snapshot volumetric fluorescence imaging system that captures volumetric videos of freely moving organisms at 120 volumes per second.
The Multi-Camera Array Scanner (MCAS) rapidly digitizes large 3D cytology samples with unparalleled resolution and machine learning integration for efficient and accurate pathology analysis.
STARCAM, our 54-camera 3D microscope, uses a self-supervised neural network for high-resolution gigapixel imaging, supporting diverse applications.
Our new T2oFu tomographic microscopy extends Fourier ptychography for 3D polarimetric tissue imaging, leveraging vectorial light.
This review covers digital staining, a deep learning method translating optical to biochemical contrast. It analyzes the state-of-the-art, identifies challenges, and postulates future applications.
Our new variable-angle illumination microscopy extends Fourier ptychography to acquire high-resolution, large field-of-view complex polarimetric data, accounting for light's vectorial nature.
We use a SPAD array camera and deep neural network process speckle fluctuations to reconstruct deep tissue dynamics and monitor internal flow in phantoms."
Multi-lens microscopy efficiently analyzes specimens using overlapping sensor views. Its software accurately detects malaria and WBC counting features.
Integrating an illumination model into deep CNNs enables learning task-specific LED patterns, significantly improving fluorescence image inference from unstained microscopy.
We study the feasibility of implementing Fourier ptychography (FP) with SPAD array cameras to reconstruct an image with higher resolution and larger dynamic range from acquired binary intensity measurements.
A novel machine learning method using multiple instance learning to analyze peripheral blood smears, aiming to understand COVID-19's poorly understood morphological impact on various blood cell types.
A high-sensitivity DCS system using a SPAD array can detect small deep tissue perturbations, measure human pulse with high fidelity, and identify physiological changes in the prefrontal cortex.
Deep Prior Diffraction Tomography (DP-DT) is a novel technique that reconstructs high-resolution 3D refractive index maps of thick biological samples from low-resolution images taken with varying illumination.
In this work, we investigate an approach to jointly optimize multiple microscope settings, together with a classification network, for improved performance with such automated tasks.
Using reinforcement learning to discover the best way to illuminate microscope samples for faster, more accurate classification.
A method to enhance automated image classification speed and accuracy by co-optimizing microscope illumination and a deep neural network classification pipeline.
