G. Popescu

Machine learning assisted health viability assay for mouse embryos with artificial confocal microscopy (ACM)

The paper develops a machine learning tool using artificial confocal microscopy to assess embryo viability by detecting nucleus features and classifying embryos into healthy/intermediate or sick categories.

GANscan: continuous scanning microscopy using deep learning deblurring

GANscan uses deep learning to restore sharp images from motion-blurred videos captured during continuous scanning, achieving 30x faster throughput than traditional stop-and-stare methods.

Label-free imaging of collagen fibers in tissue slices using phase imaging with computational specificity

This paper introduces PICS, a method that uses deep learning to infer collagen distribution from unlabeled tissue images, matching ground truth metrics.

Cell cycle stage classification using phase imaging with computational specificity

This paper introduces a method using phase imaging and neural networks to classify cell cycle stages without fluorescence, achieving high accuracy in G1, S, and G2/M classification.

Monitoring Reactivation of Latent HIV by Label-Free Gradient Light Interference Microscopy

This study uses label-free GLIM to quantify HIV reactivation in single cells by analyzing morphological changes, finding specific dry mass and diameter thresholds associated with latency and reactivation.

Rapid SARS-CoV-2 Detection and Classification Using Phase Imaging with Computational Specificity

This work proposes a rapid (<1 min.), label-free testing method for SARS-CoV-2 detection using quantitative phase imaging and deep learning with 96% accuracy.

A 'Cell-Nucleus Segmentation' Script for Non-Invasive Nuclear Dry Mass Measurement

This paper introduces an image analysis script to quantify nuclear dry mass using fluorescent and quantitative phase images, revealing a correlation between nuclear dry mass and filopodia dynamics in cervical epithelial cells.

Live-dead assay on unlabeled cells using phase imaging with computational specificity

This paper introduces a method to assess cell viability without staining using phase imaging and deep learning, achieving 95% accuracy in distinguishing live and dead cells.

Patterned substrates modulate growth and dynamics of 3D cellular systems

This study investigates how patterned substrates affect 3D cell growth and dynamics using mouse embryonic fibroblasts and novel imaging techniques.

Tissue spatial correlation as cancer marker

The paper introduces a new cancer marker based on spatial autocorrelation length from quantitative phase images and demonstrates its application in diagnosing breast tissue.

Optical excitation and detection of neuronal activity

This paper demonstrates phase imaging as a label-free method to detect optogenetic-induced intracellular transport in neurons.

Tissue disorder strength measured by quantitative phase imaging as intrinsic cancer marker

This study uses quantitative phase imaging to measure tissue disorder strength, finding it increases with disease progression in breast tissue samples.

Real-time halo correction in phase contrast imaging

This paper introduces a real-time halo correction method for phase contrast imaging that eliminates artifacts without manual intervention or prior measurements.

Topography and refractometry of sperm cells using SLIM

This study uses SLIM to measure sperm cell thickness and refractive index, finding tail thickness down to 150 nm and refractive index up to 1.6 near the head.

Label-free quantitative screening of breast tissue using Spatial Light Interference Microscopy (SLIM)

This paper introduces a label-free method using SLIM to detect breast cancer with high sensitivity and specificity by analyzing tissue nanostructure.

Simultaneous cell traction and growth measurements using light

This paper introduces a method to simultaneously measure cell traction forces and growth using light-based imaging, showing that mesenchymal stem cells exert different forces during osteogenesis and adipogenesis.