Stain-free nucleus identification in holographic learning flow cyto-tomography
Pirone, D.; Lim, J.; Merola, F.; Miccio, L.; Mugnano, M.; Bianco, V.; Cimmino, F.; Visconte, F.; Montella, A.; Capasso, M.; Iolascon, A.; Memmolo, P.; Psaltis, D.; Ferraro, P.
Show abstract
Quantitative Phase Imaging (QPI) has gained popularity because it can avoid the staining step, which in some cases is difficult or impossible. However, QPI does not provide the well-known specificity to various parts of the cell (e.g., organelles, membrane). Here we show a novel computational segmentation method based on statistical inference that bridges the gap between the specificity of Fluorescence Microscopy (FM) and the label-free property of QPI techniques to identify the cell nucleus. We demonstrate application to stain-free cells reconstructed through the holographic learning and in flow cyto-tomography modality. In particular, by means of numerical simulations and two cancer cell lines, we demonstrate that the nucleus-like regions can be accurately distinguished within the stain-free tomograms. We show that our experimental results are consistent with confocal FM data and microfluidic cytofluorimeter outputs. This is a significant step towards extracting the three-dimensional (3D) intracellular specificity directly from the phase-contrast data in a typical flow cytometry configuration.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Live-dead assay on unlabeled cells using phase imaging with computational specificity 96%
- Establishment of morphological atlas of Caenorhabditis elegans embryo with cellular resolution using deep-learning-based 4D segmentation 95%
- A deep learning-based stripe self-correction method for stitched microscopic images 95%
Similar papers in this journal
Similar papers in this journal
- Information-Distilled Generative Label-Free Morphological Profiling Encodes Cellular Heterogeneity 95%
- Fast, 3D isotropic imaging of whole mouse brain using multi-1 angle-resolved subvoxel SPIM 95%
- High-throughput, label-free and slide-free histological imaging by computational microscopy and unsupervised learning 95%
Similar papers in this journal
- EVALUATION OF STED SUPER-RESOLUTION IMAGE QUALITY BY IMAGE CORRELATION SPECTROSCOPY (QuICS) 96%
- Computational 4D-OCM for label-free imaging of collective cell invasion and force-mediated deformations in collagen 94%
- Quantitative Phase Velocimetry for Label-Free Measurement of Intracellular Mass Transport Velocity 94%
Similar papers in this journal
- A Self-Supervised Learning Approach for High Throughput and High Content Cell Segmentation 95%
- SwinCell: a transformer-based framework for dense 3D cellular segmentation 95%
- In-vivo monitoring and quantification of breast cancer growth dynamics with non-invasive intravital mesoscopic fluorescence molecular tomography 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.