Hybrid machine-learning framework for volumetric segmentation and quantification of vacuoles in individual yeast cells using holotomography
Budding yeast
Correlative
Live cell imaging
Phase imaging
DOI:
10.1364/boe.498475
Publication Date:
2023-08-02T13:00:07Z
AUTHORS (5)
ABSTRACT
The precise, quantitative evaluation of intracellular organelles in three-dimensional (3D) imaging data poses a significant challenge due to the inherent constraints traditional microscopy techniques, requirements use exogenous labeling agents, and existing computational methods. To counter these challenges, we present hybrid machine-learning framework exploiting correlative 3D phase with fluorescence labeled cells. algorithm, which synergistically integrates random-forest classifier deep neural network, is trained using set, network then applied cell data. We this method live budding yeast results revealed precise segmentation vacuoles inside individual cells, also provided evaluations biophysical parameters, including volumes, concentration, dry masses automatically segmented vacuoles.
SUPPLEMENTAL MATERIAL
Coming soon ....
REFERENCES (51)
CITATIONS (8)
EXTERNAL LINKS
PlumX Metrics
RECOMMENDATIONS
FAIR ASSESSMENT
Coming soon ....
JUPYTER LAB
Coming soon ....