Label-free prediction of three-dimensional fluorescence images from transmitted-light microscopy.
Chawin OunkomolSharmishtaa SeshamaniMary M MaleckarForrest CollmanGregory R JohnsonPublished in: Nature methods (2018)
Understanding cells as integrated systems is central to modern biology. Although fluorescence microscopy can resolve subcellular structure in living cells, it is expensive, is slow, and can damage cells. We present a label-free method for predicting three-dimensional fluorescence directly from transmitted-light images and demonstrate that it can be used to generate multi-structure, integrated images. The method can also predict immunofluorescence (IF) from electron micrograph (EM) inputs, extending the potential applications.
Keyphrases
- label free
- single molecule
- living cells
- induced apoptosis
- deep learning
- optical coherence tomography
- convolutional neural network
- cell cycle arrest
- fluorescent probe
- high resolution
- endoplasmic reticulum stress
- machine learning
- cell death
- cell proliferation
- signaling pathway
- high speed
- pi k akt
- human health
- electron transfer