PhaseStain: the digital staining of label-free quantitative phase microscopy images using deep learning

By Yair Rivenson, Tairan Liu, Zhensong Wei, Yibo Zhang, Aydogan Ozcan. Light: Science & Applications, 2018

388 citations recorded by the source corpus.

Using a deep neural network, we demonstrate a digital staining technique, which we term PhaseStain, to transform the quantitative phase images (QPI) of label-free tissue sections into images that are equivalent to the brightfield microscopy images of the same samples that are histologically stained. Through pairs of image data (QPI and the corresponding brightfield images, acquired after staining), we train a generative adversarial network and demonstrate the effectiveness of this virtual-staining approach using sections of human skin, kidney, and liver tissue, matching the brightfield microscopy images of the same samples stained with Hematoxylin and Eosin, Jones’ stain, and Masson’s trichrome stain, respectively. This digital-staining framework may further strengthen various uses of label-free QPI techniques in pathology applications and biomedical research in general, by eliminating the need for histological staining, reducing sample preparation related costs and saving time. Our results provide a powerful example of some of the unique opportunities created by data-driven image transformations enabled by deep learning. Combining a technique called quantitative phase microscopy with a trained neural network avoids the need to use chemical stains to visualize constituents of biological tissue samples. Quantitative phase microscopy reveals the features of a label-free specimen by analyzing changes in the phase of light waves as they interact with different regions of a sample. Aydogan Ozcan, Yair Rivenson and colleagues at the University of California, Los Angeles, USA, trained a neural network to transform phase microscopy images of human skin, kidney and liver tissues into images that matched those obtained using conventional histological staining techniques used in pathology. This virtual-staining approach, which the authors termed PhaseStain, offers easier, faster and cheaper high quality analysis of tissue samples for use in biology and medicine.

Subfields: Atomic and Molecular Physics, and Optics, Biophysics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/9246908159ab0c0a967e332801b7414d196e702c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atomic and Molecular Physics, and Optics

In Biophysics

In Computer Vision and Pattern Recognition

Citations in the corpus

Inference in artificial intelligence with deep optics and photonics (2020, background): “One example of this is cross-modality image transformations 84–86, 96–98 , where a DNN is From the perspective of deep learning-based computational imaging, what really sets microscopy apart from macro-scale imaging is the precision and repeatability of microscopes in terms of, for example, their…”
Deep learning-enabled virtual histological staining of biological samples (2022, background): “For instance, to avoid intensity variations caused by potential photobleaching in autofluorescence imaging, Rivenson et al. normalized the input autofluorescence images by subtracting the mean value across the entire tissue slide and dividing it by the standard deviation of the pixel values18.”