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

Abstract

Using a deep neural network, we demonstrate a digital staining technique, which we term PhaseStain, to transform quantitative phase images (QPI) of labelfree tissue sections into images that are equivalent to brightfield microscopy images of the same samples that are histochemically stained. Through pairs of image data (QPI and the corresponding brightfield images, acquired after staining) we train a generative adversarial network (GAN) 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 might further strengthen various uses of labelfree QPI techniques in pathology applications and biomedical research in general, by eliminating the need for chemical 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.

References in corpus (12)

• A Survey on Deep Learning in Medical Image Analysis
• Wide-field, high-resolution Fourier ptychographic microscopy
• Phase recovery and holographic image reconstruction using deep learning in neural networks
• Deep learning-based virtual histology staining using auto-fluorescence of label-free tissue
• Deep Learning Microscopy
• Deep-STORM: super-resolution single-molecule microscopy by deep learning
• Detecting Cancer Metastases on Gigapixel Pathology Images
• Extended depth-of-field in holographic image reconstruction using deep learning based auto-focusing and phase-recovery
• Deep learning enhanced mobile-phone microscopy
• Quantitative phase microscopy spatial signatures of cancer cells
• Deep learning reconstruction of ultrashort pulses from 2D spatial intensity patterns recorded by an all-in-line system in a single-shot
• Quantitative Phase Imaging and Artificial Intelligence: A Review

Cited by in corpus (45)

• Deep neural network models for computational histopathology: A survey
• Deep Learning-enabled Virtual Histological Staining of Biological Samples
• DeepSTORM3D: dense three dimensional localization microscopy and point spread function design by deep learning
• Deep learning-based transformation of the H&E stain into special stains
• Design of Task-Specific Optical Systems Using Broadband Diffractive Neural Networks
• On the use of deep learning for phase recovery
• Terahertz Pulse Shaping Using Diffractive Surfaces
• Digital synthesis of histological stains using micro-structured and multiplexed virtual staining of label-free tissue
• Phase Imaging with Computational Specificity (PICS) for measuring dry mass changes in sub-cellular compartments
• Misalignment Resilient Diffractive Optical Networks
• Quantitative Digital Microscopy with Deep Learning
• Quantitative phase imaging through an ultra-thin lensless fiber endoscope
• Self-supervised learning of hologram reconstruction using physics consistency
• HoloStain: Holographic virtual staining of individual biological cells
• Resolution-enhanced parallel coded ptychography for high-throughput optical imaging
• Single-shot autofocusing of microscopy images using deep learning
• Deep learning in biomedical optics
• Scale-, shift- and rotation-invariant diffractive optical networks
• Label-free virtual HER2 immunohistochemical staining of breast tissue using deep learning
• Deep learning-based holographic polarization microscopy
• Virtual histological staining of unlabeled autopsy tissue
• Multiplane Quantitative Phase Imaging Using a Wavelength-Multiplexed Diffractive Optical Processor
• Deep learning-based color holographic microscopy
• Label-free colorectal cancer screening using deep learning and spatial light interference microscopy (SLIM)
• Virtual stain transfer in histology via cascaded deep neural networks
• Recurrent neural network-based volumetric fluorescence microscopy
• Digital staining in optical microscopy using deep learning -- a review
• Extracting quantitative biological information from brightfield cell images using deep learning
• Deep learning-based photoacoustic imaging of vascular network through thick porous media
• Multispectral Quantitative Phase Imaging Using a Diffractive Optical Network
• Virtual staining of defocused autofluorescence images of unlabeled tissue using deep neural networks
• Pixel super-resolved virtual staining of label-free tissue using diffusion models
• Virtual birefringence imaging and histological staining of amyloid deposits in label-free tissue using autofluorescence microscopy and deep learning
• Ptychographic modulation engine (PME): a low-cost DIY microscope add-on for coherent super-resolution imaging
• Virtual Gram staining of label-free bacteria using darkfield microscopy and deep learning
• A robust and scalable framework for hallucination detection in virtual tissue staining and digital pathology
• Computational interference microscopy enabled by deep learning
• Automated Whole Slide Imaging for Label-Free Histology using Photon Absorption Remote Sensing Microscopy
• Virtual organelle self-coding for fluorescence imaging via adversarial learning
• Physical model simulator-trained neural network for computational 3D phase imaging of multiple-scattering samples
• Label-free evaluation of lung and heart transplant biopsies using tissue autofluorescence-based virtual staining
• Computer-free, all-optical reconstruction of holograms using diffractive networks
• BlurryScope enables compact, cost-effective scanning microscopy for HER2 scoring using deep learning on blurry images
• Diffractive Interconnects: All-Optical Permutation Operation Using Diffractive Networks
• Learning with minimal effort: leveraging in silico labeling for cell and nucleus segmentation