Computational tissue staining of non-linear multimodal imaging using supervised and unsupervised deep learning

in: Biomedical Optics Express (2021)
Bocklitz, Thomas W.; Pradhan, Pranita; Meyer, Tobias; Vieth, Michael; Stallmach, Andreas; Waldner, Maximilian; Schmitt, Michael; Popp, Jürgen
Hematoxylin and Eosin (H&E) staining is the ’gold-standard’ method in histopathology. However, standard H&E staining of high-quality tissue sections requires long sample preparation times including sample embedding, which restricts its application for ’real-time’ disease diagnosis. Due to this reason, a label-free alternative technique like non-linear multimodal (NLM) imaging, which is the combination of three non-linear optical modalities including coherent anti-Stokes Raman scattering, two-photon excitation fluorescence and second-harmonic generation, is proposed in this work. To correlate the information of the NLM images with H&E images, this work proposes computational staining of NLM images using deep learning models in a supervised and an unsupervised approach. In the supervised and the unsupervised approach, conditional generative adversarial networks (CGANs) and cycle conditional generative adversarial networks (cycle CGANs) are used, respectively. Both CGAN and cycle CGAN models generate pseudo H&E images, which are quantitatively analysed based on mean squared error, structure similarity index and color shading similarity index. The mean of the three metrics calculated for the computationally generated H&E images indicate significant performance. Thus, utilizing CGAN and cycle CGAN models for computational staining is beneficial for diagnostic applications without performing a laboratory-based staining procedure. To the author’s best knowledge, it is the first time that NLM images are computationally stained to H&E images using GANs in an unsupervised manner.

Third party cookies & scripts

This site uses cookies. For optimal performance, smooth social media and promotional use, it is recommended that you agree to third party cookies and scripts. This may involve sharing information about your use of the third-party social media, advertising and analytics website.
For more information, see privacy policy and imprint.
Which cookies & scripts and the associated processing of your personal data do you agree with?

You can change your preferences anytime by visiting privacy policy.