Filters

2015 - 201912020 - 20211

More filters

20222
Reset filters

Settings

Subject: image quality × WGL Institute: IPHT ×

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Computational tissue staining of non-linear multimodal imaging using supervised and unsupervised deep learning
    (Washington, DC : OSA, 2021) Pradhan, Pranita; Meyer, Tobias; Vieth, Michael; Stallmach, Andreas; Waldner, Maximilian; Schmitt, Michael; Popp, Juergen; Bocklitz, Thomas
    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 analyzed 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.
  • Thumbnail Image
    Item
    Two-dimensional imaging in hyperbolic media-the role of field components and ordinary waves
    ([London] : Macmillan Publishers Limited, part of Springer Nature, 2015) Tuniz, Alessandro; Kuhlmey, Boris T.
    We study full vector imaging of two dimensional source fields through finite slabs of media with extreme anisotropy, such as hyperbolic media. For this, we adapt the exact transfer matrix method for uniaxial media to calculate the two dimensional transfer functions and point spread functions for arbitrary vector fields described in Cartesian coordinates. This is more convenient for imaging simulations than the use of the natural, propagation direction-dependent TE/TM basis and clarifies which field components contribute to sub-diffraction imaging. We study the effect of ordinary waves on image quality, which previous one-dimensional approaches could not consider. Perfect sub-diffraction imaging can be achieved if longitudinal fields are measured, but in the more common case where field intensities or transverse fields are measured, ordinary waves cause artefacts. These become more prevalent when attempting to image large objects with high resolution. We discuss implications for curved hyperbolic imaging geometries such as hyperlenses.