YBYury Belyaev

Yury Belyaev

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Yury Belyaev has a total of 78 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Monitoring the point spread function for quality control of Fluorescent microscopes v2 v2

    by Glyn Nelson, Ioannis Alexopoulos, Luis-Francisco Acevedo-Hueso, Maria Azevedo, Fabio Barachati, Yury Belyaev, Mariana T Carvalho, Yann Cesbron, Aurelien Dauphin, Alexander D Corbett, et al.

    This protocol focuses on measuring the microscope's lateral and axial resolution, essential for reporting size measurements of near-resolution limit objects or distances between them. Here resolution is expressed as the Full Width at Half Maximum (FWHM) of a measured Point Spread Function (PSF) of sub-resolution size beads. PSF is highly related to objective quality and condition, but also depends strongly upon other parameters ranging from sample preparation to signal detection. Monitoring PSF over time will identify possible aberrations in the system (e.g., damaged, unclean objective, defective or not adapted oil, etc.). We define test sample preparation, image acquisition, and data analysis protocols for point scanning and spinning disk confocal microscopes as well as widefield fluorescent microscopes.

  • Learning to Reconstruct Confocal Microscopy Stacks From Single Light Field Images

    by Josué Page Vizcaíno, Federico Saltarin, Yury Belyaev, Ruth Lyck, Tobias Lasser, Paolo Favaro

    We present a novel deep learning approach to reconstruct confocal microscopy stacks from single light field images. To perform the reconstruction, we introduce LFMNet, a fully convolutional neural network architecture inspired by the U-Net design. A property of LFMNet is its ability to reconstruct with near confocal accuracy a 112 ×112 ×57.6 μm 3 volume (1287×1287×64 voxels) in 50 ms given a single light field image of 1287×1287 pixels, thus dramatically reducing 720-fold the capture time compared to confocal scanning of assays at the same volumetric resolution and 64-fold the required storage. To prove its applicability in life sciences, our approach is evaluated both quantitatively and qualitatively on mouse brain slices with fluorescently labeled blood vessels. Because of the drastic reduction in image acquisition time, our setup and method are suitable for imaging highly dynamic and light-sensitive events, and in closed-loop systems, where latency due to the reconstruction time is crucial. We provide empirical analysis of the optical design, of the network architecture and of our training procedure to reconstruct confocal-like volumes for a given target depth range. To train our network, we built a data set of 362 light field images of the mouse brain sample and the corresponding aligned set of 3D confocal scans, which we use as ground truth. The data set will be made available for research purposes.


  • Open Access

    Learning to Reconstruct Confocal Microscopy Stacks from Single Light Field Images

    by Josue Page, Federico Saltarin, Yury Belyaev, Ruth Lyck, Paolo Favaro

    We present a novel deep learning approach to reconstruct confocal microscopy stacks from single light field images. To perform the reconstruction, we introduce the LFMNet, a novel neural network architecture inspired by the U-Net design. It is able to reconstruct with high-accuracy a 112x112x57.6$\mu m^3$ volume (1287x1287x64 voxels) in 50ms given a single light field image of 1287x1287 pixels, thus dramatically reducing 720-fold the time for confocal scanning of assays at the same volumetric resolution and 64-fold the required storage. To prove the applicability in life sciences, our approach is evaluated both quantitatively and qualitatively on mouse brain slices with fluorescently labelled blood vessels. Because of the drastic reduction in scan time and storage space, our setup and method are directly applicable to real-time in vivo 3D microscopy. We provide analysis of the optical design, of the network architecture and of our training procedure to optimally reconstruct volumes for a given target depth range. To train our network, we built a data set of 362 light field images of mouse brain blood vessels and the corresponding aligned set of 3D confocal scans, which we use as ground truth. The data set will be made available for research purposes.

  • Open Access

    Structural characterization of four different naturally occurring porcine collagen membranes suitable for medical applications

    by Thimo Maurer, Michael H Stoffel, Yury Belyaev, Niklaus G Stiefel, Beatriz Vidondo, Susanne Küker, Helga Mogel, Birgit Schäfer, Jasmin Balmer

    Collagen is the main structural element of connective tissues, and its favorable properties make it an ideal biomaterial for regenerative medicine. In dental medicine, collagen barrier membranes fabricated from naturally occurring tissues are used for guided bone regeneration. Since the morphological characteristics of collagen membranes play a crucial role in their mechanical properties and affect the cellular behavior at the defect site, in-depth knowledge of the structure is key. As a base for the development of novel collagen membranes, an extensive morphological analysis of four porcine membranes, including centrum tendineum, pericardium, plica venae cavae and small intestinal submucosa, was performed. Native membranes were analyzed in terms of their thickness. Second harmonic generation and two-photon excitation microscopy of the native membranes showed the 3D architecture of the collagen and elastic fibers, as well as a volumetric index of these two membrane components. The surface morphology, fiber arrangement, collagen fibril diameter and D-periodicity of decellularized membranes were investigated by scanning electron microscopy. All the membrane types showed significant differences in thickness. In general, undulating collagen fibers were arranged in stacked layers, which were parallel to the membrane surface. Multiphoton microscopy revealed a conspicuous superficial elastic fiber network, while the elastin content in deeper layers varied. The elastin/collagen volumetric index was very similar in the investigated membranes and indicated that the collagen content was clearly higher than the elastin content. The surface of both the pericardium and plica venae cavae and the cranial surface of the centrum tendineum revealed a smooth, tightly arranged and crumpled morphology. On the caudal face of the centrum tendineum, a compact collagen arrangement was interrupted by clusters of circular discontinuities. In contrast, both surfaces of the small intestinal submucosa were fibrous, fuzzy and irregular. All the membranes consisted of largely uniform fibrils displaying the characteristic D-banding. This study reveals similarities and relevant differences among the investigated porcine membranes, suggesting that each membrane represents a unique biomaterial suitable for specific applications.


  • Live-Cell STED Microscopy with Genetically Encoded Biosensor

    by Natalia M. Mishina, Alexander S. Mishin, Yury Belyaev, Ekaterina A. Bogdanova, Sergey Lukyanov, Carsten Schultz, Vsevolod V. Belousov

    Of the various super-resolution techniques, stimulated emission depletion (STED) microscopy achieves the best temporal resolution at high spatial resolution, enabling live-cell imaging beyond the diffraction limit. However, STED and most other super-resolution imaging methods utilize a particular type of information extractable from the raw data, namely the positions of fluorophores. To expand on the use of super-resolution techniques, we report here the live-cell STED microscopy of a dynamic biosensor. Using the fluorescent H2O2 sensor HyPer2 for subdiffraction imaging, we were able not only to image filaments with superior resolution by localizing emission but also to trace H2O2 produced within living cell by monitoring brightness of the probe. STED microscopy of HyPer2 demonstrates potential utility of FP-based biosensors for super-resolution experiments in situ and in vivo.


  • Virtual slit scanning microscopy

    by Reto Fiolka, Andreas Stemmer, Yury Belyaev

    We present a novel slit scanning confocal microscope with a CCD camera image sensor and a virtual slit aperture for descanning that can be adjusted during post-processing. A very efficient data structure and mathematical criteria for aligning the virtual aperture guarantee the ease of use. We further introduce a method to reduce the anisotropic lateral resolution of slit scanning microscopes. System performance is evaluated against a spinning disk confocal microscope on identical specimens. The virtual slit scanning microscope works as the spinning disk type and outperforms on thick specimens.


  • Even illumination in total internal reflection fluorescence microscopy using laser light

    by R. Fiolka, Y. Belyaev, H. Ewers, A. Stemmer

    In modern fluorescence microscopy, lasers are a widely used source of light, both for imaging in total internal reflection and epi‐illumination modes. In wide‐field imaging, scattering of highly coherent laser light due to imperfections in the light path typically leads to nonuniform illumination of the specimen, compromising image analysis. We report the design and construction of an objective‐launch total internal reflection fluorescence microscopy system with excellent evenness of specimen illumination achieved by azimuthal rotation of the incoming illuminating laser beam. The system allows quick and precise changes of the incidence angle of the laser beam and thus can also be used in an epifluorescence mode. Microsc. Res. Tech., 2008.