Prepare for teaching AI algorithms
Learning patterns are needed for an AI to be able to categorise different micro-objects based on their images.
The generation of these patterns is particularly challenging for holographic microscopes because the system is highly sensitive to the presence of tiny objects that are not visible on the images of conventional microscopes.
In holographic systems, the refractive index and the light absorption properties of the material are complex values. To achieve the best results our team is testing different known preparation methods such as gram and nigrosine staining, fixation on polylysine surfaces, mixing detergents and surfactants with biological and inert samples.
HoloZcan: Deep Learning Powered Holographic Microscopy for Biothreat Detection on Field
This project has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 101021723.