SOURCE-LINKED INTELLIGENCE

A light-efficient microscope for fast volumetric imaging of photon starved samples

CORDIS · observation · Publication date unknown

low spatiotemporal resolution, due to photon-starved samples. LowLiteScope aims to overcome these limitations by radically redesigning the optical path, data acquisition and post processing based on artificial intelligence. LowliteScope leverages a new light field approach to capture the spatial and angular information of light rays that pass through the sample. In contrast to conventional light field microscope, this technique records three-dimensional images with high spatial resolution and a large depth of field. To econstruct the 3D volume from single exposure light field images, we will use new deep learning models based on artificial intelligence (WP1). The use of generalized and optics-informed deep learning techniques will also increase the spatial resolution beyond conventional light field microscopes. We will test the performance of the LowLiteScope prototype using photosensitive samples and samples with high intrinsic autofluorescence (WP2) - two properties that often render long-term, high-resolution imaging via fluorescence microscopy difficult. Ultimately, success is

Read original source ↗ Open in workspace

recordType

award

status

SIGNED

region

EU

value

150000

unit

EUR