Fast, multicolour optical sectioning over extended fields of view with patterned illumination and machine learning.
Edward N WardRebecca M McClellandJacob R LambRoger Rubio-SánchezCharles N ChristensenBismoy MazumderSofia KapsianiLuca MascheroniLorenzo Di MicheleGabriele S Kaminski SchierleClemens F KaminskiPublished in: Biomedical optics express (2024)
Structured illumination can reject out-of-focus signal from a sample, enabling high-speed and high-contrast imaging over large areas with widefield detection optics. However, this optical sectioning technique is currently limited by image reconstruction artefacts and poor performance at low signal-to-noise ratios. We combine multicolour interferometric pattern generation with machine learning to achieve high-contrast, real-time reconstruction of image data that is robust to background noise and sample motion. We validate the method in silico and demonstrate imaging of diverse specimens, from fixed and live biological samples to synthetic biosystems, reconstructing data live at 11 Hz across a 44 × 44 μm 2 field of view, and demonstrate image acquisition speeds exceeding 154 Hz.
Keyphrases
- high speed
- high resolution
- machine learning
- deep learning
- atomic force microscopy
- big data
- artificial intelligence
- magnetic resonance
- electronic health record
- air pollution
- mass spectrometry
- contrast enhanced
- fluorescence imaging
- real time pcr
- loop mediated isothermal amplification
- data analysis
- computed tomography
- photodynamic therapy
- ultrasound guided