Deep Learning-Assisted Localisation of Nanoparticles in synthetically generated two-photon microscopy images
This work addresses the challenge of low data volumes in in vivo imaging for drug delivery research, but it is incremental as it focuses on simulation-based augmentation rather than a new paradigm.
The researchers tackled the problem of accurately localizing nanoparticles in two-photon microscopy images for brain drug delivery studies by developing a simulator to generate synthetic training data, which improved localization quality in simulated images and explained the failure of existing intensity-based methods.
Tracking single molecules is instrumental for quantifying the transport of molecules and nanoparticles in biological samples, e.g., in brain drug delivery studies. Existing intensity-based localisation methods are not developed for imaging with a scanning microscope, typically used for in vivo imaging. Low signal-to-noise ratios, movement of molecules out-of-focus, and high motion blur on images recorded with scanning two-photon microscopy (2PM) in vivo pose a challenge to the accurate localisation of molecules. Using data-driven models is challenging due to low data volumes, typical for in vivo experiments. We developed a 2PM image simulator to supplement scarce training data. The simulator mimics realistic motion blur, background fluorescence, and shot noise observed in vivo imaging. Training a data-driven model with simulated data improves localisation quality in simulated images and shows why intensity-based methods fail.