AI Platform for Microscopy Image Restoration and Virtual Staining: Fluorescence microscopy has enabled many major discoveries in biomedical sciences. Despite therapid advancements in optics, lasers, probes, cameras and novel techniques, major factors such as spatialand temporal resolution, light exposure, signal-to-noise, depth of penetration and probe spectra continueto limit the types of experiments that are possible. Deep learning (DL) algorithms are well suited forimage-based problems like SNR/super-resolution restoration and virtual staining, which have greatenabling potentials for microscopy experiments. Previously impossible experiments could be realized suchas achieving high signal-to-noise and/or spatial-temporal resolution without photobleaching/phototoxicity;simultaneously observing many image channels without interfering with native processes, etc. This couldpave the way for a quantum leap forward in microscopy-based discoveries that elucidate biologicalfunctions and the mechanisms of disorders, and enable new diagnostics and therapies for human diseases. However, these new methods have not been widely translated to new microscopy experiments. Thedelay is due to several practical hurdles and challenges such as required expertise, computing and trust. Inorder to accelerate the adoption of DL in microscopy, novel AI platform tailored for biologists are neededfor training, applying and validating DL models and outputs. The present project aims to develop an AI platform for microscopy image restoration and virtualstaining called AI for Restoring and Staining (AIRS) platform. With our collaborator, Dr. Hari Shroff(National Institute of Biomedical Imaging and Bioengineering) we have successfully created DL models forSNR restoration, super-resolution restoration and virtual staining for a variety of imaging conditions andorganelles in our preliminary studies. The AIRS platform intends to (1)provide a comprehensive suite ofvalidated DL models for microscopy restoration and virtual staining applications including SNRrestoration, super-resolution restoration, spatial deconvolution, spectral unmixing, prediction of 3d from2d images, organelle virtual staining and analysis; (2)provide plug and play for common microscopyexperiments; (3)provide semi-automatic update training to tailor DL models to match advancedmicroscopy experiments; (4)provide user friendly support for new DL model training for pioneeringmicroscopy experiments; (5)provide confidence scores to assess the output results by a DL model, (6)provide DL models that avoid image artifact (hallucination) and allow continuous learning and evolution;(7) and be able to access the required computing infrastructure and database connection.
Public Health Relevance Statement: Project Narrative
Deep learning (DL) algorithms have great enabling potentials for microscopy experiments. Previously
impossible experiments could now be realized. This could pave the way for a quantum leap forward in
microscopy-based discoveries.
Powered by deep learning and DRVision innovations and collaborating with Dr. Hari Shroff and 7
additional labs, this project aims to create an AI platform for microscopy image restorations and virtual
staining called AI for restoring and staining (AIRS). The tool will be integrated with DRVision's
flagship product Aivia for commercialization to accelerate the adoption of DL in microscopy.
Project Terms: | <3-D><3D><3-Dimensional><3-D Images><3-D image><3D image><3D images> | |
