14th of December 2020 - At this year's ASCB - EMBO meeting, "CELL BIO virtual 2020", we are presenting a summary of the results obtained over the last 12 months. The works presented are part of our two main research and development, NIH funded, projects: Intelligent Connectomics Analysis (ICA) and Artificial Intelligence (AI) platform for microscopy image SNR restoration, super-resolution restoration and virtual (AIRS).
ICA, a collaborative effort with Prof. Rachel Wong's group at the University of Washington, focuses on the detection and 3D reconstruction of neurons as imaged by electron and light microscopy. Deep learning is heavily used to detect and segment the neurons.
AIRS, a collaborative effort with Dr. Hari Shroff's and Dr. Jiji Chen's groups at the NIH, aims to develop and characterize state-of-the-art image restoration approaches leveraging deep learning.
Bellow are the three posters (high resolution print out and downloadable pdf) as well as the respective video presentations:
1) AI Microscopy: deep learning minimizes the impact of fundamental microscopy limitations
For more details on these studies see our pre-print: "Three-dimensional residual channel attention networks denoise and sharpen fluorescence microscopy image volumes" https://www.biorxiv.org/content/10.1101/2020.08.27.270439v1
Join the discussion directly at the online CellBio2020 poster session: P1374 https://ascb.confex.com/ascb/CellBio20/eposters/eposterview.cgi?eposterid=1828
2) Intelligent connectomic analysis tool for dense neuronal circuits
Join the discussion directly at the online CellBio2020 poster session: P1371 https://ascb.confex.com/ascb/CellBio20/eposters/eposterview.cgi?eposterid=1008
3) Active learning enable intelligent annotation for deep model training applied to EM connectomics analyses
Join the discussion directly at the online CellBio2020 poster session: P1372 https://ascb.confex.com/ascb/CellBio20/eposters/eposterview.cgi?eposterid=1017