MIA: David Van Valen, Deep learning multiplexed images; Primer by Emily Laubscher

Models, Inference and Algorithms Broad Institute of MIT and Harvard March 3, 2021 Meeting: Singlecell biology in a software 2. 0 world David Van Valen Division of Biology and Biological Engineering, California Institute of Technology Multiplexed imaging methods can measure the expression of dozens of proteins while preserving spatial information. While these methods open an exciting new window into the biology of human tissues, interpreting the images they generate with single cell resolution remains a significant challenge. Current approaches to this problem in tissues rely on identifying cell nuclei, which results in inaccurate estimates of cellular phenotype and morphology. In this work, we overcome this limitation by combining multiplexed imagings ability to image nuclear and membrane markers with largescale data annotation and deep learning. We describe the construction of TissueNet, an image dataset containing more than one million paired wholecell and nuclear annotation