LLAMA: a robust and scalable machine learning pipeline for analysis of cell surface projections in large scale 4D microscopy data

We present LLAMA, a pipeline for systematic analysis of terabyte scale 4D microscopy datasets. Analysis of individual biological structures in imaging at this scale requires efficient and robust methods which do not require human micromanagement or editing of outputs. To meet this challenge, we use a machine learning method for semantic segmentation, followed by a robust and configurable object separation and tracking algorithm, and the generation of detailed object level statistics. Advanced visualisation is a key element of LLAMA: we provide a specialised software tool which supports quality control and optimisation as well as visualisation of outputs. LLAMA was used in a quantitative analysis of macrophage surface membrane projections (filopodia, ruffles, tent-pole ruffles) examining the differential effects of two interventions: lipopolysaccharide (LPS) and macrophage colony stimulating factor (CSF-1). Distinct patterns of increased activity were identified. In addition, a continuity of behaviour was found between tent pole ruffling and wave-like ruffling, further defining the role of filopodia in ruffling.

[1]  Casey Reas,et al.  Processing: programming for the media arts , 2006, AI & SOCIETY.

[2]  T. Chew,et al.  Light sheet microscopes: Novel imaging toolbox for visualizing life's processes. , 2016, The international journal of biochemistry & cell biology.

[3]  Kevin W Eliceiri,et al.  NIH Image to ImageJ: 25 years of image analysis , 2012, Nature Methods.

[4]  C Wählby,et al.  Combining intensity, edge and shape information for 2D and 3D segmentation of cell nuclei in tissue sections , 2004, Journal of microscopy.

[5]  P. Gleeson,et al.  Macropinocytosis in Different Cell Types: Similarities and Differences , 2020, Membranes.

[6]  H. Sebastian Seung,et al.  Trainable Weka Segmentation: a machine learning tool for microscopy pixel classification , 2017, Bioinform..

[7]  P. McPherson,et al.  Macropinosome formation by tent pole ruffling in macrophages , 2018, The Journal of cell biology.

[8]  Wesley R. Legant,et al.  Lattice light-sheet microscopy: Imaging molecules to embryos at high spatiotemporal resolution , 2014, Science.

[9]  Thomas Boudier,et al.  TANGO: a generic tool for high-throughput 3D image analysis for studying nuclear organization , 2013, Bioinform..

[10]  Serge Beucher,et al.  Use of watersheds in contour detection , 1979 .

[11]  Arrate Muñoz-Barrutia,et al.  3D reconstruction of histological sections: Application to mammary gland tissue , 2010, Microscopy research and technique.

[12]  B. Isaac,et al.  A WAVE2-Abi1 complex mediates CSF-1-induced F-actin-rich membrane protrusions and migration in macrophages , 2005, Journal of Cell Science.

[13]  Eric Betzig,et al.  Actin-based protrusions of migrating neutrophils are intrinsically lamellar and facilitate direction changes , 2017, eLife.

[14]  T. Chew,et al.  Frontline Science: Dynamic cellular and subcellular features of migrating leukocytes revealed by in vivo lattice lightsheet microscopy , 2020, Journal of leukocyte biology.

[15]  F. Pixley Macrophage Migration and Its Regulation by CSF-1 , 2012, International journal of cell biology.

[16]  F. Granucci,et al.  CD14 Controls the LPS-Induced Endocytosis of Toll-like Receptor 4 , 2011, Cell.

[17]  S. Grinstein,et al.  Calcium-sensing receptors signal constitutive macropinocytosis and facilitate the uptake of NOD2 ligands in macrophages , 2016, Nature Communications.

[18]  A. Ridley,et al.  Lipopolysaccharide Induces Actin Reorganization and Tyrosine Phosphorylation of Pyk2 and Paxillin in Monocytes and Macrophages1 , 2000, The Journal of Immunology.

[19]  Philippe Andrey,et al.  MorphoLibJ: integrated library and plugins for mathematical morphology with ImageJ , 2016, Bioinform..

[20]  J. Stow,et al.  The cell surface environment for pathogen recognition and entry , 2016, Clinical & translational immunology.

[21]  J. Stow,et al.  Macropinocytosis: Insights from immunology and cancer. , 2020, Current opinion in cell biology.

[22]  Vadim Zinchuk,et al.  Machine Learning for Analysis of Microscopy Images: A Practical Guide , 2020, Current protocols in cell biology.

[23]  William E. Lorensen,et al.  Marching cubes: A high resolution 3D surface construction algorithm , 1987, SIGGRAPH.

[24]  N. Shastri,et al.  Class I MHC presentation of exogenous soluble antigen via macropinocytosis in bone marrow macrophages. , 1995, Immunity.

[25]  E LorensenWilliam,et al.  Marching cubes: A high resolution 3D surface construction algorithm , 1987 .

[26]  Joel A. Swanson,et al.  Shaping cups into phagosomes and macropinosomes , 2008, Nature Reviews Molecular Cell Biology.

[27]  Wei Wang,et al.  Extended-Maxima Transform Watershed Segmentation Algorithm for Touching Corn Kernels , 2013 .

[28]  Harold W. Kuhn,et al.  The Hungarian method for the assignment problem , 1955, 50 Years of Integer Programming.

[29]  E. Betzig,et al.  A plasma membrane template for macropinocytic cups , 2016, eLife.

[30]  Qing Xu,et al.  Fluid-Phase Pinocytosis of Native Low Density Lipoprotein Promotes Murine M-CSF Differentiated Macrophage Foam Cell Formation , 2013, PloS one.