Robust Optical Flow Algorithm for General, Label-free Cell Segmentation

Cell segmentation is crucial to the field of cell biology, as the accurate extraction of cell morphology, migration, and ultimately behavior from time-lapse live cell imagery are of paramount importance to elucidate and understand basic cellular processes. Here, we introduce a novel segmentation approach centered around optical flow and show that it achieves robust segmentation by validating it on multiple cell types, phenotypes, optical modalities, and in-vitro environments without the need of labels. By leveraging cell movement in time-lapse imagery as a means to distinguish cells from their background and augmenting the output with machine vision operations, our algorithm reduces the number of adjustable parameters needed for optimization to two. The code is packaged within a MATLAB executable file, offering an accessible means for general cell segmentation typically unavailable in most cell biology laboratories.

[1]  Mirabela Rusu,et al.  A deep learning-based algorithm for 2-D cell segmentation in microscopy images , 2018, BMC Bioinformatics.

[2]  C. Ampe,et al.  Taking Aim at Moving Targets in Computational Cell Migration. , 2016, Trends in cell biology.

[3]  Javier Ruiz-del-Solar,et al.  Performance of optical flow techniques for motion analysis of fluorescent point signals in confocal microscopy , 2012, Machine Vision and Applications.

[4]  Amy Q. Shen,et al.  Usiigaci: Instance-aware cell tracking in stain-free phase contrast microscopy enabled by machine learning , 2019, bioRxiv.

[5]  Michael Möller,et al.  A framework for automated cell tracking in phase contrast microscopic videos based on normal velocities , 2012, J. Vis. Commun. Image Represent..

[6]  Joachim P Spatz,et al.  Cell membrane topology analysis by RICM enables marker-free adhesion strength quantification , 2013, Biointerphases.

[7]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

[8]  Hang-Hyun Jo,et al.  Tail-scope: Using friends to estimate heavy tails of degree distributions in large-scale complex networks , 2014, Scientific Reports.

[9]  Wolfgang Losert,et al.  Quantifying topography-guided actin dynamics across scales using optical flow , 2019, bioRxiv.

[10]  Monya Baker,et al.  Cellular imaging: Taking a long, hard look , 2010, Nature.

[11]  Katarina Z. Doctor,et al.  Monolithic quartz platform for cellular contact guidance , 2020, MRS Communications.

[12]  James B. Delehanty,et al.  Nanostructured substrates for multi-cue investigations of single cells , 2018 .

[13]  Stephanie I. Fraley,et al.  Three-dimensional matrix fiber alignment modulates cell migration and MT1-MMP utility by spatially and temporally directing protrusions , 2015, Scientific Reports.

[14]  Anne E Carpenter,et al.  CellProfiler: image analysis software for identifying and quantifying cell phenotypes , 2006, Genome Biology.

[15]  Sayak Bhattacharya,et al.  Altering the threshold of an excitable signal transduction network changes cell migratory modes , 2017, Nature Cell Biology.

[16]  M. Abercrombie,et al.  Adhesions of fibroblasts to substratum during contact inhibition observed by interference reflection microscopy. , 1975, Experimental cell research.

[17]  C. Murphy,et al.  Epithelial contact guidance on well-defined micro- and nanostructured substrates , 2003, Journal of Cell Science.

[18]  Joachim P Spatz,et al.  Lateral spacing of integrin ligands influences cell spreading and focal adhesion assembly. , 2006, European journal of cell biology.

[19]  Gregory R. Johnson,et al.  Label-free prediction of three-dimensional fluorescence images from transmitted light microscopy , 2018, Nature Methods.

[20]  Thomas Brox,et al.  U-Net: deep learning for cell counting, detection, and morphometry , 2018, Nature Methods.

[21]  K. Johnson Bowles,et al.  Taking a Long, Hard Look , 2000, Afterimage.

[22]  Steven S. Beauchemin,et al.  The computation of optical flow , 1995, CSUR.

[23]  Deep learning gets scope time , 2019, Nature Methods.

[24]  Gabriel A. Silva,et al.  Mapping the Spatiotemporal Dynamics of Calcium Signaling in Cellular Neural Networks Using Optical Flow , 2009, Annals of Biomedical Engineering.

[25]  Kenneth M. Yamada,et al.  One-dimensional topography underlies three-dimensional fibrillar cell migration , 2009, The Journal of cell biology.

[26]  Florian Jug,et al.  Cell segmentation methods for label-free contrast microscopy: review and comprehensive comparison , 2019, BMC Bioinformatics.

[27]  Fabian J. Theis,et al.  fastER: a user‐friendly tool for ultrafast and robust cell segmentation in large‐scale microscopy , 2017, Bioinform..

[28]  C. Wilkinson,et al.  Topographical control of cell behaviour: II. Multiple grooved substrata. , 1990, Development.

[29]  Núria Gavara,et al.  Lifeact-TagGFP2 alters F-actin organization, cellular morphology and biophysical behaviour , 2019, Scientific Reports.

[30]  Kazuo Sutoh,et al.  Keratocyte-like locomotion in amiB-null Dictyostelium cells. , 2004, Cell motility and the cytoskeleton.

[31]  Erik H. W. Meijering,et al.  Cell Segmentation: 50 Years Down the Road [Life Sciences] , 2012, IEEE Signal Processing Magazine.