Nuquantus: Machine learning software for the characterization and quantification of cell nuclei in complex immunofluorescent tissue images

Determination of fundamental mechanisms of disease often hinges on histopathology visualization and quantitative image analysis. Currently, the analysis of multi-channel fluorescence tissue images is primarily achieved by manual measurements of tissue cellular content and sub-cellular compartments. Since the current manual methodology for image analysis is a tedious and subjective approach, there is clearly a need for an automated analytical technique to process large-scale image datasets. Here, we introduce Nuquantus (Nuclei quantification utility software) - a novel machine learning-based analytical method, which identifies, quantifies and classifies nuclei based on cells of interest in composite fluorescent tissue images, in which cell borders are not visible. Nuquantus is an adaptive framework that learns the morphological attributes of intact tissue in the presence of anatomical variability and pathological processes. Nuquantus allowed us to robustly perform quantitative image analysis on remodeling cardiac tissue after myocardial infarction. Nuquantus reliably classifies cardiomyocyte versus non-cardiomyocyte nuclei and detects cell proliferation, as well as cell death in different cell classes. Broadly, Nuquantus provides innovative computerized methodology to analyze complex tissue images that significantly facilitates image analysis and minimizes human bias.

[1]  Bernd Bodenmiller,et al.  Automatic single cell segmentation on highly multiplexed tissue images , 2015, Cytometry. Part A : the journal of the International Society for Analytical Cytology.

[2]  Daniele Torella,et al.  Adult c-kit(pos) cardiac stem cells fulfill Koch's postulates as causal agents for cardiac regeneration. , 2014, Circulation research.

[3]  Patrick Bouthemy,et al.  Patch-Based Nonlocal Functional for Denoising Fluorescence Microscopy Image Sequences , 2010, IEEE Transactions on Medical Imaging.

[4]  Ciro Indolfi,et al.  Adult c-kitpos Cardiac Stem Cells Are Necessary and Sufficient for Functional Cardiac Regeneration and Repair , 2013, Cell.

[5]  Clive Standley,et al.  Advances in microscopy techniques. , 2011, Archives of pathology & laboratory medicine.

[6]  Chris Bakal,et al.  Visualizing cellular imaging data using PhenoPlot , 2015, Nature Communications.

[7]  Yibin Wang,et al.  p38 MAP kinase inhibition enables proliferation of adult mammalian cardiomyocytes. , 2005, Genes & development.

[8]  Steven R Houser,et al.  Are resident c-Kit+ cardiac stem cells really all that are needed to mend a broken heart? , 2013, Circulation research.

[9]  Chung-Ming Chen,et al.  Computer-Aided Detection and Diagnosis in Medical Imaging , 2013, Comput. Math. Methods Medicine.

[10]  Anthony B. Firulli,et al.  Recombinant Neuregulin 1 Does Not Activate Cardiomyocyte DNA Synthesis in Normal or Infarcted Adult Mice , 2014, PloS one.

[11]  Yvette I. Sheline,et al.  Evaluation of 5-ethynyl-2′-deoxyuridine staining as a sensitive and reliable method for studying cell proliferation in the adult nervous system , 2010, Brain Research.

[12]  Polina Golland,et al.  Scoring diverse cellular morphologies in image-based screens with iterative feedback and machine learning , 2009, Proceedings of the National Academy of Sciences.

[13]  N. Kostomitsopoulos,et al.  A comparative anatomic and physiologic overview of the porcine heart. , 2014, Journal of the American Association for Laboratory Animal Science : JAALAS.

[14]  Chih-Jen Lin,et al.  LIBLINEAR: A Library for Large Linear Classification , 2008, J. Mach. Learn. Res..

[15]  Mathews Jacob,et al.  Design of steerable filters for feature detection using canny-like criteria , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Tony Lindeberg,et al.  Edge Detection and Ridge Detection with Automatic Scale Selection , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[17]  J. Fleiss Measuring nominal scale agreement among many raters. , 1971 .

[18]  J. Terrovitis,et al.  Cardiomyocyte proliferation vs progenitor cells in myocardial regeneration: The debate continues , 2013, Global cardiology science & practice.

[19]  S. Houser,et al.  A Characterization and Targeting of the Infarct Border Zone in a Swine Model of Myocardial Infarction , 2012, Clinical and translational science.

[20]  P. Doevendans,et al.  Cardiovascular phenotyping in mice. , 1998, Cardiovascular research.

[21]  Don R. Hush,et al.  Interactive Machine Learning in Data Exploitation , 2013, Computing in Science & Engineering.

[22]  Deborah Vela,et al.  Cardiomyocyte death and renewal in the normal and diseased heart. , 2008, Cardiovascular pathology : the official journal of the Society for Cardiovascular Pathology.

[23]  D. Gudbjartsson,et al.  Variants in ELL2 influencing immunoglobulin levels associate with multiple myeloma , 2015, Nature Communications.

[24]  Kun Liu,et al.  Rotation-Invariant HOG Descriptors Using Fourier Analysis in Polar and Spherical Coordinates , 2014, International Journal of Computer Vision.

[25]  Thomas E Sharp,et al.  Bone-Derived Stem Cells Repair the Heart After Myocardial Infarction Through Transdifferentiation and Paracrine Signaling Mechanisms , 2013, Circulation research.

[26]  Gang Zhang,et al.  Quantitative assessment on the cloning efficiencies of lentiviral transfer vectors with a unique clone site , 2012, Scientific Reports.

[27]  Timoteo Carletti,et al.  The Stochastic Evolution of a Protocell: The Gillespie Algorithm in a Dynamically Varying Volume , 2011, Comput. Math. Methods Medicine.

[28]  R. Malladi,et al.  Segmentation of nuclei and cells using membrane related protein markers , 2001, Journal of microscopy.

[29]  M.,et al.  Statistical and Structural Approaches to Texture , 2022 .

[30]  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.

[31]  Ichiro Manabe,et al.  Cellular Interplay between Cardiomyocytes and Nonmyocytes in Cardiac Remodeling , 2011, International journal of inflammation.

[32]  N. Frangogiannis,et al.  Fibroblasts in myocardial infarction: a role in inflammation and repair. , 2014, Journal of molecular and cellular cardiology.

[33]  B. S. Manjunath,et al.  Biological imaging software tools , 2012, Nature Methods.

[34]  SametHanan,et al.  Efficient Component Labeling of Images of Arbitrary Dimension Represented by Linear Bintrees , 1988 .

[35]  H. Irshad,et al.  Methods for Nuclei Detection, Segmentation, and Classification in Digital Histopathology: A Review—Current Status and Future Potential , 2014, IEEE Reviews in Biomedical Engineering.

[36]  William M. Wells,et al.  Validation of image segmentation by estimating rater bias and variance , 2008, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[37]  Daniel Heim,et al.  Detection and Segmentation of Cell Nuclei in Virtual Microscopy Images: A Minimum-Model Approach , 2012, Scientific Reports.

[38]  Jianwei Zhang,et al.  Recent Advances in Morphological Cell Image Analysis , 2012, Comput. Math. Methods Medicine.

[39]  Fabian Rudolf,et al.  Accurate cell segmentation in microscopy images using membrane patterns , 2014, Bioinform..

[40]  Pauli Rämö,et al.  CellClassifier: supervised learning of cellular phenotypes , 2009, Bioinform..

[41]  Scott T. Clarke,et al.  Detection of S-phase cell cycle progression using 5-ethynyl-2'-deoxyuridine incorporation with click chemistry, an alternative to using 5-bromo-2'-deoxyuridine antibodies. , 2008, BioTechniques.

[42]  S. Hodge,et al.  Zinc and Zinc Transporters in Macrophages and Their Roles in Efferocytosis in COPD , 2014, PloS one.

[43]  Hanan Samet,et al.  Efficient Component Labeling of Images of Arbitrary Dimension Represented by Linear Bintrees , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[44]  Jon C. Aster,et al.  Robbins BASIC PATHOLOGY , 2002, Robbins Basic Pathology.

[45]  Henry K. Wong,et al.  Apoptosis in Tissue Injury , 2006 .

[46]  J. Fleiss,et al.  Statistical methods for rates and proportions , 1973 .

[47]  Kayvan Najarian,et al.  An Entropy-Based Automated Cell Nuclei Segmentation and Quantification: Application in Analysis of Wound Healing Process , 2013, Comput. Math. Methods Medicine.

[48]  Qing Nie,et al.  Mouse cardiac surgery: comprehensive techniques for the generation of mouse models of human diseases and their application for genomic studies. , 2004, Physiological genomics.

[49]  I. Tikkanen,et al.  Cardiomyocyte apoptosis and ventricular remodeling after myocardial infarction in rats. , 2001, American journal of physiology. Heart and circulatory physiology.

[50]  M. Kubát An Introduction to Machine Learning , 2017, Springer International Publishing.

[51]  Matthew McAuliffe,et al.  Whole cell segmentation in solid tissue sections , 2005, Cytometry. Part A : the journal of the International Society for Analytical Cytology.

[52]  D. Loo,et al.  In situ detection of apoptosis by the TUNEL assay: an overview of techniques. , 2011, Methods in molecular biology.

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

[54]  Richard T. Lee,et al.  Cardiac regeneration based on mechanisms of cardiomyocyte proliferation and differentiation. , 2014, Stem cell research.

[55]  Luc Florack,et al.  An Efficient Method for Tensor Voting Using Steerable Filters , 2006, ECCV.

[56]  Lesley Oakley,et al.  The Debate Continues … , 1985, Children Australia.

[57]  Jibin Zhou,et al.  Cardiomyocyte-specific deletion of Gsk3α mitigates post-myocardial infarction remodeling, contractile dysfunction, and heart failure. , 2014, Journal of the American College of Cardiology.