Bioimage Informatics for Systems Pharmacology Authors : Fuhai Li Zheng Yin Guangxu Jin Hong Zhao Stephen T. C. Wong Presented by : Iffat chowdhury
Motivation Image is worth for phenotypic changes identification High resolution microscopy, fluorescent labeling Rich in terms of information of biological processes Bioimage informatics
Bioimage informatics
Image based Studies Example Multicolor cell imaging-based studies Live-cell imaging-based studies Neuron imaging-based studies C. elegans imaging-based studies
Image based Studies Example Multicolor cell imaging-based studies Live-cell imaging-based studies Neuron imaging-based studies C. elegans imaging-based studies
Multicolor cell imaging-based studies Multiple fluorescent markers Feature extraction Drosophila cell Softwares : CellProfiler, Fiji, Icy, GcellIQ, PhenoRipper
Multicolor cell imaging-based studies
Multicolor cell imaging-based studies Multiple fluorescent markers Feature extraction Drosophila cell Softwares : CellProfiler, Fiji, Icy, GcellIQ, PhenoRipper
Image based Studies Example Multicolor cell imaging-based studies Live-cell imaging-based studies Neuron imaging-based studies C. elegans imaging-based studies
Live-cell imaging-based studies Progression, proliferation, migration of cell Dynamic behaviors of cells Live Hela cell images Softwares : CellProfiler, Fiji, BioimageXD, Icy, CellCognition, DCellIQ, TLM-Tracker
Live-cell imaging-based studies
Live-cell imaging-based studies Progression, proliferation, migration of cell Dynamic behaviors of cells Live Hela cell images Softwares : CellProfiler, Fiji, BioimageXD, Icy, CellCognition, DCellIQ, TLM-Tracker
Image based Studies Example Multicolor cell imaging-based studies Live-cell imaging-based studies Neuron imaging-based studies C. elegans imaging-based studies
Neuron imaging-based studies To study brain functions and disorders Use super-resolution microscope Softwares : NeurphologyJ, NeuronJ, NeuriteTracer, NeuriteIQ, NeuronMetrics, NeuronStudio, Vaa3D
Neuron imaging-based studies
Neuron imaging-based studies To study brain functions and disorders Use super-resolution microscope Softwares : NeurphologyJ, NeuronJ, NeuriteTracer, NeuriteIQ, NeuronMetrics, NeuronStudio, Vaa3D
Neuron imaging-based studies
Image based Studies Example Multicolor cell imaging-based studies Live-cell imaging-based studies Neuron imaging-based studies C. elegans imaging-based studies
Caenorhabditis elegans imaging-based studies Common animal model for drug and target discovery Consists of only hundred of cells Embryonic development
Caenorhabditis elegans imaging-based studies Source : Wikipedia
Caenorhabditis elegans imaging-based studies Common animal model for drug and target discovery Consists of only hundred of cells Embryonic development
Bioimage informatics
Bioimage informatics
Object Detection Detect the locations of individual objects Facilitate the segmentation by giving the position and initial boundary information Two types of object detection : 1. Blob structure detection 2. Tube structure detection
Blob Structure Detection Nuclei detection Distance transformation Seeded watershed Intensity information Gradient vector
Blob Structure Detection
Blob Structure Detection Nuclei detection Distance transformation Seeded watershed Intensity information Gradient vector
Tube Structure Detection Intensity remains constant Centerline detection Edge detectors Machine-learning
Tube Structure Detection
Tube Structure Detection Intensity remains constant Centerline detection Edge detectors Machine-learning
Tube Structure Detection
Bioimage informatics
Object Segmentation Delineate boundaries of objects Threshold segmentation Fuzzy-C-Means method Watershed algorithm Active contour model Level set representation Voronoi segmentation Graph cut method Softwares : CellProfiler, Fiji, Ilastik, SLIC
Object Segmentation
Object Segmentation Delineate boundaries of objects Threshold segmentation Fuzzy-C-Means method Watershed algorithm Active contour model Level set representation Voronoi segmentation Graph cut method Softwares : CellProfiler, Fiji, Ilastik, SLIC
Object Segmentation Figure taken from http://www.dma.fi.upm.es/mabellanas/tfcs/fvd/voronoi.html
Object Segmentation
Object Segmentation Delineate boundaries of objects Threshold segmentation Fuzzy-C-Means method Watershed algorithm Active contour model Level set representation Voronoi segmentation Graph cut method Softwares : CellProfiler, Fiji, Ilastik, SLIC
Bioimage Informatics
Object Tracking Study dynamic behaviors Three approaches : 1. Model evolution based 2. Spatial-temporal volume segmentation based 3. Segmentation based
Object Tracking
Object Tracking Study dynamic behaviors Three approaches : 1. Model evolution based 2. Spatial-temporal volume segmentation based 3. Segmentation based
Object Tracking
Object Tracking Study dynamic behaviors Three approaches : 1. Model evolution based 2. Spatial-temporal volume segmentation based 3. Segmentation based
Object Tracking
Model Evolution Based Cell / nuclei are detected first Boundary comes next Contour model Different objects get different colors
Spatial-Temporal Volume Segmentation Based 2D image sequences as 3D Level set segmentation approaches
Segmentation Based First detected and then segmented Tracking is dependent of segmentation and detection Association Filters may be used
Bioimage Informatics
Image Visualization Fiji, Icy, BioimageXD are for higher dimensional data NeuronStudio for neuron image analysis Farsight and vaa3D for microscopy images For customize tools, Visualization Toolkit helps.
Numerical Features Quantitative measuring Four quantitative features 1. Wavelet feature 2. Geometry feature 3. Zernike feature 4. Haralick texture feature
Numerical Features Wavelet feature : characterize the images in both – scale and frequency domain. Geometry feature : describe the shape and texture features. Zernike feature : projection and the use of Zernike moment. Haralick texture feature : use grey-level matrices
Phenotype Identification Cell cycle phase identification User defined phenotype, identification and classification
Cell Cycle Phase Identification Automated cell cycle phase identification is needed to calculate the dwelling time of individual cells in each phase. SVM, K-nearest neighbors, Bayesian classifiers Can be done during segmentation and tracking.
Cell Cycle Phase Identification
Cell Cycle Phase Identification Automated cell cycle phase identification is needed to calculate the dwelling time of individual cells in each phase. SVM, K-nearest neighbors, Bayesian classifiers Can be done during segmentation and tracking.
User Defined Phenotype, Identification and Classification Exhibit novel phenotype and unpredicted behaviors. Gaussian Mixture Model with statistics Clustering analysis Classifiers
User Defined Phenotype, Identification and Classification
User Defined Phenotype, Identification and Classification Exhibit novel phenotype and unpredicted behaviors. Gaussian Mixture Model with statistics Clustering analysis Classifiers
Multidimensional Profiling Analysis Clustering analysis SVM-based multivariate profiling analysis Factor-based multidimensional profiling analysis Subpopulation-based heterogeneity profiling analysis
Multidimensional Profiling Analysis Clustering analysis SVM-based multivariate profiling analysis Factor-based multidimensional profiling analysis Subpopulation-based heterogeneity profiling analysis
Clustering Analysis Experimental perturbations Softwares : Cluster 3.0, Java TreeView
Multidimensional Profiling Analysis Clustering analysis SVM-based multivariate profiling analysis Factor-based multidimensional profiling analysis Subpopulation-based heterogeneity profiling analysis
SVM-basheed Multivariate Profiling Analysis Wells with treated cells compared to wells with untreated cells. The differences are indicated by the outputs of SVM One is the accuracy and another is the normal vector of the hyperplane.
SVM-basheed Multivariate Profiling Analysis
Recommend
More recommend
