Image Interpretation Methods for Protein Location in Cells Meel Velliste Murphy Lab Dept. of Biomedical Engineering Carnegie Mellon University Copyright.

Slides:



Advertisements
Similar presentations
Cells Under the Microscope
Advertisements

(SubLoc) Support vector machine approach for protein subcelluar localization prediction (SubLoc) Kim Hye Jin Intelligent Multimedia Lab
Lessons Learned from Measuring Cell Response by Quantitative Automated Microscopy FDA Workshop, Potency Measurements for Cellular and Gene Therapy Products,
電腦視覺 Computer and Robot Vision I
Course Syllabus 1.Color 2.Camera models, camera calibration 3.Advanced image pre-processing Line detection Corner detection Maximally stable extremal regions.
Computer Vision Lecture 16: Texture
Course Syllabus 1.Color 2.Camera models, camera calibration 3.Advanced image pre-processing Line detection Corner detection Maximally stable extremal regions.
ROC Statistics for the Lazy Machine Learner in All of Us Bradley Malin Lecture for COS Lab School of Computer Science Carnegie Mellon University 9/22/2005.
Computational Biology, Part 23 Segmentation and Feature Calculation for Automated Interpretation of Subcellular Patterns Robert F. Murphy Copyright 
Clustering… in General In vector space, clusters are vectors found within  of a cluster vector, with different techniques for determining the cluster.
Three-dimensional co-occurrence matrices & Gabor filters: Current progress Gray-level co-occurrence matrices Carl Philips Gabor filters Daniel Li Supervisor:
Tour of the Cell. Robert Hooke ( ) Robert Hooke : examined thinly sliced cork and coined term “cell”
1 Life-and-Death Problem Solver in Go Author: Byung-Doo Lee Dept of Computer Science, Univ. of Auckland Presented by: Xiaozhen Niu.
Texture Classification Using QMF Bank-Based Sub-band Decomposition A. Kundu J.L. Chen Carole BakhosEvan Kastner Dave AbramsTommy Keane Rochester Institute.
Computational Biology, Part 28 Automated Interpretation of Subcellular Patterns in Microscope Images III Robert F. Murphy Copyright  1996, 1999,
Efficient Estimation of Emission Probabilities in profile HMM By Virpi Ahola et al Reviewed By Alok Datar.
Feature Screening Concept: A greedy feature selection method. Rank features and discard those whose ranking criterions are below the threshold. Problem:
Machine Learning Challenges in Location Proteomics Robert F. Murphy Departments of Biological Sciences and Biomedical Engineering & Center for Automated.
Classification of Protein Localization Patterns in 3-D Meel Velliste Carnegie Mellon University.
Feature Subset Selection using Minimum Cost Spanning Trees Mike Farah Supervisor: Dr. Sid Ray.
Smart Traveller with Visual Translator for OCR and Face Recognition LYU0203 FYP.
Texture-based Deformable Snake Segmentation of the Liver Aaron Mintz Daniela Stan Raicu, PhD Jacob Furst, PhD.
Making Protein Localization Features More Robust Meel Velliste Carnegie Mellon University.
Biomedical Image Analysis and Machine Learning BMI 731 Winter 2005 Kun Huang Department of Biomedical Informatics Ohio State University.
Entropy and some applications in image processing Neucimar J. Leite Institute of Computing
Introduction --Classification Shape ContourRegion Structural Syntactic Graph Tree Model-driven Data-driven Perimeter Compactness Eccentricity.
Using Error-Correcting Codes For Text Classification Rayid Ghani Center for Automated Learning & Discovery, Carnegie Mellon University.
Image Pattern Recognition The identification of animal species through the classification of hair patterns using image pattern recognition: A case study.
Lecture 19 Representation and description II
Integration of PSLID and SLIF with “Virtual Cell” Robert F. Murphy, Les Loew & Ion Moraru Ray and Stephanie Lane Professor of Computational Biology Molecular.
Cell Structure Section 1: Looking at Cells Section 2: Cell Features
Medical Image Analysis Image Representation and Analysis Figures come from the textbook: Medical Image Analysis, by Atam P. Dhawan, IEEE Press, 2003.
Biology: Cell Review Modern Biology©2009 Holt, Rinehart, & Winston Chapter 4.
CPSC 601 Lecture Week 5 Hand Geometry. Outline: 1.Hand Geometry as Biometrics 2.Methods Used for Recognition 3.Illustrations and Examples 4.Some Useful.
Protein Secondary Structure Prediction with inclusion of Hydrophobicity information Tzu-Cheng Chuang, Okan K. Ersoy and Saul B. Gelfand School of Electrical.
ECE 8443 – Pattern Recognition LECTURE 03: GAUSSIAN CLASSIFIERS Objectives: Normal Distributions Whitening Transformations Linear Discriminants Resources.
Hierarchical Distributed Genetic Algorithm for Image Segmentation Hanchuan Peng, Fuhui Long*, Zheru Chi, and Wanshi Siu {fhlong, phc,
Texture analysis Team 5 Alexandra Bulgaru Justyna Jastrzebska Ulrich Leischner Vjekoslav Levacic Güray Tonguç.
Texture. Texture is an innate property of all surfaces (clouds, trees, bricks, hair etc…). It refers to visual patterns of homogeneity and does not result.
Computational Biology, Part 24 Biological Imaging IV Robert F. Murphy Copyright  All rights reserved.
Digital Camera and Computer Vision Laboratory Department of Computer Science and Information Engineering National Taiwan University, Taipei, Taiwan, R.O.C.
Automatic Minirhizotron Root Image Analysis Using Two-Dimensional Matched Filtering and Local Entropy Thresholding Presented by Guang Zeng.
November 13, 2014Computer Vision Lecture 17: Object Recognition I 1 Today we will move on to… Object Recognition.
Classification Course web page: vision.cis.udel.edu/~cv May 12, 2003  Lecture 33.
Automated Target Recognition Using Mathematical Morphology Prof. Robert Haralick Ilknur Icke José Hanchi Computer Science Dept. The Graduate Center of.
CS 376b Introduction to Computer Vision 03 / 21 / 2008 Instructor: Michael Eckmann.
Introduction --Classification Shape ContourRegion Structural Syntactic Graph Tree Model-driven Data-driven Perimeter Compactness Eccentricity.
Dengsheng Zhang and Melissa Chen Yi Lim
Computer Graphics and Image Processing (CIS-601).
Prostate Cancer CAD Michael Feldman, MD, PhD Assistant Professor Pathology University Pennsylvania.
November 30, PATTERN RECOGNITION. November 30, TEXTURE CLASSIFICATION PROJECT Characterize each texture so as to differentiate it from one.
1Ellen L. Walker Category Recognition Associating information extracted from images with categories (classes) of objects Requires prior knowledge about.
A NOVEL METHOD FOR COLOR FACE RECOGNITION USING KNN CLASSIFIER
Ivica Dimitrovski 1, Dragi Kocev 2, Suzana Loskovska 1, Sašo Džeroski 2 1 Faculty of Electrical Engineering and Information Technologies, Department of.
Chapter 13 (Prototype Methods and Nearest-Neighbors )
References Books: Chapter 11, Image Processing, Analysis, and Machine Vision, Sonka et al Chapter 9, Digital Image Processing, Gonzalez & Woods.
CS 376b Introduction to Computer Vision 03 / 31 / 2008 Instructor: Michael Eckmann.
1 Overview representing region in 2 ways in terms of its external characteristics (its boundary)  focus on shape characteristics in terms of its internal.
Advanced Biology Cell Structure Chapter 5. All organisms are composed of cells  Prokaryotes have a single circular molecule of DNA, while eukaryotic.
Non-parametric Methods for Clustering Continuous and Categorical Data Steven X. Wang Dept. of Math. and Stat. York University May 13, 2010.
Chapter 4 A View of the Cell. Cell History The microscope was invented in the 17th century Using a microscope, Robert Hooke discovered cells in 1665 All.
Applying Deep Neural Network to Enhance EMPI Searching
Recognition of biological cells – development
Construction Engineering 221
Typical Image Selection
Object Recognition Today we will move on to… April 12, 2018
Computer and Robot Vision I
Anastasia Baryshnikova  Cell Systems 
Image Segmentation.
Model Selection in Parameterizing Cell Images and Populations
Presentation transcript:

Image Interpretation Methods for Protein Location in Cells Meel Velliste Murphy Lab Dept. of Biomedical Engineering Carnegie Mellon University Copyright  2002

Introduction Image source

Introduction Sequence databases allow search by similarity Database GSNWLAMQLT yfbI Rv2560 fliR The same is true for protein structure databases

Introduction Sequence databases allow search by similarity Database ? ? ? The same is true for protein structure databases How about protein location?

Basic Idea in Sequence Comparison M A T N W G S L L Q M D T N P V S L L R Similarity Matrix 25.7

Location Info in Databases Unstructured text - most databases Standardized keywords - YPD Fluorescence microscope images - TRIPLES, YPL.db Numerical descriptors needed

Subcellular Location Features (SLF) 49 Zernike Moments 13 Haralick Texture Features 22 Morphological Features - derived from morphological image processing: –Object finding –Edge finding –Convex Hulls

Morphological Features Area Distance from COF Distance from DNA COF

Some Example Features –Number of Objects –Euler Number –Average Object Size –Standard Deviation of Object sizes –Ratio of the Largest to the Smallest Object Size –Average Distance of Objects from COF –Standard Deviation of Object Distances from COF –Ratio of the Largest to Smallest Object Distance

DNA Features –The average object distance from the COF of the DNA image –The variance of object distances from the DNA COF –The ratio of the largest to the smallest object to DNA COF distance –The distance between the protein COF and the DNA COF –The ratio of the area occupied by protein to that occupied by DNA –The fraction of the protein fluorescence that co-localizes with DNA

Ten Major Classes of Protein Location

Classification Numerical Features computed from each image This is a Microtubule pattern feature1 feature2... featureN Image Image ImageM Artificial Neural Network classifies the image 83% Accuracy achieved

Goals Implement new 2D features and improve Haralick texture features Test performance on mixtures of more than one cell type and more than one microscopy source Extend features to 3D Develop Object-level classification

Skeleton Features: –Length of skeleton –Number of branch points –Fraction of object area taken up by skeleton Fraction of fluorescence below threshold New Features (SLF7)

Based on gray-level co-occurrence If image has G gray-levels: –Compute G x G co-occurrence probability matrix P( i, j) –Compute features by summing and differencing the matrix Features highly dependent on: –Number of gray-levels –Pixel resolution Haralick Texture Features

Percent Benefit of Texture Features Baseline accuracy = 86.4%

Solution Always down-sample and re- quantize to: –1.15 um/pixel –256 gray-levels Resolution-independent robust classification possible

Original Image 256 Gray-levels, 0.23 um/pixel

Down-sampled 256 Gray-levels, 1.15 um/pixel

Classification Results with SLF8 Overall accuracy = 88%

Classification of Images from Mixed Sources Overall accuracy = 92% 97102Tubul 28981Lyso 23951Golgi 73188DNA TubulLysoGolgiDNA True Class Predicted Class

Extending to 3D Results for 2-D images can be dependent on the z-position of the slice BOTTOMTOP

Extending to 3D Features sensitive to 3D distribution will be needed for polarized cells (e.g. epithelial cells) Proteins may distribute differently to the basolateral and apical surfaces

Actin (Microfilament)

Tubulin (Microtubule)

Mitochondrial

Endoplasmic Reticulum (ER)

TfR (Endosomal)

LAMP2 (Lysosomal)

Giantin (Golgi)

gpp130 (Golgi)

Nucleolin (Nucleolar)

DNA (Nuclear)

Total-Protein (Cytoplasmic)

Features for 3-D Images Used a subset of the same Morphological features as used with 2-D patterns: –Number of Objects –Euler Number –Average Object Size –Standard Deviation of Object sizes –Ratio of the Largest to the Smallest Object Size –Average Distance of Objects from COF –Standard Deviation of Object Distances from COF –Ratio of the Largest to Smallest Object Distance

Separating Components of Distance Features Can separate out Horizontal and Vertical components of distance –2D euclidean for x and y –Signed 1D distance for z Some morphological features involve measures of distance –e.g., Average distance of objects from the COF of DNA

Classification with 3D-SLF9 Features 10 classes, Overall accuracy = 91%

Classification with 3D-SLF9 Features 11 classes, Overall accuracy = 91%

11 classes, Overall accuracy = 94% …with 9 Selected 3D-SLF9 Features

2D Classification with 14 SLF2 Features 11 classes, Overall accuracy = 88%

Set size 9, Overall accuracy = 99.7% Classification of Sets of 3D Images

Conclusions For accurate determination of subcellular location: –High resolution microscopy is essential –3D images have an advantage over 2D images –SDA can achieve severely sub-optimal results

Protein Subcellular Location Patterns can be represented as Numerical Vectors Can be computed from either 2D or 3D images Features are robust to different microscopy methods or cell types Conclusions

Feature Extractor 38.1 Quantitative comparison of location is possible Roques and Murphy (2002)

Protein databases can be searched by similarity of location Database crp21 froX CAP-9 Conclusions

Automated interpretation of location patterns is possible: –Automated classification of location patterns (Boland and Murphy, 2001; Murphy et al. 2001; Velliste and Murphy, 2002) –Automated choice of representative images (Markey et al. 1999) –Rigorous statistical comparison of imaging experiments (Roques and Murphy, 2002) –Building a “family tree” of protein location Conclusions

Acknowledgements Robert F. Murphy - for being a great thesis advisor Michael V. Boland - founding work on 2D Subcellular Location Features Simon Watkins and the staff at the Center for Biologic Imaging at UPitt - providing the facilities for and assisting with microscopy Aaron C. Rising - help with collecting 3D images Gregory Porreca - improving Haralick features and classifying mixed image sets