Understanding and Quantifying the Dancing Behavior of Stem Cells Before Attachment Clinton Y. Jung 1 and Dr. Bir Bhanu 2, Department of Electrical Engineering.

Slides:



Advertisements
Similar presentations
IntroductionIntroduction AbstractAbstract AUTOMATIC LICENSE PLATE LOCATION AND RECOGNITION ALGORITHM FOR COLOR IMAGES Kerem Ozkan, Mustafa C. Demir, Buket.
Advertisements

Clustering & image segmentation Goal::Identify groups of pixels that go together Segmentation.
Histogram Analysis to Choose the Number of Clusters for K Means By: Matthew Fawcett Dept. of Computer Science and Engineering University of South Carolina.
Automatic Histogram Threshold Using Fuzzy Measures 呂惠琪.
Automatic Thresholding
1 Video Processing Lecture on the image part (8+9) Automatic Perception Volker Krüger Aalborg Media Lab Aalborg University Copenhagen
Lecture 07 Segmentation Lecture 07 Segmentation Mata kuliah: T Computer Vision Tahun: 2010.
Person Re-Identification Application for Android
電腦視覺 Computer and Robot Vision I Chapter2: Binary Machine Vision: Thresholding and Segmentation Instructor: Shih-Shinh Huang 1.
AlgirdasBeinaravičius Gediminas Mazrimas Salman Mosslem.
September 10, 2013Computer Vision Lecture 3: Binary Image Processing 1Thresholding Here, the right image is created from the left image by thresholding,
TEMPLATE DESIGN © Detection of explosives using image analysis Dr Charles A Bouman, Eri Haneda, Aarthi Balachander, Krithika.
Medical Imaging Mohammad Dawood Department of Computer Science University of Münster Germany.
Medical Imaging Mohammad Dawood Department of Computer Science University of Münster Germany.
EE 7730 Image Segmentation.
MRI Image Segmentation for Brain Injury Quantification Lindsay Kulkin 1 and Bir Bhanu 2 1 Department of Biomedical Engineering, Syracuse University, Syracuse,
Segmentation Divide the image into segments. Each segment:
Hierarchical Image Segmentation for Identifying Stroke Regions In Apparent Diffusion Coefficient (ADC) Image Maps Anthony Bianchi UCR 2007 Advisor:
Objective of Computer Vision
Computer Vision Basics Image Terminology Binary Operations Filtering Edge Operators.
A Novel 2D To 3D Image Technique Based On Object- Oriented Conversion.
Image Segmentation Using Region Growing and Shrinking
Object Tracking for Retrieval Application in MPEG-2 Lorenzo Favalli, Alessandro Mecocci, Fulvio Moschetti IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR.
Tal Mor  Create an automatic system that given an image of a room and a color, will color the room walls  Maintaining the original texture.
Chapter 3 Binary Image Analysis. Types of images ► Digital image = I[r][c] is discrete for I, r, and c.  B[r][c] = binary image - range of I is in {0,1}
UNDERSTANDING DYNAMIC BEHAVIOR OF EMBRYONIC STEM CELL MITOSIS Shubham Debnath 1, Bir Bhanu 2 Embryonic stem cells are derived from the inner cell mass.
Final project – Computational Biology
Machine Vision for Robots
Equations Speckle contrast : K(T) = σ s / Decay rate of autocorrelation: g(T) = / Critical decay time: τ 0 = g(e -1 sec) Relative velocity:v = x/ τ 0 Algorithms.
Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli
CS 6825: Binary Image Processing – binary blob metrics
CS 376b Introduction to Computer Vision 02 / 22 / 2008 Instructor: Michael Eckmann.
MRI Image Segmentation for Brain Injury Quantification Lindsay Kulkin BRITE REU 2009 Advisor: Bir Bhanu August 20, 2009.
Medical Imaging Dr. Mohammad Dawood Department of Computer Science University of Münster Germany.
September 23, 2014Computer Vision Lecture 5: Binary Image Processing 1 Binary Images Binary images are grayscale images with only two possible levels of.
Digital Image Processing Lecture 18: Segmentation: Thresholding & Region-Based Prof. Charlene Tsai.
Chapter 10, Part II Edge Linking and Boundary Detection The methods discussed in the previous section yield pixels lying only on edges. This section.
Clinton Jung Advisor: Bir Bhanu Center for Research in Intelligent Systems August 20, 2009.
Digital Camera and Computer Vision Laboratory Department of Computer Science and Information Engineering National Taiwan University, Taipei, Taiwan, R.O.C.
Handwritten Hindi Numerals Recognition Kritika Singh Akarshan Sarkar Mentor- Prof. Amitabha Mukerjee.
1 Regions and Binary Images Hao Jiang Computer Science Department Sept. 25, 2014.
Computer Graphics and Image Processing (CIS-601).
Detection of Explosives Using Image Analysis Krithika Chandrasekar, Devang Parekh, Yichen Lu, Xiaodong Li Shruthi Sanjeevi Reddy, Liqun Yang Purdue University.
Computational BioMedical Informatics
1 Regions and Binary Images Hao Jiang Computer Science Department Sept. 24, 2009.
Image Segmentation in Color Space By Anisa Chaudhary.
PROJECT#3(b) Astrocyte Analysis
Motion Detection and Processing Performance Analysis Thomas Eggers, Mark Rosenberg Department of Electrical and Systems Engineering Abstract Histograms.
Digital Image Processing
    LICENSE PLATE EXTRACTION AND CHARACTER SEGMENTATION   By HINA KOCHHAR NITI GOEL Supervisor Dr. Rajeev Srivastava        
Nottingham Image Analysis School, 23 – 25 June NITS Image Segmentation Guoping Qiu School of Computer Science, University of Nottingham
Image Segmentation Nitin Rane. Image Segmentation Introduction Thresholding Region Splitting Region Labeling Statistical Region Description Application.
SUREILLANCE IN THE DEPARTMENT THROUGH IMAGE PROCESSING F.Y.P. PRESENTATION BY AHMAD IJAZ & UFUK INCE SUPERVISOR: ASSOC. PROF. ERHAN INCE.
Quantitative Analysis of Mitochondrial Tubulation Using 3D Imaging Saritha Dwarakapuram*, Badrinath Roysam*, Gang Lin*, Kasturi Mitra§ Department of Electrical.
Machine Vision ENT 273 Hema C.R. Binary Image Processing Lecture 3.
Color Image Segmentation Mentor : Dr. Rajeev Srivastava Students: Achit Kumar Ojha Aseem Kumar Akshay Tyagi.
Detection, Tracking and Recognition in Video Sequences Supervised By: Dr. Ofer Hadar Mr. Uri Perets Project By: Sonia KanOra Gendler Ben-Gurion University.
3D Scanning Based on Computer Vision
Course : T Computer Vision
IMAGE ANALYSIS AND SEGMENTATION OF ANATOMICAL FEATURES OF CERVIX UTERI IN COLOR SPACE Viara Van Raad STI – Medical Systems, 733 Bishop St, Makai Tower,
Object Recognition and Feature Detection Using MATLAB
Image Processing For Soft X-Ray Self-Seeding
Computer Vision Lecture 13: Image Segmentation III
Computer Vision Lecture 12: Image Segmentation II
Counting Iron-Absorbed Small Intestinal Cells
Department of Computer Engineering
Image Segmentation.
Computer and Robot Vision I
Computer and Robot Vision I
Image Segmentation Using Region Growing and Shrinking
Presentation transcript:

Understanding and Quantifying the Dancing Behavior of Stem Cells Before Attachment Clinton Y. Jung 1 and Dr. Bir Bhanu 2, Department of Electrical Engineering 1. Biomedical Engineering, Johns Hopkins University, MD 21218, USA 2. Center for Research in Intelligent Systems, University of California, Riverside, CA 92521, USA Stem cells have proven themselves to be a promising frontier of biomedical research. They have an ability to develop into different cell types in the body especially when the human body is still in its earliest stages of life and growth. As the body ages, stem cells continue to serve in different tissues and divide to replenish other cells. What is incredible about stem cells is the fact that they can become other types of cells in order to perform a specialized function. As we continue to observe stem cells and try to understand their behaviors in order to more fully tap into their potential, learning about the different states of the stem cells is of significant importance. In this project, stem cells are hypothesized to be in one of five states—attached, non-attached, dancing, death, and mitosis. We focus on investigating the dancing, or pre-attachment, behavior of stem cells. This is a new, previously unobserved phenomenon. In this state, the cell loses its defined border and instead has several small bulbs attached to it. INTRODUCTION TECHNICAL METHODS DATA /IMAGE SEGMENTATION PROCESS ANALYSIS CONCLUSIONS Unattached Cell Attached Cell Pre-attachment Behavior Connected Components Image -First, apply Otsu’s Method to separate the image into two groups of pixels such that the intra-class variance is minimal and inter-class variance maximal -Next, apply connected components algorithm, another image segmentation method. -Expand connected components program to count the number of pixels in a cell undergoing pre- attachment behavior and plot this value over time -Also expand program to compute average grayscale value of a dancing cell over time and examine the averages and standard deviations of these values over time per frame. -Compare calculations for different stem cell stages Example of a single frame of video OBJECTIVES -Crop images for the cells undergoing dancing and play as video for each cell -Perform segmentation techniques -Compute features -Quantify the dancing phenomenon and change in shape Binary Image Histogram Grayscale Image Grayscale Value Number of Pixels Grayscale Value Number of Pixels Step 1: Input Original Image and convert to grayscale Step 2: Find threshold automatically using histogram Step 3: Split image into two classes (binary) based on the threshold value. This final image will have pixel values of either 0 or 255. Otsu’s Method Connected Components Algorithm -We are supplied videos captured in time-lapse fashion. The videos are in.avi format and cover 3.5 hours over the course of 106 still images -All programming and image segmentation techniques are carried out in MATLAB code Step 1: Input Original Image which must be a binary image Step 2: For each pixel, examine surrounding 8 pixels If the pixel is neighboring, assign label 1 If pixel is not neighboring, assign label 0 Step 3: Continue to check each pixel line by line until entire image is checked, resulting in a matrix of 1’s and 0’s Step 4: Convert image back to rgb in order to display components in colors. Time (Video Frame Number) Average Grayscale Value Average Grayscale Value vs. Time Total Number of Pixels vs. Time Time (Video Frame Number) Total Number of Pixels -The graphical analysis shows that the cells in the dancing, attached, and unattached states have very distinct average grayscale values per frame over the course of the video and can potentially be automatically differentiated using this property -However, the standard deviations of these values for the different stem cell states have a more inconsistent pattern which results in interference with each other -A preliminary calculation of the changes in pixel sizes for a cell undergoing pre-attachment behavior displays no periodic behavior Acknowledgements Time (Video Frame Number) Grayscale Standard Deviation Grayscale Standard Deviation vs. Time Jun Wang, Benjamin Guan, Dr. Prue Talbot, Shawn Fonteno, Sabrina Lin, Giovanni Denina, National Science Foundation Calculated Threshold Value: 162 Calculated Threshold Value: 155 Calculated Threshold Value: 138