Persistence Diagram: Topological Characterization of Noise in Images

Slides:

Advertisements

Similar presentations

The General Linear Model (GLM)

Advertisements

1st level analysis: basis functions, parametric modulation and correlated regressors. 1 st of February 2012 Sylvia Kreutzer Max-Philipp Stenner Methods.

Convolution. Why? Image processing Remove noise from images (e.g. poor transmission (from space), measurement (X-Rays))

2806 Neural Computation Self-Organizing Maps Lecture Ari Visa.

3-D Computer Vision CSc83020 / Ioannis Stamos  Revisit filtering (Gaussian and Median)  Introduction to edge detection 3-D Computater Vision CSc

Sliding Window Filters and Edge Detection Longin Jan Latecki Computer Graphics and Image Processing CIS 601 – Fall 2004.

CDS 301 Fall, 2009 Image Visualization Chap. 9 November 5, 2009 Jie Zhang Copyright ©

Chapter 2: Bayesian Decision Theory (Part 2) Minimum-Error-Rate Classification Classifiers, Discriminant Functions and Decision Surfaces The Normal Density.

Multiple testing Justin Chumbley Laboratory for Social and Neural Systems Research Institute for Empirical Research in Economics University of Zurich With.

Gunhee Kim1 Eric P. Xing1 Li Fei-Fei2 Takeo Kanade1

Connectivity between MS lesion density and cortical thickness Keith Worsley Arnaud Charil Jason Lerch Department of Mathematics and Statistics, McConnell.

The General Linear Model (GLM)

Multiple comparison correction Methods & models for fMRI data analysis 29 October 2008 Klaas Enno Stephan Branco Weiss Laboratory (BWL) Institute for Empirical.

Independent Component Analysis (ICA) and Factor Analysis (FA)

Lecture 2: Image filtering

Kernel Methods Part 2 Bing Han June 26, Local Likelihood Logistic Regression.

Presentation Image Filters

With many thanks for slides & images to: FIL Methods group, Virginia Flanagin and Klaas Enno Stephan Dr. Frederike Petzschner Translational Neuromodeling.

CS559: Computer Graphics Lecture 3: Digital Image Representation Li Zhang Spring 2008.

Techniques for Estimating Layers from Polar Radar Imagery Jerome E. Mitchell, Geoffrey C. Fox, and David J. Crandall :: CReSIS NSF Site Visit :: School.

1 / 41 Inference and Computation with Population Codes 13 November 2012 Inference and Computation with Population Codes Alexandre Pouget, Peter Dayan,

OPTIMIZATION OF FUNCTIONAL BRAIN ROIS VIA MAXIMIZATION OF CONSISTENCY OF STRUCTURAL CONNECTIVITY PROFILES Dajiang Zhu Computer Science Department The University.

Lecture 2: Edge detection CS4670: Computer Vision Noah Snavely From Sandlot ScienceSandlot Science.

Enhanced Correspondence and Statistics for Structural Shape Analysis: Current Research Martin Styner Department of Computer Science and Psychiatry.

Phase Congruency Detects Corners and Edges Peter Kovesi School of Computer Science & Software Engineering The University of Western Australia.

Luke Bloy1, Ragini Verma2 The Section of Biomedical Image Analysis

1 Markov Random Fields with Efficient Approximations Yuri Boykov, Olga Veksler, Ramin Zabih Computer Science Department CORNELL UNIVERSITY.

Detecting multivariate effective connectivity Keith Worsley, Department of Mathematics and Statistics, McGill University, Montreal Jason Lerch, Montreal.

Edge detection Goal: Identify sudden changes (discontinuities) in an image Intuitively, most semantic and shape information from the image can be encoded.

Correlation random fields, brain connectivity, and astrophysics Keith Worsley Arnaud Charil Jason Lerch Francesco Tomaiuolo Department of Mathematics and.

Spatial Smoothing and Multiple Comparisons Correction for Dummies Alexa Morcom, Matthew Brett Acknowledgements.

Neural Networks Presented by M. Abbasi Course lecturer: Dr.Tohidkhah.

METU Informatics Institute Min720 Pattern Classification with Bio-Medical Applications Part 9: Review.

EE 551/451, Fall, 2006 Communication Systems Zhu Han Department of Electrical and Computer Engineering Class 15 Oct. 10 th, 2006.

An Area-Preserving Cortical Flattening Method Yuefeng Lu 1, Moo K. Chung 1,2,3,, Steve Robbins 4, Alan C. Evans 4 1 Department of Statistics, 2 W.M. Keck.

Lecture 10 Chapter 5: Image Restoration. Image restoration Image restoration is the process of recovering the original scene from the observed scene which.

Locating a Shift in the Mean of a Time Series Melvin J. Hinich Applied Research Laboratories University of Texas at Austin

Bayesian fMRI analysis with Spatial Basis Function Priors

Keith Worsley, McGill Jonathan Taylor,

Markov Random Fields with Efficient Approximations

Image gradients and edges

Tensor-based Surface Modeling and Analysis

Moo K. Chung1,3, Kim M. Dalton3, Richard J. Davidson2,3

Detection of Local Cortical Asymmetry via Discriminant Power Analysis

Human Brain Mapping Conference 2003 # 653

Wellcome Trust Centre for Neuroimaging University College London

Detecting Sparse Connectivity: MS Lesions, Cortical Thickness, and the ‘Bubbles’ Task in an fMRI Experiment Keith Worsley, Nicholas Chamandy, McGill Jonathan.

Edge detection Goal: Identify sudden changes (discontinuities) in an image Intuitively, most semantic and shape information from the image can be encoded.

Dr. Chang Shu COMP 4900C Winter 2008

Towards Understanding the Invertibility of Convolutional Neural Networks Anna C. Gilbert1, Yi Zhang1, Kibok Lee1, Yuting Zhang1, Honglak Lee1,2 1University.

The General Linear Model (GLM)

Digital Image Processing

Automated Amygdala Surface Modeling Pipeline

The General Linear Model

Detecting Gray Matter Maturation via Tensor-based Surface Morphometry

Satellite data Marco Puts

Lecture 2: Edge detection

Spherical harmonic representation of anatomical boundary

Discrete Surfaces and Manifolds: A Potential tool to Image Processing

The General Linear Model

The General Linear Model (GLM)

Wellcome Centre for Neuroimaging at UCL

The General Linear Model

Keith Worsley, McGill Jonathan Taylor,

Mixture Models with Adaptive Spatial Priors

Discovery of Hidden Structure in High-Dimensional Data

The General Linear Model

Chapter 5: Morse functions and function-induced persistence

Recursive Implementation of Anisotropic Filtering

Building pattern  Complete the following tables and write the rule 

Presentation transcript:

Persistence Diagram: Topological Characterization of Noise in Images Moo K. Chung Department of Biostatistics and Medical Informatics Waisman Laboratory for Brain Imaging and Behavior University of Wisconsin-Madison www.stat.wisc.edu/~mchung Brain Food Meeting November 5, 2008

Kim M. Dalton, Richard J. Davidson Acknowledgments Kim M. Dalton, Richard J. Davidson Waisman Laboratory for Brain Imaging and Behavior University of Wisconsin-Madison Peter Kim University of Guelph CANADA

Standard model on cortical thickness 6mm 0mm Gaussian  GLM

Heat kernel smoothing makes data more Gaussian – central limit theorem QQ-plot 100 iterations Thickness 50 iterations Chung et al., 2005. NeuroImage

Can we do data analysis in a really crazy way? Heat kernel smoothing widely used cortical data smoothing technique cortical curvatures (Luders, 2006; Gaser, 2006) cortical thickness (Luders, 2006; Bernal-Rusiel, 2008) Hippocampus (Shen, 2006; Zhu, 2007) Magnetoencephalography (MEG) (Han, 2007) functional-MRI (Hagler, 2006: Jo, 2007) General linear model (GLM) + random field theory Can we do data analysis in a really crazy way? Why? We may be able to detect some features that can’t be detected using the traditional approach.

Persistence diagram Local max Local min A way to pair local min to local max in a nonlinear fashion.

Persistence diagram Sublevel set Number of connected components Local min: Birth: Local max: Death: Pair the time of death with the time of the closest earlier birth

PD-algorithm for pairing Set of local max Ordered local min For i from n to 1, let be the smallest of two adjacent local max iterate pair delete

Rule for pairing local minimum to local maximum death 2 2 3 3 3 2 1 birth

Persistence diagrams will show signal pattern

Orthonormal basis in [0,1] Produces sine and cosine basis Removes sine basis

 more stable computing High order derivatives are computed analytically without using finite difference  more stable computing Measurement = f + noise

Persistence diagram Red: local max Black: local min

More complicated example black = top red = bottom Statistical analysis?

Cortical thickness Flattening Weighted-SPHARM Chung et al., 2007, IEEE-TMI

Signal difference noise red=autism local min and max computation black=control local min and max computation New inference & classification framework under development

Thank you If you want to analyze your data this way, please talk to me 