JIVE Integration of HCP Data Qunqun Yu Dr. Steve Marron, Dr. Kai Zhang & Dr. Ben Risk University of North Carolina at Chapel Hill.

Slides:



Advertisements
Similar presentations
Plan for today An example with 3 variables Face ratings 1: age, gender, and attractiveness – Histograms and scatter plots – Using symbols and colors to.
Advertisements

Article review by Alexander Backus Distributed representations meeting article review.
Compensation for Measurement Errors Due to Mechanical Misalignments in PCB Testing Anura P. Jayasumana, Yashwant K. Malaiya, Xin He, Colorado State University.
INTRODUCTION Assessing the size of objects rapidly and accurately clearly has survival value. Thus, a central multi-sensory module for magnitude assessment.
Data preprocessing before classification In Kennedy et al.: “Solving data mining problems”
Structural Human Action Recognition from Still Images Moin Nabi Computer Vision Lab. ©IPM - Oct
Probabilistic Clustering-Projection Model for Discrete Data
Modeling 3D Deformable and Articulated Shapes Yu Chen, Tae-Kyun Kim, Roberto Cipolla Department of Engineering University of Cambridge.
Automatic Identification of ROIs (Regions of interest) in fMRI data.
Model: Parts and Structure. History of Idea Fischler & Elschlager 1973 Yuille ‘91 Brunelli & Poggio ‘93 Lades, v.d. Malsburg et al. ‘93 Cootes, Lanitis,
Introduction to Data-driven Animation Jinxiang Chai Computer Science and Engineering Texas A&M University.
I. Face Perception II. Visual Imagery. Is Face Recognition Special? Arguments have been made for both functional and neuroanatomical specialization for.
Face Recognition Jeremy Wyatt.
Visual Imagery One of the greatest problems confronting psychology is the nature of mental representation. Part of this debate is the nature of representations.
Face Collections : Rendering and Image Processing Alexei Efros.
Chapter 5. Operations on Multiple R. V.'s 1 Chapter 5. Operations on Multiple Random Variables 0. Introduction 1. Expected Value of a Function of Random.
Statistical Shape Models Eigenpatches model regions –Assume shape is fixed –What if it isn’t? Faces with expression changes, organs in medical images etc.
Oral Defense by Sunny Tang 15 Aug 2003
Magnetic Resonance Imaging (MRI) By Isabelle! and sofia and ronaldo.
1 Objective Investigate the feasibility and added value of data mining to Analog Semiconductor Components division of ADI Use data mining to find unique.
Playing Piano in the Mind – An fMRI study on music imagery and performance in pianists I.G. Meister, T. Krings, H. Foltys, B. Boroojerdi, M. Muller, R.
Data Mining Techniques
1 Signals & Systems Spring 2009 Week 3 Instructor: Mariam Shafqat UET Taxila.
Cao et al. ICML 2010 Presented by Danushka Bollegala.
Chapter 3 Data Exploration and Dimension Reduction 1.
Author: Sotetsu Koyamada, Yumi Shikauchi, et al. (Kyoto University)
Neural mechanisms of Spatial Learning. Spatial Learning Materials covered in previous lectures Historical development –Tolman and cognitive maps the classic.
Working memory research Group member : 唐牧辰 武天翊 侯晓林 赵诣 赵阳.
2 2  Background  Vision in Human Brain  Efficient Coding Theory  Motivation  Natural Pictures  Methodology  Statistical Characteristics  Models.
IEEE TRANSSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
The Influence of Feature Type, Feature Structure and Psycholinguistic Parameters on the Naming Performance of Semantic Dementia and Alzheimer’s Patients.
So you want to run an MVPA experiment… Lindsay Morgan April 9, 2012.
Data Preprocessing Dr. Bernard Chen Ph.D. University of Central Arkansas Fall 2010.
Modeling and Analysis of Printer Data Paths using Synchronous Data Flow Graphs in Octopus Ashwini Moily Under the supervision of Dr. Lou Somers, Prof.
Thinking part I Mental Representations and Visual Imagery Mind Reading
© Tan,Steinbach, Kumar Introduction to Data Mining 8/05/ Data Mining: Exploring Data Lecture Notes for Chapter 3 Introduction to Data Mining by Tan,
Principal Component Analysis (PCA)
Statistics – O. R. 893 Object Oriented Data Analysis Steve Marron Dept. of Statistics and Operations Research University of North Carolina.
ABSTRACT This presentation discusses brain plasticity in Schizophrenia. People with Schizophrenia experience disruptions in activating and inhibiting systems.
SGPP: Spatial Gaussian Predictive Process Models for Neuroimaging Data Yimei Li Department of Biostatistics St. Jude Children’s Research Hospital Joint.
Modeling Situated Language Learning in Early Childhood via Hypernetworks Zhang, Byoung-Tak 1,2, Lee, Eun Seok 2, Heo, Min-Oh 1, and Kang, Myounggu 1 1.
Object Orie’d Data Analysis, Last Time PCA Redistribution of Energy - ANOVA PCA Data Representation PCA Simulation Alternate PCA Computation Primal – Dual.
FMRI in Detection of Deception. What is functional Magnetic Resonance Imaging? A magnetic field is passed through the organ of interest, the brain, during.
GWAS Data Analysis. L1 PCA Challenge: L1 Projections Hard to Interpret (i.e. Little Data Insight) Solution: 1)Compute PC Directions Using L1 2)Compute.
Thinking part I Visual Imagery Mind Reading. Solving problems through imagery What shape are mickey mouse’s ears? How many windows are there in your apartment?
Thinking part I Mental Representations and Visual Imagery Mind Reading.
Automatic Data Transformation Qing Feng Joint work with Dr. Jan Hannig, Dr. J. S. Marron Mar. 22th, 2016.
       January 3 rd, 2005 The signaling properties of the individual neuron. How we move from understanding individual nerve cells.
Non-iterative JIVE for Data Integration Qing Feng Joint Work with Jan Hannig, J.S. Marron Mar. 24 th,
Do Expression and Identity Need Separate Representations?
Visual homing using PCA-SIFT
Representational Similarity Analysis
Database management system Data analytics system:
Representational Similarity Analysis
fMRI and neural encoding models: Voxel receptive fields (continued)
Inverse Transformation Scale Experimental Power Graphing
Quality Control at a Local Brewery
How to Characterize the Function of a Brain Region
A principled way to principal components analysis
Multiple Change Point Detection for Symmetric Positive Definite Matrices Dehan Kong University of Toronto JSM 2018 July 30, 2018.
Historical Vegetation Analysis
Signal, Noise, and Variation in Neural and Sensory-Motor Latency
Presented by Kojo Essuman Ackah Spring 2018 STA 6557 Project
A–D, Whole-brain MD (A) and FA (B) histograms in a patient with low (n = 2) visual score of LA (continuous line), as shown by corresponding FLAIR images.
CS723 - Probability and Stochastic Processes
Displaying data Seminar 2.
Effects of the dietary intervention on urine metabolome.
Diffusion Tensor MRI of White Matter of Healthy Full-term Newborns: Relationship to Neurodevelopmental Outcomes Higher white matter integrity (as reflected.
Data exploration and visualization
Participant Presentations
Presentation transcript:

JIVE Integration of HCP Data Qunqun Yu Dr. Steve Marron, Dr. Kai Zhang & Dr. Ben Risk University of North Carolina at Chapel Hill

Human Connectome Project (HCP)HCP HCP Goals:  structural and functional connections in the human brain  relationship of brain connectivity with behavior Our goal: Different parts of brain work together  behavior

Human Connectome Project Task functional magnetic resonance imaging (tfMRI) Brain image Task related measurements Image source:

Human Connectome Project Task related measurements ✔ Brain Image lots of confounding effects Behavior + Image  common driver  the responsible regions Joint and Individual Variation Explained (JIVE)

1 st generation: Eric F. Lock, Katherine A. Hoadley, J. S. Marron and Andrew B. Nobel. 2 nd generation: Qing Feng, Jan Hannig and J. S. Marron.

JIVE Methodology (Qing Feng) Analyze pairwise data types Figure: Toy example heat-map Matrices containing joint variation -Model common latent variation Example: X = Image Y = Behavior

JIVE Methodology Analyze pairwise data types Figure: Toy example heat-map Matrices containing individual variation -Model unique latent variation to each data type

JIVE Methodology (Qing Feng) Analyze pairwise data types Figure: Toy example heat-map

JIVE Methodology Analyze pairwise data types JIVE obtain approximations of joint and individual matrices for each data Figure: JIVE approximation

Roadmap Data introduction Data preprocessing JIVE analysis

Roadmap Data introduction Data preprocessing JIVE analysis

Data Image data (tfMRI): - Working memory/category specific representation task - Motor taskMotor task Behavioral data

Working memory/category specific representation task 2 working memory task types: 0 – back & 2 – back 4 category task types: body parts, faces, places and tools  8 task blocks: 0 bk body, 0 bk face, 0 bk place, 0 bk tool, 2 bk body, 2 bk face, 2 bk place, 2 bk tool2 bk face Use “working memory task” in short Barch et al. (2013) Task-fMRI paper

Image data format Total: locations in the brain Glasser et al. (2013) Preprocessing pipelines

Image data Remove the common activations

Behavioral data NIH Toolbox measures - cognition, emotion, motor, sensory Other measures - visual processing, personality, emotion, psychiatric, substance abuse, life function, physical function, other Working memory task related measures (e.g. working memory accuracy and reaction time) We use 139 measurements.

Roadmap Data introduction Data preprocessing JIVE analysis

Data preprocessing – missing data

Data preprocessing – Visualization Behavior variables: marginal distributions Sort variables on sd. Summary plot with equal spacing.

Data preprocessing – Visualization Behavior variables: marginal distributions Dashed lines correspond to 1-d distributions.

Data preprocessing – Visualization Behavior variables: marginal distributions 1. Different Scales

Data preprocessing – Visualization Behavior variables: marginal distributions sort on skewness 2. Strong skewness diff scale + strong skew  Shifted log and standardize

Data preprocessing – Visualization Behavior variables: marginal distributions after transformation Much less skewed. Scale similar.

Data preprocessing – Visualization Image variables: marginal distributions sort on skewness. Roughly Gaussian same scale  No Transformation

Roadmap Data introduction Data preprocessing JIVE analysis

JIVE to HCP data  Case 1: Behavioral data + wm 2 bk vs 0 bk activity score image  Case 2: Behavioral data + wm 2 bk tool activity score image  Case 3: Behavioral data + motor right hand image

How to visualize JIVE results? Separate Joint Individual PCA PCA PCA Figure: Toy example heat-map Example: X = Image Y = Behavior