This document describes using generative models to analyze brain imaging data and distinguish between disease states. It discusses:
1. Developing neural models of pathophysiological processes and validating them with experimental data.
2. Inverting these models on imaging data from individual subjects to obtain subject-specific representations in a generative score space.
3. Using these representations to train classifiers that can distinguish patient groups, with the goal of inferring pathophysiological mechanisms in patients.
4. An example application where this framework is able to accurately diagnose stroke patients based on speech-related brain regions.
The Origin of Diversity - Thinking with Chaotic WalkTakashi Iba
We will show that diverse complex patterns can emerge even in the universe governed by deterministic laws. See the details of this study on our paper: Iba, T. & Shimonishi, K. (2011), "The Origin of Diversity: Thinking with Chaotic Walk," in Unifying Themes in Complex Systems Volume VIII: Proceedings of the Eighth International Conference on Complex Systems, New England Complex Systems Institute Series on Complexity (Sayama, H., Minai, A. A., Braha, D. and Bar-Yam, Y. eds., NECSI Knowledge Press, 2011), pp.447-461.
Unlike full reading, 'skim-reading' involves the process of looking quickly over information in an attempt to cover more material whilst still being able to retain a superficial view of the underlying content. Within this work, we specifically emulate this natural human activity by providing a dynamic graph-based view of entities automatically extracted from text using superficial text parsing / processing techniques. We provide a preliminary web-based tool (called `SKIMMR') that generates a network of inter-related concepts from a set of documents. In SKIMMR, a user may browse the network to investigate the lexically-driven information space extracted from the documents. When a particular area of that space looks interesting to a user, the tool can then display the documents that are most relevant to the displayed concepts. We present this as a simple, viable methodology for browsing a document collection (such as a collection scientific research articles) in an attempt to limit the information overload of examining that document collection.
Caveon Webinar Series: Considerations for Online Assessment Program Design Caveon Test Security
This month's Caveon Webinar Series session focuses on the Online Education market, but the message shared by two industry veterans will be helpful for all test programs.
In this Webinar, we are joined by special guests Dr. Larry Rudner of GMAC and Dr. Mika Hoffman of Excelsior College. These two esteemed testing veterans will describe basics of good and secure test design and provide considerations for designing an assessment program.
Here's what you'll learn:
- Identifying strategies for developing and improving online testing
- Why good test writing is important to overall learning
- Considerations for implementing low and high stakes online assessments
- Online assessment strategies that are specifically geared for the online education market
The speakers presented real-world examples, with practical considerations for implementing various levels of student assessment. An online assessment checklist will be provided to help you identify priorities for implementing online assessment initiatives.
Featuring presentations by:
Larry Rudner, Ph.D. – is Vice President of Research and Development at the Graduate Management Admission Council (GMAC). He has 30 years of experience is in the areas of test validation, adaptive testing, professional standards, QTI specifications, test security, data forensics, and contract monitoring.
Mika Hoffman, Ph.D. - is the Executive Director of the Center for Educational Measurement for Excelsior College. She has over 20 years of professional experience in test design, quality control, integration of psychometric analyses, assessments development and production processes for higher education and government.
Please contact richelle.gruber@caveon.com if you have any questions or problems viewing.
The Origin of Diversity - Thinking with Chaotic WalkTakashi Iba
We will show that diverse complex patterns can emerge even in the universe governed by deterministic laws. See the details of this study on our paper: Iba, T. & Shimonishi, K. (2011), "The Origin of Diversity: Thinking with Chaotic Walk," in Unifying Themes in Complex Systems Volume VIII: Proceedings of the Eighth International Conference on Complex Systems, New England Complex Systems Institute Series on Complexity (Sayama, H., Minai, A. A., Braha, D. and Bar-Yam, Y. eds., NECSI Knowledge Press, 2011), pp.447-461.
Unlike full reading, 'skim-reading' involves the process of looking quickly over information in an attempt to cover more material whilst still being able to retain a superficial view of the underlying content. Within this work, we specifically emulate this natural human activity by providing a dynamic graph-based view of entities automatically extracted from text using superficial text parsing / processing techniques. We provide a preliminary web-based tool (called `SKIMMR') that generates a network of inter-related concepts from a set of documents. In SKIMMR, a user may browse the network to investigate the lexically-driven information space extracted from the documents. When a particular area of that space looks interesting to a user, the tool can then display the documents that are most relevant to the displayed concepts. We present this as a simple, viable methodology for browsing a document collection (such as a collection scientific research articles) in an attempt to limit the information overload of examining that document collection.
Caveon Webinar Series: Considerations for Online Assessment Program Design Caveon Test Security
This month's Caveon Webinar Series session focuses on the Online Education market, but the message shared by two industry veterans will be helpful for all test programs.
In this Webinar, we are joined by special guests Dr. Larry Rudner of GMAC and Dr. Mika Hoffman of Excelsior College. These two esteemed testing veterans will describe basics of good and secure test design and provide considerations for designing an assessment program.
Here's what you'll learn:
- Identifying strategies for developing and improving online testing
- Why good test writing is important to overall learning
- Considerations for implementing low and high stakes online assessments
- Online assessment strategies that are specifically geared for the online education market
The speakers presented real-world examples, with practical considerations for implementing various levels of student assessment. An online assessment checklist will be provided to help you identify priorities for implementing online assessment initiatives.
Featuring presentations by:
Larry Rudner, Ph.D. – is Vice President of Research and Development at the Graduate Management Admission Council (GMAC). He has 30 years of experience is in the areas of test validation, adaptive testing, professional standards, QTI specifications, test security, data forensics, and contract monitoring.
Mika Hoffman, Ph.D. - is the Executive Director of the Center for Educational Measurement for Excelsior College. She has over 20 years of professional experience in test design, quality control, integration of psychometric analyses, assessments development and production processes for higher education and government.
Please contact richelle.gruber@caveon.com if you have any questions or problems viewing.
TSSA 06 apparato neurologico e disturbi metaboliciEmergency Live
Il corso TSSA (corso nazionale per l’attività di trasporto sanitario e soccorso in ambulanza) è il corso sanitario avanzato della Croce Rossa Italiana che si prefigge di formare il SOCCORRITORE, cioè il Volontario che svolgerà la sua attività sulle ambulanza e perciò il percorso addestrativo è tipicamente sanitario. I corsi sono tenuti da Istruttori di Croce Rossa qualificati con un apposito percorso specifico.
In queste slide presentiamo la dispensa dedicata all'apparato neurologico e ai disturbi metabolici, con alterazioni dello stato di coscienza, con la valutazione della risposta neurologica
Artificial intelligence (AI) is everywhere, promising self-driving cars, medical breakthroughs, and new ways of working. But how do you separate hype from reality? How can your company apply AI to solve real business problems?
Here’s what AI learnings your business should keep in mind for 2017.
Study: The Future of VR, AR and Self-Driving CarsLinkedIn
We asked LinkedIn members worldwide about their levels of interest in the latest wave of technology: whether they’re using wearables, and whether they intend to buy self-driving cars and VR headsets as they become available. We asked them too about their attitudes to technology and to the growing role of Artificial Intelligence (AI) in the devices that they use. The answers were fascinating – and in many cases, surprising.
This SlideShare explores the full results of this study, including detailed market-by-market breakdowns of intention levels for each technology – and how attitudes change with age, location and seniority level. If you’re marketing a tech brand – or planning to use VR and wearables to reach a professional audience – then these are insights you won’t want to miss.
Steerable Filters generated with the Hypercomplex Dual-Tree Wavelet Transform...Jan Wedekind
The use of wavelets in the image processing domain is still in its infancy, and largely associated with image compression. With the advent of the dual-tree hypercomplex wavelet transform (DHWT) and its improved shift invariance and directional selectivity, applications in other areas of image processing are more conceivable. This paper discusses the problems and solutions in developing the DHWT and its inverse. It also offers a practical implementation of the algorithms involved. The aim of this work is to apply the DHWT in machine vision.
Tentative work on a possible new way of feature extraction is presented. The paper shows that 2-D hypercomplex basis wavelets can be used to generate steerable filters which allow rotation as well as translation.
Why we don’t know how many colors there areJan Morovic
There have been many attempts to answer the question of how many distinct colors there are, with widely varying answers. Here we present an analysis of what it would take to arrive at a reliable answer and show how currently available models fail to make predictions under the wide range of conditions that needs to be considered. Gamut volumes are reported for a number of light sources and viewing modes and the conclusion is drawn that the only reliable data we have comes from psychophysical work. The color gamut of the LUTCHI data in CIECAM02 is therefore shown as an alternative to the gamut of all possible colors.
This new release is features-rich, as we added several new functionality: trend analysis (for linear, polynomial, logarithmic, and exponential trends), histograms, spectral analysis (discrete Fourier transform), and more. We also revised the existing correlation function (XCF) to extend support for new methods (e.g. Kendall, Spearman, etc.), and added a statistical test for examining its significance. Finally, NumXL now includes a new unit-root and stationarity test: the Augmented Dickey-Fuller (ADF) test.
http://www.spiderfinancial.com/products/numxl
TSSA 06 apparato neurologico e disturbi metaboliciEmergency Live
Il corso TSSA (corso nazionale per l’attività di trasporto sanitario e soccorso in ambulanza) è il corso sanitario avanzato della Croce Rossa Italiana che si prefigge di formare il SOCCORRITORE, cioè il Volontario che svolgerà la sua attività sulle ambulanza e perciò il percorso addestrativo è tipicamente sanitario. I corsi sono tenuti da Istruttori di Croce Rossa qualificati con un apposito percorso specifico.
In queste slide presentiamo la dispensa dedicata all'apparato neurologico e ai disturbi metabolici, con alterazioni dello stato di coscienza, con la valutazione della risposta neurologica
Artificial intelligence (AI) is everywhere, promising self-driving cars, medical breakthroughs, and new ways of working. But how do you separate hype from reality? How can your company apply AI to solve real business problems?
Here’s what AI learnings your business should keep in mind for 2017.
Study: The Future of VR, AR and Self-Driving CarsLinkedIn
We asked LinkedIn members worldwide about their levels of interest in the latest wave of technology: whether they’re using wearables, and whether they intend to buy self-driving cars and VR headsets as they become available. We asked them too about their attitudes to technology and to the growing role of Artificial Intelligence (AI) in the devices that they use. The answers were fascinating – and in many cases, surprising.
This SlideShare explores the full results of this study, including detailed market-by-market breakdowns of intention levels for each technology – and how attitudes change with age, location and seniority level. If you’re marketing a tech brand – or planning to use VR and wearables to reach a professional audience – then these are insights you won’t want to miss.
Steerable Filters generated with the Hypercomplex Dual-Tree Wavelet Transform...Jan Wedekind
The use of wavelets in the image processing domain is still in its infancy, and largely associated with image compression. With the advent of the dual-tree hypercomplex wavelet transform (DHWT) and its improved shift invariance and directional selectivity, applications in other areas of image processing are more conceivable. This paper discusses the problems and solutions in developing the DHWT and its inverse. It also offers a practical implementation of the algorithms involved. The aim of this work is to apply the DHWT in machine vision.
Tentative work on a possible new way of feature extraction is presented. The paper shows that 2-D hypercomplex basis wavelets can be used to generate steerable filters which allow rotation as well as translation.
Why we don’t know how many colors there areJan Morovic
There have been many attempts to answer the question of how many distinct colors there are, with widely varying answers. Here we present an analysis of what it would take to arrive at a reliable answer and show how currently available models fail to make predictions under the wide range of conditions that needs to be considered. Gamut volumes are reported for a number of light sources and viewing modes and the conclusion is drawn that the only reliable data we have comes from psychophysical work. The color gamut of the LUTCHI data in CIECAM02 is therefore shown as an alternative to the gamut of all possible colors.
This new release is features-rich, as we added several new functionality: trend analysis (for linear, polynomial, logarithmic, and exponential trends), histograms, spectral analysis (discrete Fourier transform), and more. We also revised the existing correlation function (XCF) to extend support for new methods (e.g. Kendall, Spearman, etc.), and added a statistical test for examining its significance. Finally, NumXL now includes a new unit-root and stationarity test: the Augmented Dickey-Fuller (ADF) test.
http://www.spiderfinancial.com/products/numxl
1. Model-based analysis of disease states of the brain
using generative embedding
Kay H. Brodersen1,2
1 Translational Neuromodeling Unit (TNU), Department of Biomedical Engineering, University of Zurich & ETH Zurich
2 Machine Learning Laboratory, Department of Computer Science, ETH Zurich
2. Psychiatric spectrum diseases
Schizophrenia, depression, mania, etc.
genetically based diagnoses impossible
(diverse genetic basis, strong gene-
environment interactions)
even when symptoms are similar, causes
can differ across patients (multiple
pathophysiological mechanisms)
large variability in treatment response
Consequences
need to infer on pathophysiological
mechanisms in individual patients!
2
3. Dissecting diseases into physiologically defined subgroups
voxel-based activity space model-based parameter space
0.4 0.4 -0.15 -0.15
embedding
generative
Voxel (64,-24,4) mm
0.3 0.3 -0.2 -0.2
L.HG → L.HG
0.2 0.2 -0.25 -0.25
0.1 0.1 -0.3 -0.3
type 1
0 0 -0.35 -0.35
type 2
-10 -10 0.5 0.5
-0.1 -0.1 -0.4 -0.4
-0.5 -0.5 0 0 -0.4 -0.4 0 0
0 0 -0.2 -0.2
Voxel (-56,-20,10) mm R.HG → L.HG
0.5 10 0.5 10 0 -0.5 0 -0.5
Voxel (-42,-26,10) mm L.MGB → L.MGB
Brodersen et al. (2011) PLoS Comput Biol
3
4. Classification approaches by data representation
Model-based
analyses
How do patterns of
hidden quantities (e.g.,
connectivity among brain
regions) differ between groups?
Activation-based
Structure-based analyses
analyses
Which functional
Which anatomical differences allow us to
structures allow us to separate groups?
separate patients and
healthy controls?
4
5. From models of pathophysiology to clinical applications
Developing models of (patho)physiological processes u2
• neuronal: synaptic plasticity, neuromodulation u1 x3
• computational: learning, decision making
x1 x2
dx
m n
Validation studies in animals & humans A ui B (i ) x j D ( j ) x Cu
dt i 1 j 1
• can models detect experimentally Voxel-based feature space
induced changes, Generative score space
e.g., specific changes in synaptic plasticity?
0.4 0.4 -0.15 -0.15
embedding
0.3 0.3 -0.2 -0.2
generative
Voxel (64,-24,4) mm
L.HG L.HG
0.2 0.2 -0.25 -0.25
Clinical validation studies & translation
0.1 0.1
patients
-0.3 -0.3
patients
• clinical validation of classifications 0
0 -0.35
controls -0.35
controls
• predicting diagnosis, therapeutic response, outcome
-0.1
-0.5
-0.1
-0.5
-10 -10
-0.4 -0.4
0.5 0.5
0 0 -0.4 -0.4 0 0
0 0 Voxel (-56,-20,10) mm -0.2 -0.2 R.HG L.HG
Voxel (-42,-26,10) mm 0.5 10 0.5 10 0 -0.5 0 -0.5
L.MGB L.MGB
Klaas E. Stephan
5
6. Colleagues & collaborators
Thomas Schofield Justin R Chumbley
University College London University of Zurich
Cheng Soon Ong Jean Daunizeau
National ICT Australia · University of Melbourne ICM Paris · University College London
Kate Lomakina Joachim M Buhmann
University of Zurich · ETH Zurich ETH Zurich
Alexander Leff Klaas Enno Stephan
University College London (UCL) University of Zurich · ETH Zurich · UCL
Christoph Mathys
University of Zurich · ETH Zurich
6
7. Univariate vs. multivariate models
A univariate model considers a A multivariate model considers
single voxel at a time. many voxels at once.
context BOLD signal context BOLD signal
𝑋𝑡 ∈ ℝ 𝑑 𝑌𝑡 ∈ ℝ 𝑋𝑡 ∈ ℝ 𝑑 𝑌𝑡 ∈ ℝ 𝑣 , v ≫ 1
Spatial dependencies between voxels Multivariate models enable
are only introduced afterwards, inferences on distributed responses
through random field theory. without requiring focal activations.
7
8. Prediction vs. inference
The goal of prediction is to find The goal of inference is to decide
a highly accurate encoding or between competing hypotheses.
decoding function.
predicting a cognitive predicting a comparing a model that weighing the
state using a subject-specific links distributed neuronal evidence for
brain-machine diagnostic status activity to a cognitive sparse vs.
interface state with a model that distributed coding
does not
predictive density marginal likelihood (model evidence)
𝑝 𝑋 𝑛𝑒𝑤 𝑌 𝑛𝑒𝑤 , 𝑋, 𝑌 = ∫ 𝑝 𝑋 𝑛𝑒𝑤 𝑌 𝑛𝑒𝑤 , 𝜃 𝑝 𝜃 𝑋, 𝑌 𝑑𝜃 𝑝 𝑋 𝑌 = ∫ 𝑝 𝑋 𝑌, 𝜃 𝑝 𝜃 𝑑𝜃
8
9. Goodness of fit vs. complexity
Goodness of fit is the degree to which a model explains observed data.
Complexity is the flexibility of a model (including, but not limited to, its number of
parameters).
𝑌 1 parameter 4 parameters 9 parameters
truth
data
model 𝑋
underfitting optimal overfitting
We wish to find the model that optimally trades off goodness of fit and complexity.
Bishop (2007) PRML
9
10. Constructing a classifier
A principled way of designing a classifier would be to adopt a probabilistic approach:
𝑌𝑡 𝑓 that 𝑘 which maximizes 𝑝 𝑋 𝑡 = 𝑘 𝑌𝑡 , 𝑋, 𝑌
In practice, classifiers differ in terms of how strictly they implement this principle.
Generative classifiers Discriminative classifiers Discriminant classifiers
use Bayes’ rule to estimate estimate 𝑝 𝑋 𝑡 𝑌𝑡 directly estimate 𝑓 𝑌𝑡 directly
𝑝 𝑋 𝑡 𝑌𝑡 ∝ 𝑝 𝑌𝑡 𝑋 𝑡 𝑝 𝑋 𝑡 without Bayes’ theorem
• Gaussian Naïve Bayes • Logistic regression • Fisher’s Linear
• Linear Discriminant • Relevance Vector Discriminant
Analysis Machine • Support Vector Machine
10
11. Support vector machine (SVM)
Linear SVM Nonlinear SVM
v2
v1
Vapnik (1999) Springer; Schölkopf et al. (2002) MIT Press
11
12. Model-based analysis by generative embedding
step 1 — A step 2 —
A→B
model inversion kernel construction
A→C
B→B
B
C B→C
measurements from subject-specific subject representation in the
an individual subject inverted generative model generative score space
5 0.6
0.5
4
0.4
3
A
(14) R.HG -> L.HG
step 4 — 0.3
step 3 —
Voxel 2
2
interpretation 0.2
analysis
1
0.1
B
C 0
0
-1 -0.1
-2 0 2 4 6 8 -0.4 -0.35 -0.3 -0.25 -0.2 -0.15
Voxel 1 (1) L.MGB -> L.MGB
jointly discriminative separating hyperplane to
connection strengths discriminate between groups
Brodersen et al. (2011) NeuroImage; Brodersen et al. (2011) PLoS Comput Biol
12
13. Choosing a generative model: DCM for fMRI
BOLD signal haemodynamic forward model
signal 𝑥 = 𝑔(𝑧, 𝜃ℎ )
𝑥2 (𝑡)
signal signal
𝑥1 (𝑡) 𝑥3 (𝑡)
neuronal states neural state equation
activity
𝑧2 (𝑡)
𝑧 = 𝐴 + ∑𝑢 𝑗 𝐵 𝑗 𝑧 + 𝐶𝑢
activity activity
𝑧1 (𝑡) 𝑧3 (𝑡)
intrinsic
connectivity direct inputs
modulation of
driving input 𝑢1(𝑡) modulatory input 𝑢2(𝑡) connectivity
t Friston, Harrison & Penny (2003) NeuroImage
t Stephan & Friston (2007) Handbook of Brain Connectivity
13
14. Summary of the analysis
1 2 3
estimation of unsupservised training the
group contrasts DCM inversion SVM
based on for each subject on all subjects
all subjects except subject j
except subject j
pre- testing the SVM performance
processing selection of on subject j evaluation
voxels for
regions of
interest
A
B
C
repeat for each subject
14
16. Example: diagnosing stroke patients
To illustrate our approach, we aimed to distinguish between stroke patients and
healthy controls, based on non-lesioned regions involved in speech processing.
16
22. Classification performance
100
100% * Activation-based analyses
a anatomical feature selection
90
90% c mass-univariate contrast feature selection
balanced accuracy
s locally univariate searchlight feature selection
balanced accuracy
p PCA-based dimensionality reduction
80%
80
Correlation-based analyses
m correlations of regional means
70%
70 e correlations of regional eigenvariates
z Fisher-transformed eigenvariates correlations
60%
60 Model-based analyses
o gen.embed., original full model
n.s. n.s.
50% f gen.embed., less plausible feedforward model
50
162 8977p2m332 07o24389 60
a 1c 1 s 34791 e 3 z 81 f 3 l 3 r l gen.embed., left hemisphere only
r gen.embed., right hemisphere only
activation- correlation- model-
based based based
22
23. Biologically less plausible models perform poorly
L.PT R.PT L.PT R.PT
L.HG R.HG L.HG R.HG
(A1) (A1) (A1) (A1)
L.MGB R.MGB L.MGB R.MGB
auditory stimuli auditory stimuli auditory stimuli
feedforward connections only left hemisphere only right hemisphere only
accuracy: 77% accuracy: 81% accuracy: 59%
23
24. The generative projection
Voxel-based contrast space Model-based parameter space
0.4 0.4 -0.15 -0.15
embedding
generative
Voxel (64,-24,4) mm
0.3 0.3 -0.2 -0.2
L.HG → L.HG
0.2 0.2 -0.25 -0.25
0.1 0.1 -0.3 -0.3
patients
0 0 -0.35 -0.35
controls
-10 -10 0.5 0.5
-0.1 -0.1 -0.4 -0.4
-0.5 -0.5 0 0 -0.4 -0.4 0 0
0 0 -0.2 -0.2
Voxel (-56,-20,10) mm R.HG → L.HG
Voxel (-42,-26,10) mm 0.5 10 0.5 10 0 -0.5 0 -0.5
L.MGB → L.MGB
classification accuracy classification accuracy
(using all voxels in the regions of interest) (using all 23 model parameters)
75% 98%
24
26. Discriminative features in model space
PT PT
HG HG
(A1) (A1)
L R
MGB MGB
stimulus input highly discriminative
somewhat discriminative
not discriminative
26
27. Generative embedding and DCM
Question 1 – What do the data tell us about hidden processes in the brain?
compute the posterior ?
𝑝 𝑦 𝜃,𝑚 𝑝 𝜃 𝑚
𝑝 𝜃 𝑦, 𝑚 =
𝑝 𝑦 𝑚
Question 2 – Which model is best w.r.t. the observed fMRI data?
compute the model evidence
𝑝 𝑚 𝑦 ∝ 𝑝 𝑦 𝑚 𝑝(𝑚)
= ∫ 𝑝 𝑦 𝜃, 𝑚 𝑝 𝜃 𝑚 𝑑𝜃
?
Question 3 – Which model is best w.r.t. an external criterion?
compute the classification accuracy
{ patient,
𝑝 ℎ 𝑦 = 𝑥 𝑦 control }
= 𝑝 ℎ 𝑦 = 𝑥 𝑦, 𝑦train , 𝑥train 𝑝 𝑦 𝑝 𝑦train 𝑝 𝑥train 𝑑𝑦 𝑑𝑦train 𝑑𝑥train
27
28. Model-based classification using DCM
model-based
classification { group 1,
group 2 }
activation-based model selection
classification
vs.
structure-based inference on ?
classification model
parameters
28
29. Model-based inference on individual pathophysiology
model of neuronal (patho)physiology
application to brain activity data diagnostic classification
from individual patients
type 1 treatment X
spectrum model-based
type 2 treatment Y
disease diagnostic tests
type 3 treatment Z
29