SlideShare a Scribd company logo
1 of 58
Download to read offline
DW-MRI, Tractography,
and Connectivity: what
Machine Learning can do?


     Ting-Shuo Yo




   Max Planck Institute
   for Human Cognitive and Brain Sciences
   Leipzig, Germany


       Max Planck Institute for Human Cognitive and Brain Sciences
Where the story begins
●   Diffusion Weighted MRI (DWI) is a newly
    developed MR scanning protocol, which can
    detect the movement/displacement of water
    molecules in tissues.
●   So far, the techniques used in DWI analysis are
    mostly deterministic and mechanical. The
    stochastic approaches (ML related) can bring
    new insights to this field.


                                                                                  2

                               Max Planck Institute for Human Cognitive and Brain Sciences
Outline
●   MPG/MPIs
●   A brief introduction of DWI
●   What DWI can do
●   A comparison of different tractography algorithms
●   What ML can do in DWI




                                                                                     3

                                  Max Planck Institute for Human Cognitive and Brain Sciences
Outline
●   MPG/MPIs
        –   Max Planck Society
        –   Objective and Organization
        –   MPI - CBS
●   A brief introduction of DWI
●   What DWI can do
●   A comparison of different tractography algorithms
●   What ML can do in DWI
                                                                                     4

                                  Max Planck Institute for Human Cognitive and Brain Sciences
The Max Planck Society
●   The Max Planck Society for the
    Advancement of Science is an independent,
    non-profit research organization.
●   In particular, the Max Planck Society takes up
    new and innovative and interdisciplinary
    research areas that German universities are
    not in a position to accommodate or deal with
    adequately.


                                                     5
The Max Planck Institutes
●   The research institutes
    of the Max Planck
    Society perform basic
    research in the interest
    of the general public in
    the natural sciences,
    life sciences, social
    sciences, and the
    humanities.
●   Currently there are 81
    MPIs.

                                     6
7

Max Planck Institute for Human Cognitive and Brain Sciences
The MPI for CBS




                  8
Outline
●   MPG/MPIs
●   An Introduction of DWI tractography
       –   Local modelling
       –   Fibre tracking
●   What DWI can do
●   A comparison of different tractography algorithms
●   What ML can do in DWI

                                                                                  9

                               Max Planck Institute for Human Cognitive and Brain Sciences
Diffusion Weighted MRI
●   MRI can detect the
    movement of water
    molecules.
●   The movement is
    constrained by the
    neural fibers.




                                                                           10

                         Max Planck Institute for Human Cognitive and Brain Sciences
Diffusion Weighted MRI
●   By posing a gradient magnetic field, the
    displacement in the corresponding direction
    can be measured.




                                                                                11

                              Max Planck Institute for Human Cognitive and Brain Sciences
Tractography          (1)




       ●   Local modelling:
       ➢   Reconstruct the fibre
           orientation within each voxel




                                                              12

            Max Planck Institute for Human Cognitive and Brain Sciences
Tractography              (2)




●   Diffusion propagator
    –   Diffusion Tensor (DT)
    –   Multiple compartment models
    –   Persistent Angular Structure (PAS)

●   Fibre Orientation Distribution Function
    –   Spherical Deconvolution



                                                                                     13

                                   Max Planck Institute for Human Cognitive and Brain Sciences
Tractography             (3)




●   Fiber tracking:
➢   Reconstruct fibre tracts by
    integrating the reconstructed
    local information




                                                                                      14

                                    Max Planck Institute for Human Cognitive and Brain Sciences
Tractography          (4)




●   Streamline approach
    –   Deterministic
    –   Probabilistic

●   Optimization for a larger region
    –   Spin tracking
    –   Gibbs tracking



                                                                                  15

                                Max Planck Institute for Human Cognitive and Brain Sciences
Tractography          (5)




●   Deterministic tracking
    –   At each step, only
        consider the most likely
        direction
         ●   Curvature threshold
         ●   Step size
         ●   Interpolation
         ●   ......




                                                                                     16

                                   Max Planck Institute for Human Cognitive and Brain Sciences
Tractography               (6)




●   Probabilistic tracking
    –   Perform deterministic tracking for multiple times
    –   Allow uncertainty at each step




                                                                                       17

                                     Max Planck Institute for Human Cognitive and Brain Sciences
Tractography              (7)




●   Probabilistic tracking and tractogram
    –   Probability of connection




                                                                                      18

                                    Max Planck Institute for Human Cognitive and Brain Sciences
Tractography           (8)




●   Optimization for a larger region
    –   Spin tracking
    –   Gibbs tracking




                                                    From Kreher et al. 2008
                                                                                  19

                                Max Planck Institute for Human Cognitive and Brain Sciences
Outline
●   MPG/MPIs
●   A brief introduction of DWI
●   What DWI can do
        –   To reveal anatomical structure in white matter
        –   To construct the general brain network
        –   In vivo
●   A comparison of different tractography algorithms
●   What ML can do in DWI
                                                                                       20

                                     Max Planck Institute for Human Cognitive and Brain Sciences
White matter structure from DWI
●   Product of tractography




                                                                                21

                              Max Planck Institute for Human Cognitive and Brain Sciences
Brain Network from DWI
●   Hagmann 2008




                                                                       22

                     Max Planck Institute for Human Cognitive and Brain Sciences
What DWI can do
●   fMRI shows "where" is working.
       –   The "nodes" in a graph/network
●   DWI shows the structure of the fiber bundles.
       –   The “edges" in a graph/network
       –   With further analysis, can also show "strength of
            edges".
●   The brain network:
       –   The amount of nodes: 10^2
       –   The amount of edges: 10^3
                                                                                      23

                                    Max Planck Institute for Human Cognitive and Brain Sciences
Outline
●   MPG/MPIs
●   A brief introduction of DWI
●   What DWI can do
●   A comparison of different tractography
    algorithms
        –   Selected algorithms
        –   Procedure
        –   Results
●   What ML can do in DWI
                                                                                    24

                                  Max Planck Institute for Human Cognitive and Brain Sciences
Selected Algorithms




                                                              25

            Max Planck Institute for Human Cognitive and Brain Sciences
Procedure




                                                         26

       Max Planck Institute for Human Cognitive and Brain Sciences
Results   (1)




                                                        27

      Max Planck Institute for Human Cognitive and Brain Sciences
Results   (2)




                                                        28

      Max Planck Institute for Human Cognitive and Brain Sciences
Results   (3)




                                                        29

      Max Planck Institute for Human Cognitive and Brain Sciences
Results   (4)




                                                        30

      Max Planck Institute for Human Cognitive and Brain Sciences
Results   (5)




                                                        31

      Max Planck Institute for Human Cognitive and Brain Sciences
Results   (6)




                                                        32

      Max Planck Institute for Human Cognitive and Brain Sciences
Results   (7)




                                                        33

      Max Planck Institute for Human Cognitive and Brain Sciences
Results   (8)




                                                        34

      Max Planck Institute for Human Cognitive and Brain Sciences
Quick Summary
●   More connections
     –   Local models which allow multiple fibres
     –   Probabilistic tracking
●   Consistent patterns across methods
     –   Strong connections within a lobe
     –   Strong connections to corpus callosum
     –   Weak trans-callosum connections


                                                                                    35

                                  Max Planck Institute for Human Cognitive and Brain Sciences
Results   (9)




                                                        36

      Max Planck Institute for Human Cognitive and Brain Sciences
Outline
●   MPG/MPIs
●   A brief introduction of DWI
●   What DWI can do
●   A comparison of different tractography algorithms
●   What ML can do in DWI
        –   Local model reconstruction
        –   Fiber tracking
        –   Further application
                                                                                      37

                                    Max Planck Institute for Human Cognitive and Brain Sciences
ML in DWI

●   Local modeling: deconvolution approach
       –   Assume the signals are convolution of neural
            fibers and noises.
       –   Need to “learn" the deconvolution kernel from
            data defined as "one single fiber".
       –   So far only GLM (2nd order polynomial) is used.
       –   More sophisticated kernel methods can be used.



                                                                                      38

                                    Max Planck Institute for Human Cognitive and Brain Sciences
ML in DWI
●   Fiber tracking
        –   Speed up the optimization process.
        –   Different fiber reconstruction method.


●   Probabilistic modeling of fiber tracts




                                                                                       39

                                     Max Planck Institute for Human Cognitive and Brain Sciences
MICCAI'09 Fiber Cup
●   6 datasets:
    –   3 of resolution 3x3x3mm (image size: 64x64x3) and
        3 b-values (650, 1500 and 2000)
    –   3 of resolution 6x6x6mm (image size: 64x64x1) and
        3 b-values (650, 1500, 2650)
●   Participants have to return one single fiber per
    spatial position selected.



                                                                                    40

                                  Max Planck Institute for Human Cognitive and Brain Sciences
MICCAI'09 Fiber Cup




                                                              41

            Max Planck Institute for Human Cognitive and Brain Sciences
A Very Brief Review of Tractography
●   Local modeling
●   Fiber tracking




                                                                       42

                     Max Planck Institute for Human Cognitive and Brain Sciences
Why are we doing this?
●   Streamline-based tractography:
    –   Each simulation (a fiber) is a possible trajectory in
        the given vector field.
         ●   What is the probability of one given fiber?
         ●   How to select the most representative fibers?




                                                                                            43

                                          Max Planck Institute for Human Cognitive and Brain Sciences
Probability of a Fiber Tract                                   (1)



●   Fiber tract, t = { x1, x2, ...., xl }
●   P(t) = P( x1, x2, ...., xl )




                                                                                        44

                                      Max Planck Institute for Human Cognitive and Brain Sciences
Probability of a Fiber Tract                                                (2)



●   Conditional Probability and Joint Probability
     –   P(A|B) = P(A,B) / P(B)
     –   P(A,B) = P(A|B) P(B)

●   P(t) = P( x1, x2, ...., xl )
         = P(xl| x1, ...., xl-1) P(x1, ...., xl-1)
         = P(xl| x1, ...., xl-1) P(xl-1|x1, ...., xl-2) P(x1, ...., xl-2)
         = P(xl| x1, ...., xl-1) P(xl-1|x1, ...., xl-2) ......P(x2|x1) P(x1)


                                                                                                       45

                                                     Max Planck Institute for Human Cognitive and Brain Sciences
Probability of a Fiber Tract                                              (3)



●
    Assumption: fiber tracking is a 1st order Markov
    process
    –   P(xi| x1, ...., xi-1) = P(xl|xi-1)
    –   P(t) = P( x1, x2, ...., xl )
             = P(xl| x1, ...., xl-1) P(xl-1|x1, ...., xl-2) ......P(x2|x1) P(x1)
             = P(xl|xl-1) P(xl-1|xl-2) ......P(x2|x1) P(x1)
                          l−1
             =   P  x 1 ∏ P  x i1∣x i 
                          i=1



                                                                                                     46

                                                   Max Planck Institute for Human Cognitive and Brain Sciences
Probability of a Fiber Tract                                          (4)



●   How do we define P(xi+1|xi) and P(xi) ?
    –   C: connection probability map
    –   P(xi) ~ C(xi)
    –   P(xi+1|xi) ~ C(xi+1|xi) ~ C(xi+1,xi)


                        l−1
    P t=P  x1  ∏ P  x i1∣x i 
                        i=1




                                                                                                 47

                                               Max Planck Institute for Human Cognitive and Brain Sciences
Finite State Automata                         (1)



●   Each step of fiber tracking can lead to next
    middle point or the terminal point.




                                                                                  48

                                Max Planck Institute for Human Cognitive and Brain Sciences
Finite State Automata                     (2)




          t={x 1 , ... , x l }
                                   l−1
          P t=P0  x l  ∏ 1−P 0  x i 
                                   i=1



                                                                   49

                 Max Planck Institute for Human Cognitive and Brain Sciences
Finite State Automata                                 (3)



●   How to define P0?
    –   # of fibers in the neighboring voxels, NB(x)
    –   (1-P0(xi)) ~ C(NB(xi))
                                                    P 0  x=1−C  x k

    –   C(NB(xi))~ C(xi)                                   K = 20, 10, 5

                     l−1
     P t=P0  x l  ∏ 1−P 0  x i 
                     i=1

             l −1
    P t≃∏ 1−1−C  xi k
             i=1
                                                                                            50

                                          Max Planck Institute for Human Cognitive and Brain Sciences
Finite State Automata                                    (4)



●   Likelihood and Log-likelihood
                       l−1
       P t=P0  x l  ∏ 1−P 0  x i 
                       i=1

              l −1
       P t≃∏ 1−1−C  xi       k

              i=1


              l−1                           l−1
       L t≃∑ ln 1−1−C  x i k ≃∑ −1−C  xi k
              i=1                           i=1

                                  Approximation with 1st order Taylor's expansion

                                                                                              51

                                            Max Planck Institute for Human Cognitive and Brain Sciences
Entropy of a Fiber Tract                                  (1)



●   Entropy
                       l
              H t =∑ C  x i ⋅lnC  x i 
                      i=1

●   Can be seen as the log-likelihood of
               l                                l

              ∑ C  xi ⋅lnC  xi =ln ∏ C  x i              C xi 
                                                                            
              i=1                             i =1




                                                                                         52

                                       Max Planck Institute for Human Cognitive and Brain Sciences
Fiber Cup Results              (2)



Max. Entropy       Max. Likelihood




                                                                        53

                      Max Planck Institute for Human Cognitive and Brain Sciences
ML in DWI
●   Connectivity based clustering
       –   Brain parcellation
       –   Brain tissue is mostly
            continuous without clear
            segmentation, how to
            define regions on it?
       –   Perform clustering based
            on the connectivity
            matrices.



                                                                                        54

                                      Max Planck Institute for Human Cognitive and Brain Sciences
Leipzig, Germany   Saclay, Gif-sur-Yvette, France

A. Anwander        M. Descoteaux
T.R. Knösche       P. Fillard
T. Yo              C. Poupon


                                                                          55

                        Max Planck Institute for Human Cognitive and Brain Sciences
Questions




                                                         56

       Max Planck Institute for Human Cognitive and Brain Sciences
Doing what the brain does - how
   computers learn to listen




                                                                    57

                  Max Planck Institute for Human Cognitive and Brain Sciences
Thank You




                                                  58

Max Planck Institute for Human Cognitive and Brain Sciences

More Related Content

What's hot

Diffusion tensor imaging in Neurology
Diffusion tensor imaging in NeurologyDiffusion tensor imaging in Neurology
Diffusion tensor imaging in NeurologyOsama Ragab
 
Functional magnetic resonance imaging-fMRI
Functional magnetic resonance imaging-fMRIFunctional magnetic resonance imaging-fMRI
Functional magnetic resonance imaging-fMRIREMIX MAHARJAN
 
Magnetic resonance imaging (mri) asit meher ppt
Magnetic resonance imaging (mri) asit meher pptMagnetic resonance imaging (mri) asit meher ppt
Magnetic resonance imaging (mri) asit meher pptAsit Meher
 
Basics of mri physics Dr. Muhammad Bin Zulfiqar
Basics of mri physics Dr. Muhammad Bin ZulfiqarBasics of mri physics Dr. Muhammad Bin Zulfiqar
Basics of mri physics Dr. Muhammad Bin ZulfiqarDr. Muhammad Bin Zulfiqar
 
Magnetic Resonance Diffusion
Magnetic Resonance DiffusionMagnetic Resonance Diffusion
Magnetic Resonance DiffusionRahman Ud Din
 
K Space in MRI
K Space in MRIK Space in MRI
K Space in MRIKajal Jha
 
CT image acquisition
CT image acquisitionCT image acquisition
CT image acquisitiondypradio
 
Mri presentation main
Mri presentation mainMri presentation main
Mri presentation mainKarim Yousry
 
Magnetic Resonance Imaging
Magnetic Resonance ImagingMagnetic Resonance Imaging
Magnetic Resonance Imagingguest2d52f2
 
fMRI in machine learning
fMRI in machine learningfMRI in machine learning
fMRI in machine learningUjjawal
 
Scanning systems, CT Scan
Scanning systems, CT Scan Scanning systems, CT Scan
Scanning systems, CT Scan Izzad Samir
 
Computed tomogrphy(c
Computed tomogrphy(cComputed tomogrphy(c
Computed tomogrphy(cSubhra Behera
 

What's hot (20)

Diffusion tensor imaging in Neurology
Diffusion tensor imaging in NeurologyDiffusion tensor imaging in Neurology
Diffusion tensor imaging in Neurology
 
Functional magnetic resonance imaging-fMRI
Functional magnetic resonance imaging-fMRIFunctional magnetic resonance imaging-fMRI
Functional magnetic resonance imaging-fMRI
 
Introduction to mri
Introduction to mriIntroduction to mri
Introduction to mri
 
Computed tomography
Computed tomographyComputed tomography
Computed tomography
 
Magnetic resonance imaging (mri) asit meher ppt
Magnetic resonance imaging (mri) asit meher pptMagnetic resonance imaging (mri) asit meher ppt
Magnetic resonance imaging (mri) asit meher ppt
 
BASIC MRI SEQUENCES
BASIC MRI SEQUENCESBASIC MRI SEQUENCES
BASIC MRI SEQUENCES
 
Basics of mri physics Dr. Muhammad Bin Zulfiqar
Basics of mri physics Dr. Muhammad Bin ZulfiqarBasics of mri physics Dr. Muhammad Bin Zulfiqar
Basics of mri physics Dr. Muhammad Bin Zulfiqar
 
MRI
MRIMRI
MRI
 
Introduction to fMRI
Introduction to fMRIIntroduction to fMRI
Introduction to fMRI
 
Magnetic Resonance Diffusion
Magnetic Resonance DiffusionMagnetic Resonance Diffusion
Magnetic Resonance Diffusion
 
K Space in MRI
K Space in MRIK Space in MRI
K Space in MRI
 
CT image acquisition
CT image acquisitionCT image acquisition
CT image acquisition
 
Principles of MRI
Principles of MRIPrinciples of MRI
Principles of MRI
 
Mri presentation main
Mri presentation mainMri presentation main
Mri presentation main
 
Mri components
Mri componentsMri components
Mri components
 
Magnetic Resonance Imaging
Magnetic Resonance ImagingMagnetic Resonance Imaging
Magnetic Resonance Imaging
 
fMRI in machine learning
fMRI in machine learningfMRI in machine learning
fMRI in machine learning
 
Scanning systems, CT Scan
Scanning systems, CT Scan Scanning systems, CT Scan
Scanning systems, CT Scan
 
Computed tomogrphy(c
Computed tomogrphy(cComputed tomogrphy(c
Computed tomogrphy(c
 
Mri basics
Mri basicsMri basics
Mri basics
 

Viewers also liked

Presentation1.pptx, diffusion tensor imaging of white matter tract in cerebra...
Presentation1.pptx, diffusion tensor imaging of white matter tract in cerebra...Presentation1.pptx, diffusion tensor imaging of white matter tract in cerebra...
Presentation1.pptx, diffusion tensor imaging of white matter tract in cerebra...Abdellah Nazeer
 
Week 2. Diffusion magnetic resonance imaging, tractography, mapping the brain...
Week 2. Diffusion magnetic resonance imaging, tractography, mapping the brain...Week 2. Diffusion magnetic resonance imaging, tractography, mapping the brain...
Week 2. Diffusion magnetic resonance imaging, tractography, mapping the brain...Dr. Jakab András
 
Perfusión en TC
Perfusión en TCPerfusión en TC
Perfusión en TCGaro TM
 
Diffusion Tensor Imaging Analysis-3749
Diffusion Tensor Imaging Analysis-3749Diffusion Tensor Imaging Analysis-3749
Diffusion Tensor Imaging Analysis-3749Kitware Kitware
 
Week 5. Basics and clinical uses of MR spectroscopy.
Week 5. Basics and clinical uses of MR spectroscopy.Week 5. Basics and clinical uses of MR spectroscopy.
Week 5. Basics and clinical uses of MR spectroscopy.Dr. Jakab András
 
Role of diffusion weighted magnetic resonance imaging in
Role of diffusion weighted magnetic resonance imaging inRole of diffusion weighted magnetic resonance imaging in
Role of diffusion weighted magnetic resonance imaging inshubhamoygantait
 
Diffusion-weighted and Perfusion MR Imaging for Brain Tumor Characterization ...
Diffusion-weighted and Perfusion MR Imaging for Brain Tumor Characterization ...Diffusion-weighted and Perfusion MR Imaging for Brain Tumor Characterization ...
Diffusion-weighted and Perfusion MR Imaging for Brain Tumor Characterization ...Arif S
 
135 contrast enhanced mri of vulnerable plaque
135 contrast enhanced mri of vulnerable plaque135 contrast enhanced mri of vulnerable plaque
135 contrast enhanced mri of vulnerable plaqueSHAPE Society
 
Helpful radiological signs in cxr25 11-91
Helpful radiological signs in cxr25 11-91Helpful radiological signs in cxr25 11-91
Helpful radiological signs in cxr25 11-91aalmasi1970
 
Imaging in pediatric brain tumors
Imaging in pediatric brain tumorsImaging in pediatric brain tumors
Imaging in pediatric brain tumorsDr.Suhas Basavaiah
 
Canale and kelly
Canale and kellyCanale and kelly
Canale and kellyGaro TM
 
Advanced MRI Imaging Combined with Intraoperative MRI for Brain Tumors
Advanced MRI Imaging Combined with Intraoperative MRI for Brain TumorsAdvanced MRI Imaging Combined with Intraoperative MRI for Brain Tumors
Advanced MRI Imaging Combined with Intraoperative MRI for Brain TumorsAllina Health
 
3 lung and thorax
3 lung and thorax3 lung and thorax
3 lung and thoraxnswhems
 
fMRI cerebral y tractografia
fMRI cerebral y tractografiafMRI cerebral y tractografia
fMRI cerebral y tractografianicolasarayar
 
Neuroanatomía. Tractografía.
Neuroanatomía. Tractografía.Neuroanatomía. Tractografía.
Neuroanatomía. Tractografía.Heidy Saenz
 
Neural Networks and Deep Learning for Physicists
Neural Networks and Deep Learning for PhysicistsNeural Networks and Deep Learning for Physicists
Neural Networks and Deep Learning for PhysicistsHéloïse Nonne
 
Anisotropic Diffusion for Medical Image Enhancement
Anisotropic Diffusion for Medical Image EnhancementAnisotropic Diffusion for Medical Image Enhancement
Anisotropic Diffusion for Medical Image EnhancementCSCJournals
 
Brain Networks
Brain NetworksBrain Networks
Brain NetworksJimmy Lu
 

Viewers also liked (20)

Presentation1.pptx, diffusion tensor imaging of white matter tract in cerebra...
Presentation1.pptx, diffusion tensor imaging of white matter tract in cerebra...Presentation1.pptx, diffusion tensor imaging of white matter tract in cerebra...
Presentation1.pptx, diffusion tensor imaging of white matter tract in cerebra...
 
Week 2. Diffusion magnetic resonance imaging, tractography, mapping the brain...
Week 2. Diffusion magnetic resonance imaging, tractography, mapping the brain...Week 2. Diffusion magnetic resonance imaging, tractography, mapping the brain...
Week 2. Diffusion magnetic resonance imaging, tractography, mapping the brain...
 
Perfusión en TC
Perfusión en TCPerfusión en TC
Perfusión en TC
 
Diffusion Tensor Imaging Analysis-3749
Diffusion Tensor Imaging Analysis-3749Diffusion Tensor Imaging Analysis-3749
Diffusion Tensor Imaging Analysis-3749
 
DTI Fiber Tracking
DTI Fiber TrackingDTI Fiber Tracking
DTI Fiber Tracking
 
DTI lecture 100710
DTI lecture 100710DTI lecture 100710
DTI lecture 100710
 
Week 5. Basics and clinical uses of MR spectroscopy.
Week 5. Basics and clinical uses of MR spectroscopy.Week 5. Basics and clinical uses of MR spectroscopy.
Week 5. Basics and clinical uses of MR spectroscopy.
 
Role of diffusion weighted magnetic resonance imaging in
Role of diffusion weighted magnetic resonance imaging inRole of diffusion weighted magnetic resonance imaging in
Role of diffusion weighted magnetic resonance imaging in
 
Diffusion-weighted and Perfusion MR Imaging for Brain Tumor Characterization ...
Diffusion-weighted and Perfusion MR Imaging for Brain Tumor Characterization ...Diffusion-weighted and Perfusion MR Imaging for Brain Tumor Characterization ...
Diffusion-weighted and Perfusion MR Imaging for Brain Tumor Characterization ...
 
135 contrast enhanced mri of vulnerable plaque
135 contrast enhanced mri of vulnerable plaque135 contrast enhanced mri of vulnerable plaque
135 contrast enhanced mri of vulnerable plaque
 
Helpful radiological signs in cxr25 11-91
Helpful radiological signs in cxr25 11-91Helpful radiological signs in cxr25 11-91
Helpful radiological signs in cxr25 11-91
 
Imaging in pediatric brain tumors
Imaging in pediatric brain tumorsImaging in pediatric brain tumors
Imaging in pediatric brain tumors
 
Canale and kelly
Canale and kellyCanale and kelly
Canale and kelly
 
Advanced MRI Imaging Combined with Intraoperative MRI for Brain Tumors
Advanced MRI Imaging Combined with Intraoperative MRI for Brain TumorsAdvanced MRI Imaging Combined with Intraoperative MRI for Brain Tumors
Advanced MRI Imaging Combined with Intraoperative MRI for Brain Tumors
 
3 lung and thorax
3 lung and thorax3 lung and thorax
3 lung and thorax
 
fMRI cerebral y tractografia
fMRI cerebral y tractografiafMRI cerebral y tractografia
fMRI cerebral y tractografia
 
Neuroanatomía. Tractografía.
Neuroanatomía. Tractografía.Neuroanatomía. Tractografía.
Neuroanatomía. Tractografía.
 
Neural Networks and Deep Learning for Physicists
Neural Networks and Deep Learning for PhysicistsNeural Networks and Deep Learning for Physicists
Neural Networks and Deep Learning for Physicists
 
Anisotropic Diffusion for Medical Image Enhancement
Anisotropic Diffusion for Medical Image EnhancementAnisotropic Diffusion for Medical Image Enhancement
Anisotropic Diffusion for Medical Image Enhancement
 
Brain Networks
Brain NetworksBrain Networks
Brain Networks
 

Similar to Diffusion MRI, Tractography,and Connectivity: what machine learning can do?

Brainhack results
Brainhack resultsBrainhack results
Brainhack resultspiloubazin
 
Brainhack results
Brainhack resultsBrainhack results
Brainhack resultspiloubazin
 
CARLsim 3: Concepts, Tools, and Applications
CARLsim 3: Concepts, Tools, and ApplicationsCARLsim 3: Concepts, Tools, and Applications
CARLsim 3: Concepts, Tools, and ApplicationsMichael Beyeler
 
How can we har­ness the Human Brain Project to max­i­mize its future health a...
How can we har­ness the Human Brain Project to max­i­mize its future health a...How can we har­ness the Human Brain Project to max­i­mize its future health a...
How can we har­ness the Human Brain Project to max­i­mize its future health a...SharpBrains
 
The Human Connectome Project multimodal cortical parcellation: new avenues fo...
The Human Connectome Project multimodal cortical parcellation: new avenues fo...The Human Connectome Project multimodal cortical parcellation: new avenues fo...
The Human Connectome Project multimodal cortical parcellation: new avenues fo...Emma Robinson
 
Two Cognitive Architectures for General Intelligence - Cortical Feedback & Ep...
Two Cognitive Architectures for General Intelligence - Cortical Feedback & Ep...Two Cognitive Architectures for General Intelligence - Cortical Feedback & Ep...
Two Cognitive Architectures for General Intelligence - Cortical Feedback & Ep...Project AGI
 
Two Cognitive Architectures for General Intelligence - Cortical Feedback & Ep...
Two Cognitive Architectures for General Intelligence - Cortical Feedback & Ep...Two Cognitive Architectures for General Intelligence - Cortical Feedback & Ep...
Two Cognitive Architectures for General Intelligence - Cortical Feedback & Ep...Project AGI
 
Blue Brain Technology, Artificial Intelligence
Blue Brain Technology, Artificial IntelligenceBlue Brain Technology, Artificial Intelligence
Blue Brain Technology, Artificial Intelligencejjoyjessy31
 
20160203_마인즈랩_딥러닝세미나_02 deep and wide analytics 최대우교수님
20160203_마인즈랩_딥러닝세미나_02 deep and wide analytics 최대우교수님20160203_마인즈랩_딥러닝세미나_02 deep and wide analytics 최대우교수님
20160203_마인즈랩_딥러닝세미나_02 deep and wide analytics 최대우교수님Taejoon Yoo
 
Neural Networks: Self-Organizing Maps (SOM)
Neural Networks:  Self-Organizing Maps (SOM)Neural Networks:  Self-Organizing Maps (SOM)
Neural Networks: Self-Organizing Maps (SOM)Mostafa G. M. Mostafa
 
Slide Presentation
Slide PresentationSlide Presentation
Slide Presentationgur509
 
dkNET Webinar: The Human BioMolecular Atlas Program (HuBMAP) 10/14/2022
dkNET Webinar: The Human BioMolecular Atlas Program (HuBMAP) 10/14/2022dkNET Webinar: The Human BioMolecular Atlas Program (HuBMAP) 10/14/2022
dkNET Webinar: The Human BioMolecular Atlas Program (HuBMAP) 10/14/2022dkNET
 
20190122_cohenadad_sc-mri-workshop
20190122_cohenadad_sc-mri-workshop20190122_cohenadad_sc-mri-workshop
20190122_cohenadad_sc-mri-workshopNeuroPoly
 
Individual Brain Charting: third-release dataset validation
Individual Brain Charting: third-release dataset validationIndividual Brain Charting: third-release dataset validation
Individual Brain Charting: third-release dataset validationAna Luísa Pinho
 
Seminar blue brain
Seminar blue brainSeminar blue brain
Seminar blue brainSruthy K S
 

Similar to Diffusion MRI, Tractography,and Connectivity: what machine learning can do? (20)

Brainhack results
Brainhack resultsBrainhack results
Brainhack results
 
Brainhack results
Brainhack resultsBrainhack results
Brainhack results
 
Year 1 Achievements
Year 1 AchievementsYear 1 Achievements
Year 1 Achievements
 
CARLsim 3: Concepts, Tools, and Applications
CARLsim 3: Concepts, Tools, and ApplicationsCARLsim 3: Concepts, Tools, and Applications
CARLsim 3: Concepts, Tools, and Applications
 
How can we har­ness the Human Brain Project to max­i­mize its future health a...
How can we har­ness the Human Brain Project to max­i­mize its future health a...How can we har­ness the Human Brain Project to max­i­mize its future health a...
How can we har­ness the Human Brain Project to max­i­mize its future health a...
 
The Human Connectome Project multimodal cortical parcellation: new avenues fo...
The Human Connectome Project multimodal cortical parcellation: new avenues fo...The Human Connectome Project multimodal cortical parcellation: new avenues fo...
The Human Connectome Project multimodal cortical parcellation: new avenues fo...
 
Two Cognitive Architectures for General Intelligence - Cortical Feedback & Ep...
Two Cognitive Architectures for General Intelligence - Cortical Feedback & Ep...Two Cognitive Architectures for General Intelligence - Cortical Feedback & Ep...
Two Cognitive Architectures for General Intelligence - Cortical Feedback & Ep...
 
Two Cognitive Architectures for General Intelligence - Cortical Feedback & Ep...
Two Cognitive Architectures for General Intelligence - Cortical Feedback & Ep...Two Cognitive Architectures for General Intelligence - Cortical Feedback & Ep...
Two Cognitive Architectures for General Intelligence - Cortical Feedback & Ep...
 
Blue Brain Technology, Artificial Intelligence
Blue Brain Technology, Artificial IntelligenceBlue Brain Technology, Artificial Intelligence
Blue Brain Technology, Artificial Intelligence
 
20160203_마인즈랩_딥러닝세미나_02 deep and wide analytics 최대우교수님
20160203_마인즈랩_딥러닝세미나_02 deep and wide analytics 최대우교수님20160203_마인즈랩_딥러닝세미나_02 deep and wide analytics 최대우교수님
20160203_마인즈랩_딥러닝세미나_02 deep and wide analytics 최대우교수님
 
Neural Networks: Self-Organizing Maps (SOM)
Neural Networks:  Self-Organizing Maps (SOM)Neural Networks:  Self-Organizing Maps (SOM)
Neural Networks: Self-Organizing Maps (SOM)
 
Slide Presentation
Slide PresentationSlide Presentation
Slide Presentation
 
dkNET Webinar: The Human BioMolecular Atlas Program (HuBMAP) 10/14/2022
dkNET Webinar: The Human BioMolecular Atlas Program (HuBMAP) 10/14/2022dkNET Webinar: The Human BioMolecular Atlas Program (HuBMAP) 10/14/2022
dkNET Webinar: The Human BioMolecular Atlas Program (HuBMAP) 10/14/2022
 
Reinterpreting the Cortical Circuit
Reinterpreting the Cortical CircuitReinterpreting the Cortical Circuit
Reinterpreting the Cortical Circuit
 
20190122_cohenadad_sc-mri-workshop
20190122_cohenadad_sc-mri-workshop20190122_cohenadad_sc-mri-workshop
20190122_cohenadad_sc-mri-workshop
 
Study proposal: Dohorap
Study proposal: DohorapStudy proposal: Dohorap
Study proposal: Dohorap
 
Neuroinformatics
NeuroinformaticsNeuroinformatics
Neuroinformatics
 
NEUROINFORMATICS
NEUROINFORMATICSNEUROINFORMATICS
NEUROINFORMATICS
 
Individual Brain Charting: third-release dataset validation
Individual Brain Charting: third-release dataset validationIndividual Brain Charting: third-release dataset validation
Individual Brain Charting: third-release dataset validation
 
Seminar blue brain
Seminar blue brainSeminar blue brain
Seminar blue brain
 

More from Ting-Shuo Yo

20141030 ntustme computer_programmingandbeyond_share
20141030 ntustme computer_programmingandbeyond_share20141030 ntustme computer_programmingandbeyond_share
20141030 ntustme computer_programmingandbeyond_shareTing-Shuo Yo
 
Tag2Card User's manual v01
Tag2Card User's manual v01Tag2Card User's manual v01
Tag2Card User's manual v01Ting-Shuo Yo
 
Introduction to BCI
Introduction to BCIIntroduction to BCI
Introduction to BCITing-Shuo Yo
 
Design Thinking and Innovation
Design Thinking and InnovationDesign Thinking and Innovation
Design Thinking and InnovationTing-Shuo Yo
 
A Comparison of Evaluation Methods in Coevolution 20070921
A Comparison of Evaluation Methods in Coevolution 20070921A Comparison of Evaluation Methods in Coevolution 20070921
A Comparison of Evaluation Methods in Coevolution 20070921Ting-Shuo Yo
 
Neighborhood Component Analysis 20071108
Neighborhood Component Analysis 20071108Neighborhood Component Analysis 20071108
Neighborhood Component Analysis 20071108Ting-Shuo Yo
 
The Neurophysiology of Speech
The Neurophysiology of SpeechThe Neurophysiology of Speech
The Neurophysiology of SpeechTing-Shuo Yo
 
Simulating Weather: Numerical Weather Prediction as Computational Simulation
Simulating Weather: Numerical Weather Prediction as Computational SimulationSimulating Weather: Numerical Weather Prediction as Computational Simulation
Simulating Weather: Numerical Weather Prediction as Computational SimulationTing-Shuo Yo
 

More from Ting-Shuo Yo (9)

20141030 ntustme computer_programmingandbeyond_share
20141030 ntustme computer_programmingandbeyond_share20141030 ntustme computer_programmingandbeyond_share
20141030 ntustme computer_programmingandbeyond_share
 
Tag2Card User's manual v01
Tag2Card User's manual v01Tag2Card User's manual v01
Tag2Card User's manual v01
 
InnoCentive
InnoCentiveInnoCentive
InnoCentive
 
Introduction to BCI
Introduction to BCIIntroduction to BCI
Introduction to BCI
 
Design Thinking and Innovation
Design Thinking and InnovationDesign Thinking and Innovation
Design Thinking and Innovation
 
A Comparison of Evaluation Methods in Coevolution 20070921
A Comparison of Evaluation Methods in Coevolution 20070921A Comparison of Evaluation Methods in Coevolution 20070921
A Comparison of Evaluation Methods in Coevolution 20070921
 
Neighborhood Component Analysis 20071108
Neighborhood Component Analysis 20071108Neighborhood Component Analysis 20071108
Neighborhood Component Analysis 20071108
 
The Neurophysiology of Speech
The Neurophysiology of SpeechThe Neurophysiology of Speech
The Neurophysiology of Speech
 
Simulating Weather: Numerical Weather Prediction as Computational Simulation
Simulating Weather: Numerical Weather Prediction as Computational SimulationSimulating Weather: Numerical Weather Prediction as Computational Simulation
Simulating Weather: Numerical Weather Prediction as Computational Simulation
 

Diffusion MRI, Tractography,and Connectivity: what machine learning can do?

  • 1. DW-MRI, Tractography, and Connectivity: what Machine Learning can do? Ting-Shuo Yo Max Planck Institute for Human Cognitive and Brain Sciences Leipzig, Germany Max Planck Institute for Human Cognitive and Brain Sciences
  • 2. Where the story begins ● Diffusion Weighted MRI (DWI) is a newly developed MR scanning protocol, which can detect the movement/displacement of water molecules in tissues. ● So far, the techniques used in DWI analysis are mostly deterministic and mechanical. The stochastic approaches (ML related) can bring new insights to this field. 2 Max Planck Institute for Human Cognitive and Brain Sciences
  • 3. Outline ● MPG/MPIs ● A brief introduction of DWI ● What DWI can do ● A comparison of different tractography algorithms ● What ML can do in DWI 3 Max Planck Institute for Human Cognitive and Brain Sciences
  • 4. Outline ● MPG/MPIs – Max Planck Society – Objective and Organization – MPI - CBS ● A brief introduction of DWI ● What DWI can do ● A comparison of different tractography algorithms ● What ML can do in DWI 4 Max Planck Institute for Human Cognitive and Brain Sciences
  • 5. The Max Planck Society ● The Max Planck Society for the Advancement of Science is an independent, non-profit research organization. ● In particular, the Max Planck Society takes up new and innovative and interdisciplinary research areas that German universities are not in a position to accommodate or deal with adequately. 5
  • 6. The Max Planck Institutes ● The research institutes of the Max Planck Society perform basic research in the interest of the general public in the natural sciences, life sciences, social sciences, and the humanities. ● Currently there are 81 MPIs. 6
  • 7. 7 Max Planck Institute for Human Cognitive and Brain Sciences
  • 8. The MPI for CBS 8
  • 9. Outline ● MPG/MPIs ● An Introduction of DWI tractography – Local modelling – Fibre tracking ● What DWI can do ● A comparison of different tractography algorithms ● What ML can do in DWI 9 Max Planck Institute for Human Cognitive and Brain Sciences
  • 10. Diffusion Weighted MRI ● MRI can detect the movement of water molecules. ● The movement is constrained by the neural fibers. 10 Max Planck Institute for Human Cognitive and Brain Sciences
  • 11. Diffusion Weighted MRI ● By posing a gradient magnetic field, the displacement in the corresponding direction can be measured. 11 Max Planck Institute for Human Cognitive and Brain Sciences
  • 12. Tractography (1) ● Local modelling: ➢ Reconstruct the fibre orientation within each voxel 12 Max Planck Institute for Human Cognitive and Brain Sciences
  • 13. Tractography (2) ● Diffusion propagator – Diffusion Tensor (DT) – Multiple compartment models – Persistent Angular Structure (PAS) ● Fibre Orientation Distribution Function – Spherical Deconvolution 13 Max Planck Institute for Human Cognitive and Brain Sciences
  • 14. Tractography (3) ● Fiber tracking: ➢ Reconstruct fibre tracts by integrating the reconstructed local information 14 Max Planck Institute for Human Cognitive and Brain Sciences
  • 15. Tractography (4) ● Streamline approach – Deterministic – Probabilistic ● Optimization for a larger region – Spin tracking – Gibbs tracking 15 Max Planck Institute for Human Cognitive and Brain Sciences
  • 16. Tractography (5) ● Deterministic tracking – At each step, only consider the most likely direction ● Curvature threshold ● Step size ● Interpolation ● ...... 16 Max Planck Institute for Human Cognitive and Brain Sciences
  • 17. Tractography (6) ● Probabilistic tracking – Perform deterministic tracking for multiple times – Allow uncertainty at each step 17 Max Planck Institute for Human Cognitive and Brain Sciences
  • 18. Tractography (7) ● Probabilistic tracking and tractogram – Probability of connection 18 Max Planck Institute for Human Cognitive and Brain Sciences
  • 19. Tractography (8) ● Optimization for a larger region – Spin tracking – Gibbs tracking From Kreher et al. 2008 19 Max Planck Institute for Human Cognitive and Brain Sciences
  • 20. Outline ● MPG/MPIs ● A brief introduction of DWI ● What DWI can do – To reveal anatomical structure in white matter – To construct the general brain network – In vivo ● A comparison of different tractography algorithms ● What ML can do in DWI 20 Max Planck Institute for Human Cognitive and Brain Sciences
  • 21. White matter structure from DWI ● Product of tractography 21 Max Planck Institute for Human Cognitive and Brain Sciences
  • 22. Brain Network from DWI ● Hagmann 2008 22 Max Planck Institute for Human Cognitive and Brain Sciences
  • 23. What DWI can do ● fMRI shows "where" is working. – The "nodes" in a graph/network ● DWI shows the structure of the fiber bundles. – The “edges" in a graph/network – With further analysis, can also show "strength of edges". ● The brain network: – The amount of nodes: 10^2 – The amount of edges: 10^3 23 Max Planck Institute for Human Cognitive and Brain Sciences
  • 24. Outline ● MPG/MPIs ● A brief introduction of DWI ● What DWI can do ● A comparison of different tractography algorithms – Selected algorithms – Procedure – Results ● What ML can do in DWI 24 Max Planck Institute for Human Cognitive and Brain Sciences
  • 25. Selected Algorithms 25 Max Planck Institute for Human Cognitive and Brain Sciences
  • 26. Procedure 26 Max Planck Institute for Human Cognitive and Brain Sciences
  • 27. Results (1) 27 Max Planck Institute for Human Cognitive and Brain Sciences
  • 28. Results (2) 28 Max Planck Institute for Human Cognitive and Brain Sciences
  • 29. Results (3) 29 Max Planck Institute for Human Cognitive and Brain Sciences
  • 30. Results (4) 30 Max Planck Institute for Human Cognitive and Brain Sciences
  • 31. Results (5) 31 Max Planck Institute for Human Cognitive and Brain Sciences
  • 32. Results (6) 32 Max Planck Institute for Human Cognitive and Brain Sciences
  • 33. Results (7) 33 Max Planck Institute for Human Cognitive and Brain Sciences
  • 34. Results (8) 34 Max Planck Institute for Human Cognitive and Brain Sciences
  • 35. Quick Summary ● More connections – Local models which allow multiple fibres – Probabilistic tracking ● Consistent patterns across methods – Strong connections within a lobe – Strong connections to corpus callosum – Weak trans-callosum connections 35 Max Planck Institute for Human Cognitive and Brain Sciences
  • 36. Results (9) 36 Max Planck Institute for Human Cognitive and Brain Sciences
  • 37. Outline ● MPG/MPIs ● A brief introduction of DWI ● What DWI can do ● A comparison of different tractography algorithms ● What ML can do in DWI – Local model reconstruction – Fiber tracking – Further application 37 Max Planck Institute for Human Cognitive and Brain Sciences
  • 38. ML in DWI ● Local modeling: deconvolution approach – Assume the signals are convolution of neural fibers and noises. – Need to “learn" the deconvolution kernel from data defined as "one single fiber". – So far only GLM (2nd order polynomial) is used. – More sophisticated kernel methods can be used. 38 Max Planck Institute for Human Cognitive and Brain Sciences
  • 39. ML in DWI ● Fiber tracking – Speed up the optimization process. – Different fiber reconstruction method. ● Probabilistic modeling of fiber tracts 39 Max Planck Institute for Human Cognitive and Brain Sciences
  • 40. MICCAI'09 Fiber Cup ● 6 datasets: – 3 of resolution 3x3x3mm (image size: 64x64x3) and 3 b-values (650, 1500 and 2000) – 3 of resolution 6x6x6mm (image size: 64x64x1) and 3 b-values (650, 1500, 2650) ● Participants have to return one single fiber per spatial position selected. 40 Max Planck Institute for Human Cognitive and Brain Sciences
  • 41. MICCAI'09 Fiber Cup 41 Max Planck Institute for Human Cognitive and Brain Sciences
  • 42. A Very Brief Review of Tractography ● Local modeling ● Fiber tracking 42 Max Planck Institute for Human Cognitive and Brain Sciences
  • 43. Why are we doing this? ● Streamline-based tractography: – Each simulation (a fiber) is a possible trajectory in the given vector field. ● What is the probability of one given fiber? ● How to select the most representative fibers? 43 Max Planck Institute for Human Cognitive and Brain Sciences
  • 44. Probability of a Fiber Tract (1) ● Fiber tract, t = { x1, x2, ...., xl } ● P(t) = P( x1, x2, ...., xl ) 44 Max Planck Institute for Human Cognitive and Brain Sciences
  • 45. Probability of a Fiber Tract (2) ● Conditional Probability and Joint Probability – P(A|B) = P(A,B) / P(B) – P(A,B) = P(A|B) P(B) ● P(t) = P( x1, x2, ...., xl ) = P(xl| x1, ...., xl-1) P(x1, ...., xl-1) = P(xl| x1, ...., xl-1) P(xl-1|x1, ...., xl-2) P(x1, ...., xl-2) = P(xl| x1, ...., xl-1) P(xl-1|x1, ...., xl-2) ......P(x2|x1) P(x1) 45 Max Planck Institute for Human Cognitive and Brain Sciences
  • 46. Probability of a Fiber Tract (3) ● Assumption: fiber tracking is a 1st order Markov process – P(xi| x1, ...., xi-1) = P(xl|xi-1) – P(t) = P( x1, x2, ...., xl ) = P(xl| x1, ...., xl-1) P(xl-1|x1, ...., xl-2) ......P(x2|x1) P(x1) = P(xl|xl-1) P(xl-1|xl-2) ......P(x2|x1) P(x1) l−1 = P  x 1 ∏ P  x i1∣x i  i=1 46 Max Planck Institute for Human Cognitive and Brain Sciences
  • 47. Probability of a Fiber Tract (4) ● How do we define P(xi+1|xi) and P(xi) ? – C: connection probability map – P(xi) ~ C(xi) – P(xi+1|xi) ~ C(xi+1|xi) ~ C(xi+1,xi) l−1 P t=P  x1  ∏ P  x i1∣x i  i=1 47 Max Planck Institute for Human Cognitive and Brain Sciences
  • 48. Finite State Automata (1) ● Each step of fiber tracking can lead to next middle point or the terminal point. 48 Max Planck Institute for Human Cognitive and Brain Sciences
  • 49. Finite State Automata (2) t={x 1 , ... , x l } l−1 P t=P0  x l  ∏ 1−P 0  x i  i=1 49 Max Planck Institute for Human Cognitive and Brain Sciences
  • 50. Finite State Automata (3) ● How to define P0? – # of fibers in the neighboring voxels, NB(x) – (1-P0(xi)) ~ C(NB(xi)) P 0  x=1−C  x k – C(NB(xi))~ C(xi) K = 20, 10, 5 l−1 P t=P0  x l  ∏ 1−P 0  x i  i=1 l −1 P t≃∏ 1−1−C  xi k i=1 50 Max Planck Institute for Human Cognitive and Brain Sciences
  • 51. Finite State Automata (4) ● Likelihood and Log-likelihood l−1 P t=P0  x l  ∏ 1−P 0  x i  i=1 l −1 P t≃∏ 1−1−C  xi  k i=1 l−1 l−1 L t≃∑ ln 1−1−C  x i k ≃∑ −1−C  xi k i=1 i=1 Approximation with 1st order Taylor's expansion 51 Max Planck Institute for Human Cognitive and Brain Sciences
  • 52. Entropy of a Fiber Tract (1) ● Entropy l H t =∑ C  x i ⋅lnC  x i  i=1 ● Can be seen as the log-likelihood of l l ∑ C  xi ⋅lnC  xi =ln ∏ C  x i  C xi   i=1 i =1 52 Max Planck Institute for Human Cognitive and Brain Sciences
  • 53. Fiber Cup Results (2) Max. Entropy Max. Likelihood 53 Max Planck Institute for Human Cognitive and Brain Sciences
  • 54. ML in DWI ● Connectivity based clustering – Brain parcellation – Brain tissue is mostly continuous without clear segmentation, how to define regions on it? – Perform clustering based on the connectivity matrices. 54 Max Planck Institute for Human Cognitive and Brain Sciences
  • 55. Leipzig, Germany Saclay, Gif-sur-Yvette, France A. Anwander M. Descoteaux T.R. Knösche P. Fillard T. Yo C. Poupon 55 Max Planck Institute for Human Cognitive and Brain Sciences
  • 56. Questions 56 Max Planck Institute for Human Cognitive and Brain Sciences
  • 57. Doing what the brain does - how computers learn to listen 57 Max Planck Institute for Human Cognitive and Brain Sciences
  • 58. Thank You 58 Max Planck Institute for Human Cognitive and Brain Sciences