Medical Image Processing and Analysis Kaikai Shen, PhD Visiting - - PowerPoint PPT Presentation

▶
medical image processing and analysis
SMART_READER_LITE
LIVE PREVIEW

Medical Image Processing and Analysis Kaikai Shen, PhD Visiting - - PowerPoint PPT Presentation

Aug 18, 2023 163 likes •500 views

Medical Image Processing and Analysis Kaikai Shen, PhD Visiting Fellow, Department of Biomedical Sciences, Macquarie University; Research Scientist, Australian eHealth Research Centre, CSIRO; Australian Alzheimers Research Foundation 25 June

slide-1
SLIDE 1

Medical Image Processing and Analysis

AUSTRALIAN EHEALTH RESEARCH CENTRE, CSIRO

Kaikai Shen, PhD

Visiting Fellow, Department of Biomedical Sciences, Macquarie University; Research Scientist, Australian eHealth Research Centre, CSIRO; Australian Alzheimer’s Research Foundation

25 June 2018

slide-2
SLIDE 2

Medical Imaging and Image Analysis

What we do

  • Develop and apply advanced computational tools to turn individual (and populations
  • f) images into information (imaging biomarkers).

– Accurate and reliable automated image analysis (reduces costs and may improve care), – provide new insights (Validity, reproducibility and predictive value), – enables new and improved diagnostics, screening and treatments.

Medical Image Processing and Analysis | Kaikai Shen 2 |

Image analysis team § image processing

§ registration § segmentation § pattern recognition § machine learning § statistics Medical Images Personalized medicine § Monitor individuals changes. § Patient specific treatments § Characterize phenotype variability of disease. Preventing diseases § Population studies § Early detection/screening § Diagnosis tools

slide-3
SLIDE 3

Quantitative Image Analysis

Overview of Neuroimaging Biomarkers we extract

Medical Image Processing and Analysis | Kaikai Shen 3 |

DWI

White matter connections

FLAIR

White matter lesions

SWI

Venous tree

T2W

CSF and structures

T1W

Anatomy

PET

Amyloid beta load Glucose metabolism

Neocortical uptake Patten of uptake Connectivity strength Axonal integrity White matter lesions Microbleeds Iron deposit Tissue atrophy Cortical thickness Hippocampus volume Atrophy patterns Tissue contrast

slide-4
SLIDE 4

Quantitative Image Analysis

Medical Image Processing and Analysis | Kaikai Shen 4 |

Prostate radiotherapy planning with MRI

Knee Vertebrae Hip

slide-5
SLIDE 5

Structural MRI: structural changes in neurodegenerative diseases

Medical Image Processing and Analysis | Kaikai Shen 5 |

slide-6
SLIDE 6

Structural MRI: structural changes in neurodegenerative diseases

Medical Image Processing and Analysis | Kaikai Shen 6 |

Atrophy compared to Healthy control in early Alzheimer’s disease

slide-7
SLIDE 7

Structural MRI: Volumetric Analysis

Medical Image Processing and Analysis | Kaikai Shen 7 |

Skull Stripping Group-wise Registration Multi-Atlas (N=30) Hippocampus Parcellation Multi-Atlas (N=15) Full brain Parcellation Segmentation

Native Space

slide-8
SLIDE 8

Structural MRI: Cortical thickness

Medical Image Processing and Analysis | Kaikai Shen 8 |

Cortical Thickness Z-score and report Smoothing and registration to template Meshing Web interface

slide-9
SLIDE 9

Structural MRI (cont.)

Medical Image Processing and Analysis | Kaikai Shen 9 |

slide-10
SLIDE 10

CurAIBL: MR Assessment of Neurodegeneration

Medical Image Processing and Analysis | Kaikai Shen 10 |

https://milxcloud.csiro.au

slide-11
SLIDE 11

Medical Image Processing and Analysis | Kaikai Shen 11 |

FLAIR WM lesion segmentation

slide-12
SLIDE 12

Diffusion MRI: Background

Medical Image Processing and Analysis | Kaikai Shen 12 |

Unrestricted diffusion Brownian motion

slide-13
SLIDE 13

Diffusion MRI: Background

Medical Image Processing and Analysis | Kaikai Shen 13 |

Diffusion Tensor Imaging (DTI)

slide-14
SLIDE 14

Diffusion MRI: Background

Medical Image Processing and Analysis | Kaikai Shen 14 |

Colour codes for orientation

slide-15
SLIDE 15

Diffusion MRI: Background

Medical Image Processing and Analysis | Kaikai Shen 15 |

slide-16
SLIDE 16

Diffusion MRI: Background

Medical Image Processing and Analysis | Kaikai Shen 16 |

Fibre Orientation Distribution (FOD)

  • Fibre Orientation Distribution (FOD)
  • Constrained spherical deconvolution (Tounier et al., 2008)

Tournier, J.-D., et al., 2008. Resolving crossing fibres using constrained spherical deconvolution: Validation using diffusion- weighted imaging phantom data. NeuroImage 42, 617–625.

slide-17
SLIDE 17

Medical Image Processing and Analysis | Kaikai Shen 17 |

Diffusion Tensor Imaging (DTI)

slide-18
SLIDE 18

Medical Image Processing and Analysis | Kaikai Shen 18 |

Fibre Orientation Distribution

slide-19
SLIDE 19

Medical Image Processing and Analysis | Kaikai Shen 19 |

single-shell single-tissue FOD (b = 3000 s/mm2) multi-shell multi-tissue FOD

slide-20
SLIDE 20

Medical Image Processing and Analysis | Kaikai Shen 20 |

FOD @ b = 3000 s/mm2 multi-shell multi-tissue FOD

slide-21
SLIDE 21

Medical Image Processing and Analysis | Kaikai Shen 21 |

Genetic influence on connectivity

  • Aims
  • To develop new insights into brain development
  • To understand how our brains work in health,

illness, youth, and old age

  • To study the cerebral cortex and the underlying

neural connectivity, from the structural and diffusion MR images

  • To investigate the influence of genes by imaging

monozygotic (MZ) and dizygotic(DZ) twins

  • Twin Study
  • Queensland Twin IMaging study (QTIM)
  • CSIRO and Queensland Institute of Medical

Research (QIMR)

de Zubicaray, G.I., Chiang, M.C., McMahon, K.L., Shattuck, D.W., Toga, A.W., Martin, N.G., Wright, M.J., Thompson, P.M., 2008. Meeting the challenges of neuroimaging genetics. Brain Imaging Behav. 2, 258–263.

slide-22
SLIDE 22

Genetic influence on connectivity: Methods

Medical Image Processing and Analysis | Kaikai Shen 22 |

  • Measure the FODs
  • Peak amplitude

Diffusion Weighted Images

(a) Preprocessing and spherical deconvolution Fibre Orientation

Distribution (FOD) Registered FOD images in the common space FOD peak amplitude

  • f average FOD template

Group average FOD in the common space FOD peak amplitude

  • f FOD images

(c) Find peaks (d) Find peaks on FOD images corresponding to the peaks of the group average FOD (b) Iterateive Groupwise registration (e) Inter-subject statistical analysis

Test-retest reliability of FOD peak measure Heritability of FOD peak measure

Raffelt, D., et al., 2012. Apparent Fibre Density: A novel measure for the analysis of diffusion-weighted magnetic resonance images. NeuroImage 59, 3976–3994.

1st peak 2nd peak

  • Processing/Analysis framework
  • Raffelt et al., 2012
slide-23
SLIDE 23

Genetic influence on connectivity: Methods

Medical Image Processing and Analysis | Kaikai Shen 23 |

  • Diffusiton MR: 94 gradient directions at b = 1159 s/mm2
  • Twin cohort
  • N=328 subjects (118M, 210F), age 22.7(2.3)
  • 71 pairs (N=142, 48M, 94F) of monozygotic twins (MZ) + 90 pairs (N=180,

69M, 111F) of dizygotic twins (DZ)

  • Heritability
  • ACE model: Additive genetics + Common environment + unique

Environment

  • Heritability

FOD = A + C + E

) Var( ) Var( ) Var( ) Var(

2

E C A A h + + =

Falconer’s formula h2 = 2(rMZ – rDZ)

slide-24
SLIDE 24

Medical Image Processing and Analysis | Kaikai Shen 24 |

slide-25
SLIDE 25

Genetic influence on connectivity: Methods

Medical Image Processing and Analysis | Kaikai Shen 25 |

  • Tractography
  • Whole brain, probabilistic using FOD
  • Tract-wise heritability
  • Interpolation of heritabilities of nearest peaks
  • Tract average heritability
slide-26
SLIDE 26

Medical Image Processing and Analysis | Kaikai Shen 26 |

Human Brain Mapping Volume 37, Issue 6, pages 2331-2347, 23 MAR 2016 DOI: 10.1002/hbm.23177 http://onlinelibrary.wiley.com/doi/10.1002/hbm.23177/full#hbm23177-fig-0004

slide-27
SLIDE 27

Medical Image Processing and Analysis | Kaikai Shen 27 |

Heritability maps of cortical thickness. From left to right: heritability index h2, intraclass correlation between monozygotic twins ICCMZ, intraclass correlation between dizygotic twins ICCDZ.

slide-28
SLIDE 28

Medical Image Processing and Analysis | Kaikai Shen 28 |

The genetic correlation rg between the cortical thickness and white matter connectivity measured for each cortical region.

slide-29
SLIDE 29

Positron Emission Tomography (PET)

  • β-amyloid plaque in Alzheimer’s disease
  • PET 11C-PiB has been used as the tracer in many clinical

studies since 2006

Medical Image Processing and Analysis | Kaikai Shen 29 |

slide-30
SLIDE 30

PET: Quantification

Medical Image Processing and Analysis | Kaikai Shen 30 |

Multi-atlas

  • Local Patch based

selection.

  • Bayesian Fusion
  • Estimated GM

Zhou et al. (PloS one; Jan, 2014: DOI: 10.1371/journal.pone.0084777) Results: MR based top PET only bottom

slide-31
SLIDE 31

CapAIBL: PET Assessment of Neurodegeneration

Medical Image Processing and Analysis | Kaikai Shen 31 |

MILXCloud: https://milxcloud.csiro.au/

  • CapAIBL: PET quantification
  • CurAIBL: MRI
slide-32
SLIDE 32

Acknowledgement

Medical Image Processing and Analysis | Kaikai Shen 32 |

Olivier Salvado Jurgen Fripp (CSIRO) Pierrick Bourgeat Shekhar Chandra Amy Chan David Conlan Vincent Doré Amir Fazlollahi Aleš Neubert Kerstin Pannek Anthony Paproki Parnesh Raniga Lee Reid Ying Xia Sabine Bird Belinda Brown Samatha Gardener Simon Laws Stephanie Rainey-Smith Hamid Sohrabi Kevin Taddei Sherilyn Tan Michael Weinborn

  • Prof. Ralph Martins

(MQ, AARF) Pratishtha Chatterjee Cintia Dias Mitra Elmi Sunil Gupta Maryam Mohamaadi Danit Saks Tejal Shah

slide-33
SLIDE 33

Kaikai Shen Kaikai.Shen@csiro.au

AUSTRALIAN EHEALTH RESEARCH CENTRE

Thank you

Medical Image Processing and Analysis | Kaikai Shen 33 |