Segmentation of Brain MRI in Young Children

1
Segmentation of Brain MRI in Young Children

• Maria Murgasova1, Leigh Dyet2,
• David Edwards2, Mary Rutherford2, Jo Hajnal2 and
  Daniel Rueckert1
• 1Department of Computing
• 2Department of Imaging Sciences
• Imperial College London

2
Motivation

• The effect of premature birth
• impaired brain development
• neurological, behavioural, learning difficulties
• To understand and treat the changes we need to
  measure
• volumes of different brain structures
• growth of different brain structures
• This requires
• segmentation of anatomical
• structures at different time points

3
Registration-based segmentation

• Non-rigid registration of atlas to subject
• Segmentation is warped from atlas to subject
• Advantage
• Does not assume any tissue intensity model
• gt successful in central brain structures
• Disadvantage
• Does not deal well with complex cortical folding

4
EM-based segmentation

• Expectation-Maximisation framework (Dempster
  1977)
• E-step
• soft segmentation
• MRF for smoothness and connectivity (Zhang 2001)
• Partial volume effect model (Joshi 2005)
• M-step
• Tissue intensity distributions (Van Leemput 1999)
• Bias estimation (Wells 1996, Van Leemput 1999)
• Registration of a probabilistic atlas (Ashburner
  2005, dAgostino 2006 , Pohl 2005)

5
EM-based segmentation

• Classical model for brain MRI
• 3 basic tissue classes (WM, GM, CSF)
• Tissue intensity distributions approximately
  Gaussian
• Advantage
• Can capture complexity of cortex based on
  intensity
• Disadvantage
• Cant deal well with overlaps in tissue intensity
  distributions

Real tissue distributions of 2-year-old subject
based on manual segmentation
6
EM-based segmentation

• Sub cortical structures brighter than cortical
• Overlaps cause significant difficulties
• Classical WM, GM, CSF model not sufficient for
  correct segmentation

The histograms were normalised to unit height
7
EM-based segmentation

• Probabilistic atlas
• Aligned with the image
• Spatially constrains the segmentation process
• Helps to overcome misclassification due to
  overlaps in tissue intensity distributions

8
Application of EM to young children

• Bias correction N3 (Sled 1998)
• Affine registration of probabilistic atlas
• EM segmentation (Van Leemput 1999)
• E-step soft segmentation
• M-step Gaussian tissue intensity distribution

9
Application of EM to young children

• During early childhood the shape of central brain
  structures differs significantly from those
  during adulthood
• WM overestimated in sub-cortical area
• Requires a specific atlas for young children

Segmentation of 1-year-old
Adult
Adult atlas
1-year-old
10
Creating a population-specific atlas
Manual segmentation
Reference subject
Average subjects
Non-rigid registration
Population specific atlas
Affine registration
New subject
Registration-based segmentation
11
Atlas comparison

• Atlas for
• 2-year-olds
• (from
• 37 subjects)
• Adult atlas

12
Segmentation results

• Improvement in thalamus
• 1.0T brain MRI of a 2-year-old child

Image
Manual segmentation
EM with adult atlas
EM with new atlas
13
Segmentation results

• Improvement overall
• 1.0T brain MRI of a 2-year-old child

Image
Adult atlas
Our atlas
14
Validation

• Dice metric
• Agreement between manual and automatic
  segmentation
• Tman set of samples in manual segmentation
• Taut set of samples in automatic segmentation

15
Validation

• 1 subject complete manual segmentation

EMS original software for EM segmentation by
Koen Van Leemput
16
Validation

• 4 subjects
• manual segmentation of 6-8 slices
• manual segmentation of thalamus

17
Conclusions

• Atlas can be generated dynamically for different
  populations

Age 1
Age 2
18
Conclusions

• Global model for intensity distributions of WM
  and GM is not sufficient
• Population-specific atlas substantially improves
  the segmentation results
• Future work
• Include more brain structures in the model
  (Fischl 2002, Pohl 2005)
• Local tissue intensity distribution estimation

19
Acknowledgements

• This work is funded by