Title: Koen Van Leemput1,2, Akram Bakkour1,3, Thomas Benner1, Graham Wiggins1,
1Automated Segmentation of Hippocampal Subfields
from Ultra-High Resolution In Vivo MRI
Koen Van Leemput1,2, Akram Bakkour1,3, Thomas
Benner1, Graham Wiggins1, Lawrence L. Wald1,4,
Jean Augustinack1, Bradford C. Dickerson1,3,
Polina Golland2, and Bruce Fischl1,2,4
1 Athinoula A. Martinos Center for Biomedical
Imaging, Department of Radiology, MGH, Harvard
Medical School, USA 2 Computer Science and
Artificial Intelligence Laboratory, MIT, USA 3
Department of Neurology, MGH, Harvard Medical
School, USA 4 Harvard-MIT Division of Health
Sciences and Technology, MIT, USA
2Introduction
- The hippocampus consists of multiple, interacting
subregions - Distinct hippocampal subregions
- are implicated in different memory subsystems
- are differentially affected in different
conditions and disease processes (normal aging,
Alzheimers disease (AD), )
3Introduction
The ability to reliably detect these subregions
using in vivo neuroimaging is of great potential
value Basic neuroscience insights into the
function and structure of the hippocampus in the
living human brain, and how it is affected in
normal aging. Clinical research sensitive,
non-invasive biomarkers for early diagnosis,
treatment evaluation, and clinical trials in AD.
4Introduction
- Recent developments in MR data acquisition
technology are starting to yield images that show
anatomical features of the hippocampal formation
at an unprecedented level of detail
New opportunities for explicitly quantifying
individual subregions, rather than their
agglomerate, directly from in vivo MRI
Standard resolution 1 x 1 x 1 mm3
Analyzing large imaging studies of ultra-high
resolution MRI scans requires automated
computational techniques
Ultra-high resolution 0.38 x 0.38 x 0.8 mm3
5Model-based segmentation
- Derive computational models from manual
delinations in a number of subjects - Use those models to automatically segment MRI
scans of new subjects
Manual delineation in subject 1
Manual delineation in subject N
Scan of new subject
6Probabilistic atlas
Manual delineation in subject 1
Manual delineation in subject N
prior probability for subiculum
prior probability for white matter
etc
7Probabilistic atlas
8Statistical model of image formation
prior probability for white matter
prior probability for subiculum
etc
9Statistical model of image formation
deformed prior probability for white matter
deformed prior probability for subiculum
etc
10Statistical model of image formation
Label image
etc
11Statistical model of image formation
Label image
MR image
etc
12Segmentation solving the inverse problem
MR image
13Segmentation solving the inverse problem
MR image
Label image
14Segmentation solving the inverse problem
MR image
Label image
15Segmentation solving the inverse problem
MR image
Label image
Bayesian inference
- Start from our statistical model of image
formation - Play with the mathematical rules of probability
16Example
17Example
18Example
19Example
20Example
21Example
22Example
23Validation Van Leemput et al., Hippocampus
2009
- Ultra-high resolution (0.38 x 0.38 x 0.8 mm3) MRI
data - 3T Siemens Trio with prototype custom-built
32-channel coil - Optimized MPRAGE sequence, 208 coronal slices
- 5 acquisitions motion-corrected and resampled to
0.38mm isostropic - Manual segmentation of the right hippocampus in
10 subjects (6 younger 4 older cognitive
normal, age range 22-89) - Fimbria, CA1, CA2/3, CA4/DG, presubiculum,
subiculum, hippocampal fissure surrounding
structures - Extremely time consuming several days per
hippocampus!
Validation of the automated segmentation
algorithm using leave-one-out cross-validation
24Qualitative results
MRI data
manual segmentation
automated segmentation
25Quantitative results spatial overlap
- Dice coefficient for automated vs. manual
segmentation - ( volume of overlap ) / ( average volume )
26Quantitative results spatial overlap
- Two slices in the midbody of the hippocampus
re-segmented twice by the same operator for five
subjects - Dice overlap between repeated manual
segmentations (empty bars) vs. Dive overlap
between automated and manual segmentations
(filled bars)
27Quantitative results volume measurements
- Volume differences between manual and automated
segmentations - Linear regression between volume measurements
with both methods (Pearsons correlation
coefficient)
0.91 p 0.0002
0.60 p 0.066
0.83 p 0.0028
Corr. coeff.
28Currently working on
- Segmenting hippocampal subfields in lower
resolution scans - Explicitly modeling the partial volume
effect
Standard resolution 1 x 1 x 1 mm3
29Currently working on
- Segmenting hippocampal subfields in standard
resolution (1x1x1mm3) scans - Quantifying segmentation
uncertainties - (error bars on
measurements)
30Currently working on
- Incorporating the software code into FreeSurfer