1. Quantitative analysis of radiologic images:
Image segmentation and registration,
statistical atlases
Christos Davatzikos, Ph.D.
Professor of Radiology
Section of Biomedical Image Analysis
http://www.rad.upenn.edu/sbia
2. You can control a quantity if you can measure or weigh it
Lord Kelvin, 1824-1907
Need to develop tools that obtain accurate and
precise measurement from image data
3. Expert 1: Total Lesion volume: 15,635 mm^3 Expert 2: Total Lesion volume: 7,560 mm^3
Human limitations in measuring: inter-rater differences
5. Quantification/measurement:
- ~3% longitudinal atrophy of the
hippocampus in early AD patients
- Contraction pattern of the cardiac muscle
- a 5% change in radiologic signal could be
indicative of evolving pathology
More human limitations
8. Manual Drawing of anatomical structures
Visual evaluation of a 3% atrophy is practically
impossible Laborious and not well-reproducible
manual outlining is required
9. •Evaluating complex spatio-temporal patterns of
radiologic signal change, especially if the
magnitude of the signal change is small and
anatomical variability is large
Kahneman and Tversky in their Nobel prize winninng
careers studied human reasoning under uncertainty and
demonstrated the limitations of human reasoning in
evaluating conjunctions, i.e. A and B and C …
Even more fundamental limitations of human evaluation
13. Brain and criminal behavior
-2
-1.8
-1.6
-1.4
-1.2
-1
-0.8
-0.6
-0.4
-0.2
0
Total
Frontal
Left
Total
Frontal
Right
Total
Parietal
Left
Total
Parietal
Right
Total
Temporal
Left
Total
Temporal
Right
Total
Occipital
Left
Total
Occipital
Right
lateral
ventricle
left
lateral
ventricle
right
15. Statistical anatomical atlases: from single-
individual anatomical examples, to atlases
capturing variability in a population
Analogous to training of a human reader
16. • Disease identification (learn variation of normal anatomy
identify abnormality as a deviation from normal variation)
• Integration of data from multiple individuals in order to discover
systematic relationships among radiologic and clinical measurements
-Does a lesion in a particular part of the brain correlate with a
certain neurological deficit?
-Does prostate cancer appear uniformly throughout the prostate or
does it tend to appear in certain regions more frequently what
is the optimal way of biopsying/treating a patient in order to
maximize probability of cancer detection/elimination?)
-What is the normal variation of hippocampal size for a given
age?
- What is the normal variation of cardiac shape and deformation?
17. Image Registration: Integration and Comparative Analysis of
Images from different individuals / modalities / times /conditions
Before
Spatial
Normalization
After
Spatial
Normalization
--Image integration and co-registration helps generalize
from the individual to the group, and to construct normative
data abnormalities can be distinguished from normal
statistical variation
Underlying biological
process that results in
abnormal signal, or
simply normal tissue
whose normal variability,
in terms of image
properties, needs to be
measured
Overlay/Comparison
of such images?
19. • The deformation function measures the local deformation of the template:
Deformation 1 Deformation 2
Local structural measurements can be measured by analyzing the
deformation functions with standard statistical methodologies
Template Shape 1 Shape 2
Red: Contraction
Green:
Expansion
≈
High-Dimensional Shape Transformations
Template MR image Warped template
20.
21. Significant 4-year GM changes in 107 older adults
From the cover page of
the Lancet, Neurology
23. Tissue atrophy map of an AD patient, relative to
cognitively normal controls
Template Space
Patient’s scan
24. Regions of differences between
schizophrenics and normal controls
Average of 148 brain
images, after
deformable registration
to the atlas
25. Atlas with optimal
needle positions
Apex
Base
Left
Right
6
7
4
3
1
2
5
Apex
Base
Left Right
Targeted Prostate Biopsy Using Mathematical Optimization
100 Samples Template
…
Segmented 3D Prostate
Warped Prostate Atlas
US prostate image
MRI prostate image
Deformable Segmentation
of Prostate Images
26. 20 subjects, average age 64.70 20 subjects, average age 83.05
Quantitative analysis
meets
visual image interpretation
40174 mm3
20564 mm3
“Younger Old Adult”
Average Model
“Older Old Adult”
Average Model
Average age 64.7 Average age 83
27. Using a statistical atlas to guide
WM lesion segmentation
Spatial distribution of WM
abnormalities in 50 older adults
(BLSA)
29. Pattern Matching: Finding
Anatomical Correspondences
Attribute vector based on wavelet analysis of the anatomical context
around each voxel morphological signature of each voxel
31. Model
Measuring volumes of anatomical structures :
An atlas with anatomical definitions is registered to the patient’s images
Subject
HAMMER HAMMER
32. To summarize:
• Anatomical definitions are used to create an atlas
analogous to the knowledge of anatomy by humans
• Pattern matching performed hierachically at various
scales is used to match the atlas to the individual
33. Can we use these quantitative image
analysis tools as diagnostic tools?
-Combine all morphological, physiological, and clinical
measurements into a broader phenotypic profile
-Use high-dimensional pattern classification and machine
learning techniques
Problem: Potentially high statistical
overlap for any single anatomical
structure, if disease is not focal
34. Where is the problem?
0.001
0.0012
0.0014
0.0016
0.0018
0.002
0.0022
0.0024
0.0026
0.0028
0.0017 0.0027 0.0037 0.0047
Hippocampus Volume
Entorhinal
Cortex
Volume
Normal Controls
MCI
Data from Baltimore Longitudinal Study of Aging, Davatzikos et.al.
Neurobiology of aging, in press
35. Pattern
Classification
Abnormality
score
A pattern is sampled by measuring brain volumes
and blood flow in a number of brain regions
• Local tissue volumes and PET O15 are combined
• 15-20 brain regions (clusters) build a multi-
parametric imaging profile
36. Abnormality Score
Measurement and Integration of Structural
and Functional Patterns
0.001
0.0012
0.0014
0.0016
0.0018
0.002
0.0022
0.0024
0.0026
0.0028
0.0017 0.0027 0.0037 0.0047
Hippocampus Volume
Entorhinal
Cortex
Volume
Normal Controls
MCI
37. Individual Diagnosis
• High-dimensional Pattern Classification (Machine learning)
• Evaluate spatial patterns of GM, WM, CSF, PET signal distribution
• Use these pattern to construct an image-based classifier, using
support vector machines
L-ERC
w
Anterior L-hipp
38. Brain regions that collectively contributed to classification
All GM
Effect size
WM
Effect size
PET
Effect size
Images in radiology
convention
40. Change of abnormality scores over time
* Clinically normal, has now gone
through autopsy with Braak 4 and
moderate plaques meets AD
pathology criteria
*
After removing this one
participant
41. Normals: -0.3
MCI at latest scan: 0.26
MCI at year of conversion: 0.15
Already significant structural abnormality
on year of conversion to MCI
Abnormality scores when converting from normal to MCI
42. Data from ADNI
AD vs CN classifier applied to MCI: most MCI’s
have AD-like MRI profiles
MMSE
decline
43. fMRI for Lie Detection: A Card
Concealment Experiment
• Experiments performed by the Brain and Behavior Laboratory (Psychiatry)
• Particiapnts were asked to lie about the possession of a card of their choice
• 22 participants, both true/lie responses
• Parameter images were created using the GLM with double gamma HRF
50. Conclusion
Computers can complement humans in:
• Quantification
• Increased reproducibility
• Analysis of non-focal disease
• Evaluating complex spatio-temporal patterns
-patterns of longitudinal change of structure and
function
- patterns of tissue motion and deformation
In the heart of computational image analysis is the notion of
statistical atlases, which represent normal variation and help
identify disease as a deviation from this normal range