1 Doing Ontology Over Images Barry Smith. What ontologies are for.
Post on 19-Dec-2015
217 Views
Preview:
Transcript
1
Doing Ontology Over Images
Barry Smith
What ontologies are for
3
what molecular function ?
what disease process ?
need for semantic annotation of data
4
need for semantic annotation of data
through labels (nouns, noun phrases)which are algorithmically processable
5
natural language labels
to make the data cognitively accessible to human beings
6
compare: legends for mapscompare: legends for maps
7
compare: legends for cartoons
9
ontologies are legends for data
10
ontologies are legends for images
11
what lesion ?
what brain function ?
12
xi = vector of measurements of gene i k = the state of the gene ( as “on” or “off”)θi = set of parameters of the Gaussian model......
ontologies are legends for mathematical equations
13
The OBO Foundry Idea
MouseEcotope GlyProt
DiabetInGene
GluChem
sphingolipid transporter
activity
14
annotation using common ontologies yields integration of databases
MouseEcotope GlyProt
DiabetInGene
GluChem
Holliday junction helicase complex
15
annotation using common ontologies can yield integration of image data
16
annotation using common ontologies can support comparison of image data
17
truth
18
simple representations can be true
19
there are true cartoons
20
a cartoon can be a veridical representation of reality
21
Cartographic Projection
22
maps may be correct by reflecting topology, rather than geometry
23
a fully labeled image can be aneven more veridical representation of reality
an image can be a veridical representation of reality
24
25
26
cartoons, like maps, always have a certain threshold of granularity
27
grain resolution
28
grain resolution serves cognitive accessibility
we transform true imagesinto true cartoons
29
there are also true cartoon sequences
30
31
Pathway diagrams are annotated dynamic cartoons
32
pathways can be represented at different levels of granularity
33
the jaw
34
35
Joint capsule
Netter
36
Mandible and condyle movement
37
Condyle position in fossa wrt location of disc
38
TMJ in jaw open and closed positions
39
Parts• 1 head of condyle F• 2 neck of condyle F• 3 disc B• 4 retrodiscal tissue B• 7 articular eminence F• 8 zygomatic arch F• 10 upper head of lateral pterygoid muscle F• 11 lower head of lateral pterygoid muscle F
Holes• 5 lower joint compartment B• 6 upper joint compartment B
Holes and Parts
40
ANTERIOR
Temporomandibular Joint (TMJ)
from Thomas Bittner and Louis Goldberg, KR-MED 2006
41
adjacency relations
No connectednessOnly (temporary) adjacency
Connectednessadjacencygraph
Adjacency relations
42
Frames of reference
Rigid = do notchange shape(bones)
A
BC
DE
F
The extension of the axis of the condyleintersects the fossa in region D
43
instances vs. types
44
two kinds of annotations
45
names of instances
46
names of types
47
pathway maps are representations of complexes of types
48
molecular images and radiographic images are
representations of instances
49
MIAKT system
50
51
52
53
54
Patient #47920
55
56
Mammography #31667
57
Mammography #31667
Medical-Image #44922
58
MRI-Exam #32388
Medical-Image #44922
Mammography #31667
Patient #47920
Breast #1388
Abnormality #86023
top related