Screening and Diagnosis of Diabetic

peachpuceΤεχνίτη Νοημοσύνη και Ρομποτική

6 Νοε 2013 (πριν από 4 χρόνια και 4 μέρες)

66 εμφανίσεις

Image Processing in the Tosca Project



Developing Internet Based Software for
Screening and Diagnosis of Diabetic
Retinopathy

Ole K Hejlesen
1
, Bernhard M Ege
1
, Karl
-
Hans
Englmeier
2
, Steve Aldington
3
, Leo McCanna
4
, Toke Bek
5

1
Department of Health Science and Technology, Aalborg University, Fredrik
Bajersvej 7 D1, DK
-
9220 Aalborg, Denmark,
2
GSF
-
MEDIS, Munich,
Germany,
3
Imperial College, London, UK,
4
OCUCO Ltd. Dublin, Ireland
5
Department of Ophthalmology,
Aa
rhus University Hospital, Denmark

Aim


to develop Internet based software and
image data bases


for screening and diagnosis of diabetic
retinopathy and


implementing it into a real life situation


The
work consisted of



Construction of an Internet based communication
platform for transmitting and analyzing retinal
images


Implementation of routines for


detecting the first microaneurysm (transition from
normal to pathologic)


detecting patients needing referral for treatment
(presence of venous beading or hard exudates near the
fovea)


serial analysis (image alignment)


Construction of a reference image data base


C
ommunication structure

Internet based communication

platform


example: image alignment


Web Client


standard browser


Web Server


image analysis broker


Image Processing Servers


ex: image
alignment


Image alignment

Unaligned

images

Aligned

images

Landmark

extraction

Point

matching

Polynomial

transf.

Image

warping




Cross validation results


Deviation from “perfect”, i.e. the deviation of rotation, translation and mean
distance from 0, and the deviation of scale from 1

(
Cideciyan


1995)
.


Affine
Polynomial
Scale
µ
0.00052
0.00009
s
2
0.000000240
0.000000009
Rotation
µ
0.045
0.013
s
2
0.00100
0.00007
Translation x
µ
0.43
0.13
s
2
0.190
0.007
Translation y
µ
0.400
0.085
s
2
0.1400
0.0054
µ
0.92
0.58
s
2
0.12
0.03
Transformation
Mean dist. [pixel]
100 + 50 + 50 + 50 +50 + 50 patients

Results


Validation

of

the

reference

image

data

base

by

double

grading

by

two

expert

graders

suggested

a

sensitivity

and

a

specificity

of

just

below

90
%

for

any

lesion

and

of

more

than

95
%

for

predicting

the

overall

retinopathy

grade
.


Conclusion


TOSCA
-
Imaging

has

succeeded

in

its

primary

aim

of

developing

Internet

based

software

and

implementing

it

into

a

real

life

situation,

integrating

work

within

image

processing

done

in

four

different

European

countries

(England,

Germany,

Ireland,

and

Denmark)

to

be

accessed

from

one

Internet

web

site
.


Acknowledgements


The TOSCA Project was financed by EU's
Fifth Framework IST Programme