Diabetic Retinopathy Prof. Andrew Hunter ahunter@lincoln.ac.uk - - PowerPoint PPT Presentation

▶
diabetic retinopathy
SMART_READER_LITE
LIVE PREVIEW

Diabetic Retinopathy Prof. Andrew Hunter ahunter@lincoln.ac.uk - - PowerPoint PPT Presentation

Nov 12, 2022 31 likes •244 views

Diabetic Retinopathy Prof. Andrew Hunter ahunter@lincoln.ac.uk Lincoln University 22 th Sept. 2004 Diabetic Retinopathy The leading cause of blindness in the developed world Several million diabetics require annual screening in the

slide-1
SLIDE 1

Diabetic Retinopathy

  • Prof. Andrew Hunter

ahunter@lincoln.ac.uk Lincoln University 22th Sept. 2004

slide-2
SLIDE 2

Diabetic Retinopathy

  • The leading cause of blindness in the developed

world

– Several million diabetics require annual screening in the UK alone

  • Primary indictor: small “dots and spots” on special

retinal photographs

  • Vascular changes – beading and

neovascularization

  • Macula Oedema – swelling (discoloration and

surface shape)

slide-3
SLIDE 3

Diabetic Retinopathy

slide-4
SLIDE 4

A Haemorrhage in detail

slide-5
SLIDE 5

Peak points

slide-6
SLIDE 6

Circular Peak Points

slide-7
SLIDE 7

Lesion Growing

slide-8
SLIDE 8

An algorithm to find dark lesions

  • Extract features (measurements)
  • Contrast, shape, size, blurriness, etc. etc.
  • Feed these measurements to a neural

network which learns to distinguish lesions from distractors

slide-9
SLIDE 9

Feature Selection Method

  • Use of sensitivity analysis for classifier

inputs

  • Exploits “missing value substitution”

procedure

  • Ratio of performance with and without

available information

  • Hierarchical feature selection
slide-10
SLIDE 10

Optic Nerve Head segmentation

  • Interesting problem in deformable

modelling

  • Fundamental shape is fairly simple –

elliptical with vertical major axis

  • Overlapping blood vessels
  • Presence of pallor and peri-papilliary

atrophy distractors

slide-11
SLIDE 11

Sample Optic Nerve Heads

slide-12
SLIDE 12

The Algorithm

  • Global/local deformable model
  • Global model – fixed aspect ratio ellipse
  • Local model – distortions away from this
  • Spokes projected at 15 degree angles
  • Attractor points at maximum coincident

gradients (or second order local gradient)

  • Balance of global, local, smoothing forces
slide-13
SLIDE 13

The Deformable Model

slide-14
SLIDE 14

The stages

  • Fit global model against temporal sector of

ONH only (temporal lock phase)

  • Fit global model against whole ONH
  • Let the local model loose to fit the full

model

slide-15
SLIDE 15

Vascular Measurement

  • Changes in widths of vessels are very

diagnostic

  • Typical vessels no more than 6-8 pixels

wide

  • Require width measurements to sub-pixel

accuracy

slide-16
SLIDE 16

Vascular Model

  • A gaussian extruded forms a reasonable

shape model for a vessel

  • A difference of gaussians models specular

highlights

slide-17
SLIDE 17

A vessel profile

slide-18
SLIDE 18

Vascular Model

slide-19
SLIDE 19

Sub-pixel accuracy

  • Deformable models like this can fit

boundaries to sub-pixel accuracy

  • Exploitation of anti-aliasing effect
  • Human beings do this routinely

– That’s how a television works!

  • Accurate to at least 0.34 pixels on our tests
  • Used high-resolution images rescaled for

the algorithm (by a factor of 4).

slide-20
SLIDE 20

Algorithm at work

slide-21
SLIDE 21

Real World Use?

  • Sensitivity / specificity for Sight Threatening

Retinopathy

– Lesions near to the macula

  • 97% sensitivity (one error), 75% specificity
  • This is still insufficient! – why?

– Unanticipated disease conditions – Severe disease conditions

  • Planning use in audit rather than automated

screening