330
Q. Chen et al.
reflective and locally connected pixels that are spatially located below the RNFL
are taken as the initial estimate of the RPE layer. The morphological opening and
thickness constraint (RPE is approximately constant thickness) are adopted to smooth
and refine the RPE estimation. Lastly, the unhealthy (abnormal) and healthy (normal)
RPE layers are obtained by interpolation and fitting. The fitted lower boundary of
the normal RPE layer is taken as the baseline of the projection region used for the
RSVP generation, while the top boundary of the projection region is determined
by displacing the fitted normal RPE layer upwards the same distance as the largest
drusen peak found in the cube (Fig. 11.1a).
More so, to effectively improve the drusen visualization, this method (RSVP)
method also incorporates the brightening of the drusen substance region. We find the
maximum intensity pixel in the interpolated RPE layer and replace the values of the
pixels underneath it with this maximum intensity value, for each axial column of the
SD-OCT scans.
11.3.4.2 GA Visualization
There are two primary characteristics of GA which can be observed in SD-OCT
images: choroid brightening and RPE thinning. The choroid in GA regions is always
brighter than in healthy regions, due to RPE cell loss, increase of light penetration
in the retina, and subsequent increased reflections from the choroid coat. In the GA
regions, the RPE thickness is always thinner than in other regions. Thus, we designed
a GA visualization algorithm that is based on the detection regions with increased
brightness in the choroid region, and the RPE thinning characteristics is also used to
enhance the GA visualization.
11.3.4.3 Choroid Region Summing
We restricted the SVP projection to a sub-volume beneath the RPE layer where the
choroid resides and where the high reflections (or bright choroid) indicate where
GA is present, in order to improve the traditional SVP image for GA visualization.
Figure 11.34 shows a GA visualization example with the traditional SVP projection
(Left) and the RSVP projection (Right). The contrast of GA in the RSVP image is
higher than in the SVP image, which could potentially improve the performance of a
computerized GA segmentation method. The RSVP projection appears more blurred
than the SVP projection; this is due to smoothing with bilateral filtering for SD-OCT
retinal images.
11.3.4.4 RPE Thickness
As observed for healthy retina without GA, the RPE thickness is approximately constant (20 µm). Therefore, we employed the segmented RPE layer vicinity described
Q. Chen et al.
reflective and locally connected pixels that are spatially located below the RNFL
are taken as the initial estimate of the RPE layer. The morphological opening and
thickness constraint (RPE is approximately constant thickness) are adopted to smooth
and refine the RPE estimation. Lastly, the unhealthy (abnormal) and healthy (normal)
RPE layers are obtained by interpolation and fitting. The fitted lower boundary of
the normal RPE layer is taken as the baseline of the projection region used for the
RSVP generation, while the top boundary of the projection region is determined
by displacing the fitted normal RPE layer upwards the same distance as the largest
drusen peak found in the cube (Fig. 11.1a).
More so, to effectively improve the drusen visualization, this method (RSVP)
method also incorporates the brightening of the drusen substance region. We find the
maximum intensity pixel in the interpolated RPE layer and replace the values of the
pixels underneath it with this maximum intensity value, for each axial column of the
SD-OCT scans.
11.3.4.2 GA Visualization
There are two primary characteristics of GA which can be observed in SD-OCT
images: choroid brightening and RPE thinning. The choroid in GA regions is always
brighter than in healthy regions, due to RPE cell loss, increase of light penetration
in the retina, and subsequent increased reflections from the choroid coat. In the GA
regions, the RPE thickness is always thinner than in other regions. Thus, we designed
a GA visualization algorithm that is based on the detection regions with increased
brightness in the choroid region, and the RPE thinning characteristics is also used to
enhance the GA visualization.
11.3.4.3 Choroid Region Summing
We restricted the SVP projection to a sub-volume beneath the RPE layer where the
choroid resides and where the high reflections (or bright choroid) indicate where
GA is present, in order to improve the traditional SVP image for GA visualization.
Figure 11.34 shows a GA visualization example with the traditional SVP projection
(Left) and the RSVP projection (Right). The contrast of GA in the RSVP image is
higher than in the SVP image, which could potentially improve the performance of a
computerized GA segmentation method. The RSVP projection appears more blurred
than the SVP projection; this is due to smoothing with bilateral filtering for SD-OCT
retinal images.
11.3.4.4 RPE Thickness
As observed for healthy retina without GA, the RPE thickness is approximately constant (20 µm). Therefore, we employed the segmented RPE layer vicinity described