320
Q. Chen et al.
11.3.2.7 Conclusions
This section presents a novel algorithm for automated GA segmentation in SD-OCT
images to enable robust, accurate, and objective quantitative measurements of GA
extent and location automatically. The proposed method combines a region-based CV model with a local similarity factor in projection images of a choroid sub-volume.
This technique seems more robust to presence of noise, while preserving image
detail. Quantitative experimental results demonstrate that the algorithm shows good
agreement when compared to manual segmentation by different experts at different
sessions and to a consensus manual gold standard, resulting in higher agreement
than with a previously known semi-automated method and a commercially-available
software package. The proposed algorithm may be clinically useful in providing
relatively reliable GA quantitative data that may improve tracking of GA extent,
location and expansion in patients diagnosed with advanced non-exudative AMD.
11.3.3 Restricted Summed-Area Projection for Geographic
Atrophy Visualization in SD-OCT Images
The main principle of the existing fundus projection GA visualization techniques
generated from SD-OCT images lies in the identification of the typical choroidal
brightening that appears in the regions affected by GA. However, the many blood
vessels in the choroid, which normally manifest in low reflection values, decrease
the contrast and distinction of macular regions affected by GA. As an example,
Fig. 11.25 shows the choroidal vasculature influence on GA visualization, where
Fig. 11.25a and b are the SVP and Sub-RPE Slab projection images generated from
one 3D SD-OCT scan acquired with a Cirrus OCT (Carl Zeiss Meditec) system,
respectively.
The RPE boundaries were delineated by hand. Figure 11.25c displays the B-scan
corresponding to the yellow dashed line in Fig. 11.25a, and several structures that
can be observed in this image are manually labeled.
11.3.3.1 GA Visualization Based on RSAP
The main strategy of the RSAP technique lies in utilizing the intensity distribution
beneath the RPE layer as observed in SD-OCT images to fill the low intensity regions
produced by the presence of choroidal vessels. Vessel presence is identified by analyzing intensity profiles. An example of intensity distribution beneath the RPE in a
typical SD-OCT scan, namely the region between the two dashed green curves in
Fig. 11.25c, where GA is present is displayed in Fig. 11.26. We can observe that
the intensity distribution decreases towards the x direction (depth), and the rate of
this decrease in the GA region is typically slower than that in the normal region.
Q. Chen et al.
11.3.2.7 Conclusions
This section presents a novel algorithm for automated GA segmentation in SD-OCT
images to enable robust, accurate, and objective quantitative measurements of GA
extent and location automatically. The proposed method combines a region-based CV model with a local similarity factor in projection images of a choroid sub-volume.
This technique seems more robust to presence of noise, while preserving image
detail. Quantitative experimental results demonstrate that the algorithm shows good
agreement when compared to manual segmentation by different experts at different
sessions and to a consensus manual gold standard, resulting in higher agreement
than with a previously known semi-automated method and a commercially-available
software package. The proposed algorithm may be clinically useful in providing
relatively reliable GA quantitative data that may improve tracking of GA extent,
location and expansion in patients diagnosed with advanced non-exudative AMD.
11.3.3 Restricted Summed-Area Projection for Geographic
Atrophy Visualization in SD-OCT Images
The main principle of the existing fundus projection GA visualization techniques
generated from SD-OCT images lies in the identification of the typical choroidal
brightening that appears in the regions affected by GA. However, the many blood
vessels in the choroid, which normally manifest in low reflection values, decrease
the contrast and distinction of macular regions affected by GA. As an example,
Fig. 11.25 shows the choroidal vasculature influence on GA visualization, where
Fig. 11.25a and b are the SVP and Sub-RPE Slab projection images generated from
one 3D SD-OCT scan acquired with a Cirrus OCT (Carl Zeiss Meditec) system,
respectively.
The RPE boundaries were delineated by hand. Figure 11.25c displays the B-scan
corresponding to the yellow dashed line in Fig. 11.25a, and several structures that
can be observed in this image are manually labeled.
11.3.3.1 GA Visualization Based on RSAP
The main strategy of the RSAP technique lies in utilizing the intensity distribution
beneath the RPE layer as observed in SD-OCT images to fill the low intensity regions
produced by the presence of choroidal vessels. Vessel presence is identified by analyzing intensity profiles. An example of intensity distribution beneath the RPE in a
typical SD-OCT scan, namely the region between the two dashed green curves in
Fig. 11.25c, where GA is present is displayed in Fig. 11.26. We can observe that
the intensity distribution decreases towards the x direction (depth), and the rate of
this decrease in the GA region is typically slower than that in the normal region.