Fig 1.
Examples of OCT-A images representing all the configurations that were used in this work.
1st row, images of 3x3 millimeters. 2nd row, images of 6x6 millimeters. (a) & (c) Superficial OCT-A images. (b) & (d), Deep OCT-A images.
Fig 2.
Main steps of the proposed methodology.
Fig 3.
Application of the preprocessing step.
(a) Original image. (b) Image result after applying the-top hat operator.
Fig 4.
Vascularity edge identification using the Canny edge detector.
(a) Original OCT-A image (after the top-hat preprocessing step). (b) Results of the vascular edge identification.
Fig 5.
Morphological closure and inversion of intensities followed by a removal of small elements.
(a) Image with the vascular edge identification. (b) Result after applying a morphological closure. (c) Result after applying an inversion of intensity and an opening.
Fig 6.
Example of error in the capture process.
(a) Original image. (b) Initial set of identified FAZ candidates. (c) Final set of FAZ candidates after FP removal.
Fig 7.
Removal process of FAZ FP candidates.
(a) Initial set of identified FAZ candidates. (b) Final set of FAZ candidates.
Fig 8.
Application of the precise final FAZ segmentation.
(a) & (c) Preliminary FAZ extractions. (b) & (d) Final segmentation results.
Table 1.
Accuracy localization FAZ results using the proposed method in healthy OCT-A images.
Fig 9.
Error cases on the FAZ localization process.
Table 2.
Accuracy localization FAZ results using the proposed method in diabetic OCT-A images.
Table 3.
Correlation coefficients that were obtained using the manual and the automatic area size measurements in healthy OCT-A images.
Fig 10.
Comparative examples of the experts (green and red) and the automatic computational (blue) segmentations as well as the corresponding area size measurements.
Table 4.
Correlation coefficients that were obtained using the manual and the automatic area size measurements in diabetic OCT-A images.
Table 5.
Jaccard indexes that were obtained for each subgroup of healthy OCT-A images.
Fig 11.
Comparative examples with goods and bad results in the Jaccard’s index in the four subgroups (superficial and deep in 3 × 3 and 6 × 6 sizes).
Table 6.
Jaccard’s indexes that were obtained for each subgroup of diabetic OCT-A images.
Table 7.
Circularities that were obtained for each group of diabetic OCT-A images.
Fig 12.
Examples of representative FAZ regions from the defined levels of circularity in the diabetic OCT-A dataset.
(a) High level of circularity, (b) medium level of circularity and (c) low level of circularity.
Fig 13.
Comparative examples of the experts (green and red) and the automatic computational (blue) FAZ measurements in superficial 3 millimeters images.
Fig 14.
Comparative examples of the experts (green and red) and the automatic computational (blue) FAZ measurements in superficial 6 millimeters images.
Fig 15.
Comparative examples of the experts (green and red) and the automatic computational (blue) FAZ measurements in deep 3 millimeters images.
Fig 16.
Comparative examples of the experts (green and red) and the automatic computational (blue) FAZ measurements in deep 6 millimeters images.
Table 8.
Worst and best Jaccard’s indexes that were obtained for each subgroup of OCT-A healthy images.
Table 9.
Comparative of the coverage OCT-A image types between this proposal and the Lu et al. [10] and Hwang et al. [11] works.
Table 10.
Comparison of the Jaccard’s indexes that were obtained for 3 × 3 millimeters superficial OCT-A images in our proposal and Lu et al. method [10].