Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

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.

More »

Fig 1 Expand

Fig 2.

Main steps of the proposed methodology.

More »

Fig 2 Expand

Fig 3.

Application of the preprocessing step.

(a) Original image. (b) Image result after applying the-top hat operator.

More »

Fig 3 Expand

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.

More »

Fig 4 Expand

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.

More »

Fig 5 Expand

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.

More »

Fig 6 Expand

Fig 7.

Removal process of FAZ FP candidates.

(a) Initial set of identified FAZ candidates. (b) Final set of FAZ candidates.

More »

Fig 7 Expand

Fig 8.

Application of the precise final FAZ segmentation.

(a) & (c) Preliminary FAZ extractions. (b) & (d) Final segmentation results.

More »

Fig 8 Expand

Table 1.

Accuracy localization FAZ results using the proposed method in healthy OCT-A images.

More »

Table 1 Expand

Fig 9.

Error cases on the FAZ localization process.

More »

Fig 9 Expand

Table 2.

Accuracy localization FAZ results using the proposed method in diabetic OCT-A images.

More »

Table 2 Expand

Table 3.

Correlation coefficients that were obtained using the manual and the automatic area size measurements in healthy OCT-A images.

More »

Table 3 Expand

Fig 10.

Comparative examples of the experts (green and red) and the automatic computational (blue) segmentations as well as the corresponding area size measurements.

More »

Fig 10 Expand

Table 4.

Correlation coefficients that were obtained using the manual and the automatic area size measurements in diabetic OCT-A images.

More »

Table 4 Expand

Table 5.

Jaccard indexes that were obtained for each subgroup of healthy OCT-A images.

More »

Table 5 Expand

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).

More »

Fig 11 Expand

Table 6.

Jaccard’s indexes that were obtained for each subgroup of diabetic OCT-A images.

More »

Table 6 Expand

Table 7.

Circularities that were obtained for each group of diabetic OCT-A images.

More »

Table 7 Expand

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.

More »

Fig 12 Expand

Fig 13.

Comparative examples of the experts (green and red) and the automatic computational (blue) FAZ measurements in superficial 3 millimeters images.

More »

Fig 13 Expand

Fig 14.

Comparative examples of the experts (green and red) and the automatic computational (blue) FAZ measurements in superficial 6 millimeters images.

More »

Fig 14 Expand

Fig 15.

Comparative examples of the experts (green and red) and the automatic computational (blue) FAZ measurements in deep 3 millimeters images.

More »

Fig 15 Expand

Fig 16.

Comparative examples of the experts (green and red) and the automatic computational (blue) FAZ measurements in deep 6 millimeters images.

More »

Fig 16 Expand

Table 8.

Worst and best Jaccard’s indexes that were obtained for each subgroup of OCT-A healthy images.

More »

Table 8 Expand

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.

More »

Table 9 Expand

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].

More »

Table 10 Expand