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

Table 1.

Summary of limitations in traditional vs. deep learning-based segmentation methods.

More »

Table 1 Expand

Table 2.

Performance analysis of different edge preserving filters.

More »

Table 2 Expand

Table 3.

Comparison between AGF and OAGF in practical deployment terms.

More »

Table 3 Expand

Fig 1.

Block diagram of retinal image segmentation and enhancement using proposed OAGF.

More »

Fig 1 Expand

Fig 2.

Retinal image segmentation across six test cases using proposed OAGF.

More »

Fig 2 Expand

Fig 3.

Subjective assessment of existing and proposed OAGF based segmentation approaches.

More »

Fig 3 Expand

Table 4.

Quantitative analysis of proposed and existing methods for DRIVE and STARE datasets.

More »

Table 4 Expand

Table 5.

Statistical significance test analysis.

More »

Table 5 Expand

Fig 4.

Metrics Evaluation with DRIVE and STARE Datasets.

More »

Fig 4 Expand

Fig 5.

Visual failure case comparison.

Red box shows zoomed region where thin vessels are either missed or disconnected in the proposed method due to low contrast and anatomical ambiguity.

More »

Fig 5 Expand

Table 6.

Ablation Study and Component-Level Analysis.

More »

Table 6 Expand

Fig 6.

Sensitivity analysis of OAGF to key hyperparameters.

More »

Fig 6 Expand

Fig 7.

Subjective assessment of existing and proposed OAGF based enhancement.

More »

Fig 7 Expand

Table 7.

Comparison of existing and proposed OAGF techniques through objective assessment.

More »

Table 7 Expand

Table 8.

Comparison of existing and proposed OAGF techniques through objective assessment.

More »

Table 8 Expand