Vessel Bend-Based Cup Segmentation in Retinal Images
read more
Citations
Optic Disk and Cup Segmentation From Monocular Color Retinal Images for Glaucoma Assessment
Automated segmentation of optic disc and optic cup in fundus images for glaucoma diagnosis
A survey on computer aided diagnosis for ocular diseases
Depth Discontinuity-Based Cup Segmentation From Multiview Color Retinal Images
Automatic Optic Disk and Cup Segmentation of Fundus Images Using Deep Learning
References
Active contours without edges
Optic disk feature extraction via modified deformable model technique for glaucoma analysis
Automated detection of kinks from blood vessels for optic cup segmentation in retinal images
Unsupervised curvature-based retinal vessel segmentation
ARGALI: an automatic cup-to-disc ratio measurement system for glaucoma detection and AnaLysIs framework
Related Papers (5)
Optic disk feature extraction via modified deformable model technique for glaucoma analysis
The number of people with glaucoma worldwide in 2010 and 2020
Frequently Asked Questions (15)
Q2. What have the authors stated for future works in "Vessel bend-based cup segmentation in retinal images" ?
This signals the ambiguity in 2D information and the importance of 3D information in cup segmentation which will be investigated in their future work.
Q3. What is the way to determine the size of the ROS?
Choosing the bounds to be based on curvature minima automatically ensures the size of the ROS to be large for thick vessels and small for thin vessels.
Q4. What is the way to get the cup boundary?
If multiple bends remain, then the bend with smaller value of theta θ is selected as thin, rather than thick, vessel bends are more reliable indicators for the cup boundary.
Q5. What is the method used to obtain the cup boundary?
vessel bends, characterized by points of direction change in the vessel pixels are found and usedto obtain the cup boundary.
Q6. What is the definition of a low contrast vessel?
For the robust detection of low contrast vessels, the authors employ a two-phase thresholding scheme in which first, a high value of t is applied to get high contrast vessel points (set-1).
Q7. What is the minimum error function for r-bends?
The minimisation of error function S = ∑ i((xi − x̄)− xc) 2 + ((yi − ȳ)− yc) 2 −R2 gives the unknown parameters xc, yc and R, where, x̄ = 1n ∑ i xi, ȳ = 1 n ∑ i yi and n number of points.
Q8. What are the results of the analysis?
Trench based vessel modeling and ROS-based bend detection that have been employed result in robustness to varying thickness of the vessels.
Q9. What is the definition of a OD space?
The selection of this space gives robustness to the image variations and detection is solely driven by trench shape and directional continuity associated with a vessel structure.
Q10. What is the definition of a trench?
A point is declared as a trench if value of Υmax is greater than both threshold value t and the values of neighboring pixels in α direction.
Q11. What is the final set of r-bends?
A sector is radially analysed with a step size of 20◦ and in each step, only bends formed by vessels with the ′correct′ orientation are retained.
Q12. How is the region containing potential r-bends located?
The region containing potential r-bends is localised by finding a best-fit circle (in least-square sense) to the set of points (x, y) = {p, b}.
Q13. What is the task of identifying r-bends from bi?
The task of identifying the r-bends from bi is performed in two stages, to reduce the required analysis, by utilizing anatomical knowledge associated with r-bends.
Q14. What is the average precision of the CDR measure?
An area (pixel) overlap-based method was used to compute the precision(P)-recall(R) measures to assess the cup segmentation in each of the 4 sectors.
Q15. What are the local maxima of a vessel?
These local maxima constitute a candidate set of bends b. A ROS for any bi is defined as a segment of vessel around bi and bound on either side by the nearest curvature minimum.