2016 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) 2016
DOI: 10.1109/bibm.2016.7822548
|View full text |Cite
|
Sign up to set email alerts
|

Construction of retinal vascular trees via curvature orientation prior

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2

Citation Types

0
2
0

Year Published

2022
2022
2023
2023

Publication Types

Select...
1
1

Relationship

0
2

Authors

Journals

citations
Cited by 2 publications
(2 citation statements)
references
References 29 publications
0
2
0
Order By: Relevance
“…Since we used the proposed SEGAN model [22] trained by six public dataset containing fundus images and only tested the model on our dataset, there were some discontinuities in the segmented blood vessels resulting from the proposed SEGAN model. To solve this problem, we used a post-processing step and took advantage of two useful algorithms, a region growing method and a missing algorithm [24], to fill discontinuous parts of the segmented blood vessels.…”
Section: Post Processingmentioning
confidence: 99%
See 1 more Smart Citation
“…Since we used the proposed SEGAN model [22] trained by six public dataset containing fundus images and only tested the model on our dataset, there were some discontinuities in the segmented blood vessels resulting from the proposed SEGAN model. To solve this problem, we used a post-processing step and took advantage of two useful algorithms, a region growing method and a missing algorithm [24], to fill discontinuous parts of the segmented blood vessels.…”
Section: Post Processingmentioning
confidence: 99%
“…Algorithm 1 states our proposed region growing approach in detail in which pi represent ith terminal point, S1 is a set of neighboring points satisfying a certain criterion that was explained above and finally PS1,i represent ith point in S1. In the next step, we used the missing algorithm proposed [24] to compensate for some small discontinuities left over from the first step. The proposed missing algorithm corrected the small disconnected segments in vessel segmentation by taking advantage of the vessel graph and determining the landmark points on it.…”
Section: Post Processingmentioning
confidence: 99%