2023
DOI: 10.1016/j.engappai.2023.106069
|View full text |Cite
|
Sign up to set email alerts
|

Extraction of vascular wall in carotid ultrasound via a novel boundary-delineation network

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
6

Relationship

0
6

Authors

Journals

citations
Cited by 25 publications
(2 citation statements)
references
References 31 publications
0
2
0
Order By: Relevance
“…To solve problems such as category imbalance and boundary ambiguity, some researchers have developed corresponding modules. Considering the inaccurate location of vascular wall boundaries and segmentation errors occurring in discontinuous vascular walls and dark boundaries, Huang et al [17] proposed a new boundary delineation network (BDNet). First, the rough prediction is made based on the feature downsampling process and multi-scale feature fusion module, and then the PointHead boundary refinement module is used to realize the accurate location of the boundary points.…”
Section: Segmentation Of the Imc In Longitudinal Ultrasoundmentioning
confidence: 99%
“…To solve problems such as category imbalance and boundary ambiguity, some researchers have developed corresponding modules. Considering the inaccurate location of vascular wall boundaries and segmentation errors occurring in discontinuous vascular walls and dark boundaries, Huang et al [17] proposed a new boundary delineation network (BDNet). First, the rough prediction is made based on the feature downsampling process and multi-scale feature fusion module, and then the PointHead boundary refinement module is used to realize the accurate location of the boundary points.…”
Section: Segmentation Of the Imc In Longitudinal Ultrasoundmentioning
confidence: 99%
“…A multilevel attention module is added to the U‐Net for retinal vessel segmentation; this module utilizes attention mechanisms at multiple levels to improve segmentation performance [10], and the experimental results on a public dataset demonstrate the effectiveness of the proposed method compared with existing methods. Huang et al [11] identified the issue of imprecise localization of blood vessel wall boundaries and introduced a novel boundary depiction network to represent the connection between pixels based on global and neighborhood characteristics using the structural features of blood vessel walls to assist the model in extracting crucial structured data.…”
Section: Introductionmentioning
confidence: 99%