Research on blood vessel section video segmentation based on tree centroid
The position of the seed could be outside of blood vessel due to the concave shape of the blood vessel section, which lead to wrong segmentation result. To solve the aboveissue, a seed selection algorithm based on minimum spanning tree was proposed in this paper. Firstly, random points wereselected...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Academic Journals Center of Shanghai Normal University
2021-08-01
|
Series: | Journal of Shanghai Normal University (Natural Sciences) |
Subjects: | |
Online Access: | http://qktg.shnu.edu.cn/zrb/shsfqkszrb/ch/reader/view_abstract.aspx?file_no=20210404 |
id |
doaj-3e9b012856344a3ea629df86d3efb732 |
---|---|
record_format |
Article |
spelling |
doaj-3e9b012856344a3ea629df86d3efb7322021-09-04T01:28:27ZengAcademic Journals Center of Shanghai Normal UniversityJournal of Shanghai Normal University (Natural Sciences)1000-51372021-08-0150441341710.3969/J.ISSN.1000-5137.2021.04.00420210404Research on blood vessel section video segmentation based on tree centroidWANG Xiaohan0PENG Boxing1GUO Huinan2ZHAO Xinyue3MA Yan4College of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai 200234, ChinaCollege of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai 200234, ChinaCollege of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai 200234, ChinaCollege of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai 200234, ChinaCollege of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai 200234, ChinaThe position of the seed could be outside of blood vessel due to the concave shape of the blood vessel section, which lead to wrong segmentation result. To solve the aboveissue, a seed selection algorithm based on minimum spanning tree was proposed in this paper. Firstly, random points wereselected from the segmentation results of previous framewhich were uniformly distributed in the entire segmentation region. Secondly, Kruskal algorithm was used to construct the minimum spanning tree for all random points, and the tree centroid was taken as the seed of the current frame. Finally, the current frame was segmented with region growing algorithm. The experimental results showed that by this algorithm the center point of the cross-section of blood vesselscould be accurately located and the accuracy of vessel segmentation could be ensured.http://qktg.shnu.edu.cn/zrb/shsfqkszrb/ch/reader/view_abstract.aspx?file_no=20210404minimum spanning treeconcave shaperegion growingblood vessel segmentationimage segmentation |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
WANG Xiaohan PENG Boxing GUO Huinan ZHAO Xinyue MA Yan |
spellingShingle |
WANG Xiaohan PENG Boxing GUO Huinan ZHAO Xinyue MA Yan Research on blood vessel section video segmentation based on tree centroid Journal of Shanghai Normal University (Natural Sciences) minimum spanning tree concave shape region growing blood vessel segmentation image segmentation |
author_facet |
WANG Xiaohan PENG Boxing GUO Huinan ZHAO Xinyue MA Yan |
author_sort |
WANG Xiaohan |
title |
Research on blood vessel section video segmentation based on tree centroid |
title_short |
Research on blood vessel section video segmentation based on tree centroid |
title_full |
Research on blood vessel section video segmentation based on tree centroid |
title_fullStr |
Research on blood vessel section video segmentation based on tree centroid |
title_full_unstemmed |
Research on blood vessel section video segmentation based on tree centroid |
title_sort |
research on blood vessel section video segmentation based on tree centroid |
publisher |
Academic Journals Center of Shanghai Normal University |
series |
Journal of Shanghai Normal University (Natural Sciences) |
issn |
1000-5137 |
publishDate |
2021-08-01 |
description |
The position of the seed could be outside of blood vessel due to the concave shape of the blood vessel section, which lead to wrong segmentation result. To solve the aboveissue, a seed selection algorithm based on minimum spanning tree was proposed in this paper. Firstly, random points wereselected from the segmentation results of previous framewhich were uniformly distributed in the entire segmentation region. Secondly, Kruskal algorithm was used to construct the minimum spanning tree for all random points, and the tree centroid was taken as the seed of the current frame. Finally, the current frame was segmented with region growing algorithm. The experimental results showed that by this algorithm the center point of the cross-section of blood vesselscould be accurately located and the accuracy of vessel segmentation could be ensured. |
topic |
minimum spanning tree concave shape region growing blood vessel segmentation image segmentation |
url |
http://qktg.shnu.edu.cn/zrb/shsfqkszrb/ch/reader/view_abstract.aspx?file_no=20210404 |
work_keys_str_mv |
AT wangxiaohan researchonbloodvesselsectionvideosegmentationbasedontreecentroid AT pengboxing researchonbloodvesselsectionvideosegmentationbasedontreecentroid AT guohuinan researchonbloodvesselsectionvideosegmentationbasedontreecentroid AT zhaoxinyue researchonbloodvesselsectionvideosegmentationbasedontreecentroid AT mayan researchonbloodvesselsectionvideosegmentationbasedontreecentroid |
_version_ |
1717815567752101888 |