Segmentation of Pulmonary Vascular Trees from Thoracic 3D CT Images
This paper describes an algorithm for extracting pulmonary vascular trees (arteries plus veins) from three-dimensional (3D) thoracic computed tomographic (CT) images. The algorithm integrates tube enhancement filter and traversal approaches which are based on eigenvalues and eigenvectors of a Hessia...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2009-01-01
|
| Series: | International Journal of Biomedical Imaging |
| Online Access: | http://dx.doi.org/10.1155/2009/636240 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832562665027796992 |
|---|---|
| author | Hidenori Shikata Geoffrey McLennan Eric A. Hoffman Milan Sonka |
| author_facet | Hidenori Shikata Geoffrey McLennan Eric A. Hoffman Milan Sonka |
| author_sort | Hidenori Shikata |
| collection | DOAJ |
| description | This paper describes an algorithm for extracting pulmonary vascular trees (arteries plus veins) from
three-dimensional (3D) thoracic computed tomographic (CT) images. The algorithm integrates tube
enhancement filter and traversal approaches which are based on eigenvalues and eigenvectors of a
Hessian matrix to extract thin peripheral segments as well as thick vessels close to the lung hilum.
The resultant algorithm was applied to a simulation data set and 44 scans from 22 human subjects
imaged via multidetector-row CT (MDCT) during breath holds at 85% and 20% of their vital capacity.
A quantitative validation was performed with more than 1000 manually identified points selected from
inside the vessel segments to assess true positives (TPs) and 1000 points randomly placed outside
of the vessels to evaluate false positives (FPs) in each case. On average, for both the high and low
volume lung images, 99% of the points was properly marked as vessel and 1% of the points were
assessed as FPs. Our hybrid segmentation algorithm provides a highly reliable method of segmenting
the combined pulmonary venous and arterial trees which in turn will serve as a critical starting point
for further quantitative analysis tasks and aid in our overall goal of establishing a normative atlas of the
human lung. |
| format | Article |
| id | doaj-art-3ac24ff727044d838a06fe08d8ec3e25 |
| institution | Kabale University |
| issn | 1687-4188 1687-4196 |
| language | English |
| publishDate | 2009-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Biomedical Imaging |
| spelling | doaj-art-3ac24ff727044d838a06fe08d8ec3e252025-02-03T01:22:02ZengWileyInternational Journal of Biomedical Imaging1687-41881687-41962009-01-01200910.1155/2009/636240636240Segmentation of Pulmonary Vascular Trees from Thoracic 3D CT ImagesHidenori Shikata0Geoffrey McLennan1Eric A. Hoffman2Milan Sonka3Iowa Institute for Biomedical Imaging, The University of Iowa, Iowa City, IA 52242, USAIowa Institute for Biomedical Imaging, The University of Iowa, Iowa City, IA 52242, USAIowa Institute for Biomedical Imaging, The University of Iowa, Iowa City, IA 52242, USAIowa Institute for Biomedical Imaging, The University of Iowa, Iowa City, IA 52242, USAThis paper describes an algorithm for extracting pulmonary vascular trees (arteries plus veins) from three-dimensional (3D) thoracic computed tomographic (CT) images. The algorithm integrates tube enhancement filter and traversal approaches which are based on eigenvalues and eigenvectors of a Hessian matrix to extract thin peripheral segments as well as thick vessels close to the lung hilum. The resultant algorithm was applied to a simulation data set and 44 scans from 22 human subjects imaged via multidetector-row CT (MDCT) during breath holds at 85% and 20% of their vital capacity. A quantitative validation was performed with more than 1000 manually identified points selected from inside the vessel segments to assess true positives (TPs) and 1000 points randomly placed outside of the vessels to evaluate false positives (FPs) in each case. On average, for both the high and low volume lung images, 99% of the points was properly marked as vessel and 1% of the points were assessed as FPs. Our hybrid segmentation algorithm provides a highly reliable method of segmenting the combined pulmonary venous and arterial trees which in turn will serve as a critical starting point for further quantitative analysis tasks and aid in our overall goal of establishing a normative atlas of the human lung.http://dx.doi.org/10.1155/2009/636240 |
| spellingShingle | Hidenori Shikata Geoffrey McLennan Eric A. Hoffman Milan Sonka Segmentation of Pulmonary Vascular Trees from Thoracic 3D CT Images International Journal of Biomedical Imaging |
| title | Segmentation of Pulmonary Vascular Trees from Thoracic 3D CT Images |
| title_full | Segmentation of Pulmonary Vascular Trees from Thoracic 3D CT Images |
| title_fullStr | Segmentation of Pulmonary Vascular Trees from Thoracic 3D CT Images |
| title_full_unstemmed | Segmentation of Pulmonary Vascular Trees from Thoracic 3D CT Images |
| title_short | Segmentation of Pulmonary Vascular Trees from Thoracic 3D CT Images |
| title_sort | segmentation of pulmonary vascular trees from thoracic 3d ct images |
| url | http://dx.doi.org/10.1155/2009/636240 |
| work_keys_str_mv | AT hidenorishikata segmentationofpulmonaryvasculartreesfromthoracic3dctimages AT geoffreymclennan segmentationofpulmonaryvasculartreesfromthoracic3dctimages AT ericahoffman segmentationofpulmonaryvasculartreesfromthoracic3dctimages AT milansonka segmentationofpulmonaryvasculartreesfromthoracic3dctimages |