Wenjun Tan
ABSTRACT
This article presents a combined algorithm of pulmonary artery-vein (A/V) separation considering both global and local information, including: the transformation of geometric graph, sub-tree separation, and A/V classification. During the process, geometric graphs are firstly built based on the centerlines; A separation of the adhesion points is performed by applying the information stored in the data structure of the nodes and links in the geometric graphs; Sub-trees are then combined according to the local and global information; The combined sub-trees are growing into vascular trees using 2D area growth method; And finally, classification of the arterial and venous vascular trees based on the knowledge of anatomy. An average accuracy of 85% has been achieved of the overall process with a processing time range between 40 s to 50 s, which indicates good performance and stability of this algorithm.
- Fabijańska, Anna. Segmentation of pulmonary vascular tree from 3D CT thorax scans[J]. Biocybernetics & Biomedical Engineering, 2015, 35(2):106-119.Google Scholar
Cross Ref
- Nakamura, S. & Mekada, Y. & Ide, Ichiro & Murase, H. & Hasegawa, J. & Toriwaki, J. & Otsuji, H. Pulmonary artery and vein classification method using spatial arrangement features from X-ray CT image. International Congress Series. 2005, 1281. 1403-1403.Google ScholarCross Ref
- Saha P K, Gao Z, Alford S K, Topomorphologic Separation of Fused Isointensity Objects via Multiscale Opening: Separating Arteries and Veins in 3-D Pulmonary CT[J]. IEEE Transactions on Medical Imaging, 2010, 29(3): 840-851.Google ScholarCross Ref
- Park S, Lee S M, Kim N, Automatic reconstruction of the arterial and venous trees on volumetric chest CT[J]. Medical Physics, 2013, 40(7).Google Scholar
- Kitamura Y, Li Y, Ito W, Data-Dependent Higher-Order Clique Selection for Artery—Vein Segmentation by Energy Minimization[J]. International Journal of Computer Vision, 2016, 117(2): 142-158.Google ScholarDigital Library
- Nardelli P, Jimenezcarretero D, Bermejopelaez D, Pulmonary Artery–Vein Classification in CT Images Using Deep Learning[J]. IEEE Transactions on Medical Imaging, 2018, 37(11): 2428-2440.Google ScholarCross Ref
- Charbonnier J, Brink M, Ciompi F, Automatic Pulmonary Artery-Vein Separation and Classification in Computed Tomography Using Tree Partitioning and Peripheral Vessel Matching[J]. IEEE Transactions on Medical Imaging, 2016, 35(3): 882-892.Google ScholarCross Ref
Recommendations
Learning multi-view and centerline topology connectivity information for pulmonary artery–vein separation
Abstract Background:Automatic pulmonary artery–vein separation has considerable importance in the diagnosis and treatment of lung diseases. However, insufficient connectivity and spatial inconsistency have always been the problems of artery–vein ...
Highlights- A novel multi-scale information aggregated network is proposed for pulmonary artery–vein separation.
- A novel centerline correction algorithm is proposed for insufficient connectivity and spatial inconsistency.
- One new pulmonary ...
Retinal artery-vein caliber grading using color fundus imaging
Recent research suggests that retinal vessel caliber (or cross-sectional width) measured from retinal photographs is an important feature for predicting cardiovascular diseases (CVDs). One of the most utilized measures is to quantify retinal arteriolar ...
Comments