TY - GEN
T1 - V-GnNet
T2 - 13th International Conference on Health Information Science, HIS 2024
AU - Li, Qingya
AU - Yuan, Ye
AU - Liu, Lu
AU - Zhang, Ziming
AU - Tan, Wenjun
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.
PY - 2025
Y1 - 2025
N2 - In medical imaging, especially CT scanning, accurate classification of arteries and veins is crucial for diagnosis and treatment. Existing deep learning methods, although capable of capturing arterial and venous features, often process voxel points independently and lack a holistic understanding of vascular branch structures. This limitation results in misclassifications at branch points, especially in distal branches, necessitating post-processing for correction. Traditional post-processing algorithms, such as arterial and venous density calculations or graph cut methods, can correct short intrusions but are limited in addressing long intrusions or mixed intrusions, hindering the application in complex vascular networks. To address this issue, this paper proposes V-GnNet, a fusion learning method combining voxel-based predictions and graph structure node predictions. Firstly, V-GnNet employs an iterative 3D neural network based on the UNet architecture, IterUNet3D, for preliminary classification of vascular data. IterUNet3D enhances the classification performance of arteries and veins by enriching the network's multi-level feature inputs through iterative mini-UNet3D modules. Subsequently, a special graph structure is established by extracting the vascular skeleton, integrating priori knowledge into a feature matrix, and utilizing a Graph Attention Network (GAT) for node classification of the IterUNet3D results. Finally, a voting algorithm fuses the voxel prediction results and node prediction results, ensuring consistent branch classification in artery and vein separation, therefore addressing the challenges of branch misclassification. Experimental results demonstrate that V-GnNet significantly improves the accuracy and consistency of pulmonary artery and vein classification, effectively reducing branch misjudgments and mutual intrusions, which showcases its great potential in medical image processing.
AB - In medical imaging, especially CT scanning, accurate classification of arteries and veins is crucial for diagnosis and treatment. Existing deep learning methods, although capable of capturing arterial and venous features, often process voxel points independently and lack a holistic understanding of vascular branch structures. This limitation results in misclassifications at branch points, especially in distal branches, necessitating post-processing for correction. Traditional post-processing algorithms, such as arterial and venous density calculations or graph cut methods, can correct short intrusions but are limited in addressing long intrusions or mixed intrusions, hindering the application in complex vascular networks. To address this issue, this paper proposes V-GnNet, a fusion learning method combining voxel-based predictions and graph structure node predictions. Firstly, V-GnNet employs an iterative 3D neural network based on the UNet architecture, IterUNet3D, for preliminary classification of vascular data. IterUNet3D enhances the classification performance of arteries and veins by enriching the network's multi-level feature inputs through iterative mini-UNet3D modules. Subsequently, a special graph structure is established by extracting the vascular skeleton, integrating priori knowledge into a feature matrix, and utilizing a Graph Attention Network (GAT) for node classification of the IterUNet3D results. Finally, a voting algorithm fuses the voxel prediction results and node prediction results, ensuring consistent branch classification in artery and vein separation, therefore addressing the challenges of branch misclassification. Experimental results demonstrate that V-GnNet significantly improves the accuracy and consistency of pulmonary artery and vein classification, effectively reducing branch misjudgments and mutual intrusions, which showcases its great potential in medical image processing.
KW - Artery-Vein Classification
KW - CT
KW - Graph Structure Node Prediction
KW - Voxel Prediction
UR - http://www.scopus.com/inward/record.url?scp=105006658673&partnerID=8YFLogxK
U2 - 10.1007/978-981-96-5597-7_10
DO - 10.1007/978-981-96-5597-7_10
M3 - Conference contribution
AN - SCOPUS:105006658673
SN - 9789819655960
T3 - Lecture Notes in Computer Science
SP - 105
EP - 117
BT - Health Information Science - 13th International Conference, HIS 2024, Proceedings
A2 - Siuly, Siuly
A2 - Xing, Chunxiao
A2 - Li, Xiaofan
A2 - Zhou, Rui
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 8 December 2024 through 10 December 2024
ER -