Papers › Linking convolutional neural networks with graph convolutional networks: application...

Linking convolutional neural networks with graph convolutional networks: application in pulmonary artery-vein separation

1 Sep 2019Preprint 2019 9archive 2025-07-28

Zhiwei Zhai, Marius Staring, Xuhui Zhou, Qiuxia Xie, Xiaojuan Xiao, M. Els Bakker, Lucia J. Kroft, Boudewijn P. F. Lelieveldt, Gudula J.A.M. Boon, Frederikus A. Klok, Berend C. Stoel

Graph Convolutional Networks (GCNs) are a novel and powerful method for dealing with non-Euclidean data, while Convolutional Neural Networks (CNNs) can learn features from Euclidean data such as images. In this work, we propose a novel method to combine CNNs with GCNs (CNN-GCN), that can consider both Euclidean and non-Euclidean features and can be trained end-to-end. We applied this method to separate the pulmonary vascular trees into arteries and veins (A/V). Chest CT scans were pre-processed by vessel segmentation and skeletonization, from which a graph was constructed: voxels on the skeletons resulting in a vertex set and their connections in an adjacency matrix. 3D patches centered around each vertex were extracted from the CT scans, oriented perpendicularly to the vessel. The proposed CNN-GCN classifier was trained and applied on the constructed vessel graphs, where each node is then labeled as artery or vein. The proposed method was trained and validated on data from one hospital (11 patient, 22 lungs), and tested on independent data from a different hospital (10 patients, 10 lungs). A baseline CNN method and human observer performance were used for comparison. The CNN-GCN method obtained a median accuracy of 0.773 (0.738) in the validation (test) set, compared to a median accuracy of 0.817 by the observers, and 0.727 (0.693) by the CNN. In conclusion, the proposed CNN-GCN method combines local image information with graph connectivity information, improving pulmonary A/V separation over a baseline CNN method, approaching the performance of human observers.

PaperPDFCode

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Medical Imaging SegmentationMedical Image SegmentationPulmonary Artery–Vein ClassificationPulmorary Vessel Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Pulmonary Artery–Vein Classification LUMC CNN-GCNt Accuracy (median) 0.738 #1 of 3 Archive leaderboard report
Pulmonary Artery–Vein Classification LUMC CNN-GCN Accuracy (median) 0.723 #2 of 3 Archive leaderboard report
Pulmonary Artery–Vein Classification SunYs CNN-GCNt Accuracy (median) 0.778 #1 of 3 Archive leaderboard report
Pulmonary Artery–Vein Classification SunYs CNN-GCN Accuracy (median) 0.764 #2 of 3 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections