# CPR-GCN: Conditional Partial-Residual Graph Convolutional Network in Automated Anatomical Labeling of Coronary Arteries

arXiv: https://arxiv.org/abs/2003.08560 · HTML: https://mlsanity.com/paper/2003.08560/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Mar 2020.

## Built on by (most cited first, 16 of 16)

- [Mutual Graph Learning for Camouflaged Object Detection](https://mlsanity.com/paper/2104.02613/) (2021)
- [A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective](https://mlsanity.com/paper/2209.13232/) (2022)
- [NexToU: Efficient Topology-Aware U-Net for Medical Image Segmentation](https://mlsanity.com/paper/2305.15911/) (2023)
- [AGMN: Association Graph-based Graph Matching Network for Coronary Artery Semantic Labeling on Invasive Coronary Angiograms](https://mlsanity.com/paper/2301.04733/) (2023)
- [Residual Graph Convolutional Network for Bird's-Eye-View Semantic Segmentation](https://mlsanity.com/paper/2312.04044/) (2023)
- [Topology-Preserving Automatic Labeling of Coronary Arteries via Anatomy-aware Connection Classifier](https://mlsanity.com/paper/2307.11959/) (2023)
- [Coronary Artery Semantic Labeling using Edge Attention Graph Matching Network](https://mlsanity.com/paper/2305.12327/) (2023)
- [High-risk Factor Prediction in Lung Cancer Using Thin CT Scans: An Attention-Enhanced Graph Convolutional Network Approach](https://mlsanity.com/paper/2308.14000/) (2023)
- [Multi-graph Graph Matching for Coronary Artery Semantic Labeling](https://mlsanity.com/paper/2402.15894/) (2024)
- [LightVessel: Exploring Lightweight Coronary Artery Vessel Segmentation via Similarity Knowledge Distillation](https://mlsanity.com/paper/2211.00899/) (2022)
- [Automated Coronary Arteries Labeling Via Geometric Deep Learning](https://mlsanity.com/paper/2212.00386/) (2022)
- [O2CTA: Introducing Annotations from OCT to CCTA in Coronary Plaque Analysis](https://mlsanity.com/paper/2303.06358/) (2023)
- [Point Transformer For Coronary Artery Labeling](https://mlsanity.com/paper/2305.02533/) (2023)
- [A Novel Coronary Artery Registration Method Based on Super-pixel Particle Swarm Optimization](https://mlsanity.com/paper/2505.24351/) (2025)
- [LWT-ARTERY-LABEL: A Lightweight Framework for Automated Coronary Artery Identification](https://mlsanity.com/paper/2508.06874/) (2025)
- [ARIADNE: A Perception-Reasoning Synergy Framework for Trustworthy Coronary Angiography Analysis](https://mlsanity.com/paper/2603.19169/) (2026)

## Abstract (arXiv)

Automated anatomical labeling plays a vital role in coronary artery disease diagnosing procedure. The main challenge in this problem is the large individual variability inherited in human anatomy. Existing methods usually rely on the position information and the prior knowledge of the topology of the coronary artery tree, which may lead to unsatisfactory performance when the main branches are confusing. Motivated by the wide application of the graph neural network in structured data, in this paper, we propose a conditional partial-residual graph convolutional network (CPR-GCN), which takes both position and CT image into consideration, since CT image contains abundant information such as branch size and spanning direction. Two majority parts, a Partial-Residual GCN and a conditions extractor, are included in CPR-GCN. The conditions extractor is a hybrid model containing the 3D CNN and the LSTM, which can extract 3D spatial image features along the branches. On the technical side, the Partial-Residual GCN takes the position features of the branches, with the 3D spatial image features as conditions, to predict the label for each branches. While on the mathematical side, our approach twists the partial differential equation (PDE) into the graph modeling. A dataset with 511 subjects is collected from the clinic and annotated by two experts with a two-phase annotation process. According to the five-fold cross-validation, our CPR-GCN yields 95.8% meanRecall, 95.4% meanPrecision and 0.955 meanF1, which outperforms state-of-the-art approaches.