Neovascularization Segmentation via a Multilateral Interaction-Enhanced Graph Convolutional Network
Open Access
- 1 December 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (12) , 11107-11123
Abstract
Choroidal neovascularization (CNV), a primary characteristic of wet age-related macular degeneration (wet AMD), represents a leading cause of blindness worldwide. In clinical practice, optical coherence tomography angiography (OCTA) is commonly used for studying CNV-related pathological changes, due to its micron-level resolution and non-invasive nature. Thus, accurate segmentation of CNV regions and vessels in OCTA images is crucial for clinical assessment of wet AMD. However, challenges existed due to irregular CNV shapes and imaging limitations like projection artifacts, noises and boundary blurring. Moreover, the lack of publicly available datasets constraints the CNV analysis. To address these challenges, this paper constructs the first publicly accessible CNV dataset (CNVSeg), and proposes a novel multilateral graph convolutional interaction-enhanced CNV segmentation network (MTG-Net). This network integrates both region and vessel morphological information, exploring semantic and geometric duality constraints within the graph domain. Specifically, MTG-Net consists of a multi-task framework and two graph-based cross-task modules: Multilateral Interaction Graph Reasoning (MIGR) and Multilateral Reinforcement Graph Reasoning (MRGR). The multi-task framework encodes rich geometric features of lesion shapes and surfaces, decoupling the image into three task-specific feature maps. MIGR and MRGR iteratively reason about higher-order relationships across tasks through a graph mechanism, enabling complementary optimization for task-specific objectives. Additionally, an uncertainty-weighted loss is proposed to mitigate the impact of artifacts and noise on segmentation accuracy. Experimental results demonstrate that MTG-Net outperforms existing methods, achieving a Dice socre of 87.21% for region segmentation and 88.12% for vessel segmentation.Keywords
Funding Information
- Zhejiang Provincial Natural Science Foundation (LR24F010002)
- National Natural Science Foundation Program of China (62371442)
- Ningbo Top Medical and Health Research Program (2023030716)
- Ningbo Natural Science Foundation (2023J209)
- Shandong Provincial Natural Science Foundation (ZR2022YQ64)
- French Government
- Agence Nationale de la Recherche as part of the ”Investissements d’avenir” program (ANR-19-P3IA-0001)
This publication has 47 references indexed in Scilit:
- RBGNet: Reliable Boundary-Guided Segmentation of Choroidal Neovascularization2023
- Swin-Unet: Unet-Like Pure Transformer for Medical Image Segmentation2023
- Class-Wise Dynamic Graph Convolution for Semantic Segmentation2020
- GINet: Graph Interaction Network for Scene Parsing2020
- Deep vessel segmentation by learning graphical connectivityMedical Image Analysis, 2019
- CS-Net: Channel and Spatial Attention Network for Curvilinear Structure Segmentation2019
- Automated segmentation of choroidal neovascularization in optical coherence tomography images using multi-scale convolutional neural networks with structure priorMultimedia Systems, 2018
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Choroidal neovascularizationAmerican Journal of Ophthalmology, 2004
- Fronts propagating with curvature-dependent speed: Algorithms based on Hamilton-Jacobi formulationsJournal of Computational Physics, 1988