Learning Dynamic Collaborative Network for Semi-Supervised 3D Vessel Segmentation

2025-06-10

Computer Vision and Pattern Recognition

AI Summary

This work addresses a critical limitation in conventional semi-supervised 3D vessel segmentation methods, where fixed teacher–student roles often introduce cognitive bias due to suboptimal teacher performance, thereby constraining segmentation accuracy. To overcome this, the authors propose DiCo, a dynamic collaborative network that, for the first time, incorporates a role-switching mechanism between teacher and student during training. DiCo further integrates a multi-view ensemble module to emulate clinical multi-angle diagnosis and employs adversarial supervision on 2D projections to mitigate label inconsistency across views. Extensive experiments demonstrate that DiCo achieves state-of-the-art performance on three benchmark 3D vessel segmentation datasets, significantly enhancing the utilization efficiency of unlabeled data.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multi-instance/Multi-view Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

In this paper, we present a new dynamic collaborative network for semi-supervised 3D vessel segmentation, termed DiCo. Conventional mean teacher (MT) methods typically employ a static approach, where the roles of the teacher and student models are fixed. However, due to the complexity of 3D vessel data, the teacher model may not always outperform the student model, leading to cognitive biases that can limit performance. To address this issue, we propose a dynamic collaborative network that allows the two models to dynamically switch their teacher-student roles. Additionally, we introduce a multi-view integration module to capture various perspectives of the inputs, mirroring the way doctors conduct medical analysis. We also incorporate adversarial supervision to constrain the shape of the segmented vessels in unlabeled data. In this process, the 3D volume is projected into 2D views to mitigate the impact of label inconsistencies. Experiments demonstrate that our DiCo method sets new state-of-the-art performance on three 3D vessel segmentation benchmarks. The code repository address is https://github.com/xujiaommcome/DiCo.

Problem

• semi-supervised learning
• 3D vessel segmentation
• dynamic collaboration
• cognitive bias
• mean teacher

Innovation

• dynamic collaborative network
• semi-supervised learning
• 3D vessel segmentation
• multi-view integration
• adversarial supervision