用递归精修方法生成更准的血管中心线，拓扑正确且参数更少。
RefTr: Recurrent Refinement of Confluent Trajectories for 3D Vascular Tree Centerlines
- 通过递归精修融合轨迹，端到端生成血管中心线。
- 精度提升，解码器参数减少2.4倍，推理更快。
- 适合临床血管分析，尤其关注拓扑完整性的场景。
管状树结构如血管和气道在临床诊断、治疗规划与手术导航中至关重要。准确提取具有正确拓扑的中心线是关键，因遗漏小分支可能导致评估不全或异常被忽略。本文提出RefTr，一种3D图像到图的框架，通过递归精修融合轨迹生成血管中心线。RefTr采用基于Transformer的生产者-精修者架构：生产者预测候选轨迹，共享精修器迭代优化以逼近目标分支。融合轨迹表示支持整支血管的精修，并显式保证拓扑有效性。该递归机制使精度提升，解码器参数减少2.4倍。此外，提出高效非极大值抑制算法处理空间树图以合并重复分支，并引入半径感知评估指标以实现稳健比较。在多个公开数据集上的实验表明，RefTr表现更优，推理更快，参数显著减少，充分验证其在3D血管树分析中的有效性。
原文摘要 · Abstract (English)
Tubular tree structures such as blood vessels and lung airways are central to many clinical tasks, including diagnosis, treatment planning, and surgical navigation. Accurate centerline extraction with correct topology is essential, as missing small branches can lead to incomplete assessments or overlooked abnormalities. We propose RefTr, a 3D image-to-graph framework that generates vascular centerlines via recurrent refinement of confluent trajectories. RefTr adopts a Transformer-based Producer-Refiner architecture in which the Producer predicts candidate trajectories and a shared Refiner iteratively refines them toward the target branches. The confluent trajectory representation enables whole-branch refinement while explicitly enforcing valid topology. This recurrent scheme improves precision and reduces decoder parameters by 2.4x compared to the state-of-the-art. We further introduce an efficient non-maximum suppression algorithm for spatial tree graphs to merge duplicate branches and extend evaluation metrics to be radius-aware for robust comparison. Experiments on multiple public datasets demonstrate stronger overall performance, faster inference, and substantially fewer parameters, highlighting the effectiveness of RefTr for 3D vascular tree analysis.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。