保持解剖连续性：三维腹部CT扫描中结肠分割的三阶段流水线
Preserving Anatomical Continuity: Three-Stage Pipeline for Colon Segmentation in 3D Abdominal CT Scans
浏览论文内容
中文总结 AI 辅助
针对深度学习结肠分割不连续问题，提出三阶段拓扑保持流水线，通过初始分割、中心线桥接和重建提升结构一致性，在TotalSegmentator和RAOS数据集上验证了有效性。
中文摘要 AI 辅助
从CT图像中进行准确的结肠分割对于结直肠疾病分析至关重要，然而基于深度学习的方法由于复杂的解剖结构常常产生不连续的预测。本研究引入了一个三阶段、拓扑保持的分割流水线来解决这一问题。第一阶段执行基于深度学习的初始分割，随后通过中心线桥接来重新连接不连续的区域，以及一个重建阶段来细化连续性。在TotalSegmentator和RAOS数据集上使用重叠、距离和基于拓扑的指标进行的评估表明，在保持分割精度的同时，结构一致性得到了改善。所提出的方法增强了拓扑完整性，使得结肠分割在临床和研究应用中更加可靠。
英文摘要
Accurate colon segmentation from CT images is essential for colorectal disease analysis, yet deep learning based methods often produce disconnected predictions due to complex anatomy. This study introduces a three-stage, topology-preserving segmentation pipeline to address this issue. The first stage performs initial deep learning-based segmentation, followed by centreline bridging to reconnect disjoint regions and a reconstruction stage to refine continuity. Evaluations on TotalSegmentator and RAOS datasets using overlap, distance and topology-based metrics demonstrate improved structural consistency while maintaining segmentation accuracy. The proposed method enhances topological integrity, enabling more reliable colon segmentation for clinical and research applications.
发表机构
- University of New South Wales（新南威尔士大学）
- Sydney Adventist Hospital（悉尼 Adventist 医院）
机构由 AI 辅助整理，请以论文原文为准。
