用解剖引导的形状插入生成合成数据，实现胸部X光片异物实例分割
Foreign object segmentation in chest x-rays through anatomy-guided shape insertion
- 通过解剖约束插入任意形状生成合成数据
- 仅需93%更少的人工标注即达到全监督模型性能
- 适合医疗图像标注稀缺场景，尤其儿童异物检测
本文针对术后随访中常见的心脏支架、起搏器或儿童误吞异物等胸部放射影像中的异物实例分割问题展开研究。由于异物形态多样，现有数据集标注不足，难以支撑密集标注。为此，我们提出一种简单有效的合成数据生成方法：(1) 在图像中插入具有不同对比度和透明度的线段、多边形、椭圆等任意形状；(2) 从少量半自动提取的标签中进行剪切粘贴增强。所有插入操作均受解剖标签引导，确保如支架仅出现在对应血管区域，提升真实感。该方法使网络在极少人工标注下即可完成复杂结构分割，显著减少标注成本。实验表明，仅使用93%更少的人工标注，模型性能即可媲美全监督训练结果。
原文摘要 · Abstract (English)
In this paper, we tackle the challenge of instance segmentation for foreign objects in chest radiographs, commonly seen in postoperative follow-ups with stents, pacemakers, or ingested objects in children. The diversity of foreign objects complicates dense annotation, as shown in insufficient existing datasets. To address this, we propose the simple generation of synthetic data through (1) insertion of arbitrary shapes (lines, polygons, ellipses) with varying contrasts and opacities, and (2) cut-paste augmentations from a small set of semi-automatically extracted labels. These insertions are guided by anatomy labels to ensure realistic placements, such as stents appearing only in relevant vessels. Our approach enables networks to segment complex structures with minimal manually labeled data. Notably, it achieves performance comparable to fully supervised models while using 93\% fewer manual annotations.
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。