Scholarlink

<p>Volumetric segmentation is a major challenge in medical imaging, as current methods require extensive annotations and retraining, limiting transferability across objects. We present PAM, a propagation-based framework that generates 3D segmentations from a minimal 2D prompt. PAM integrates a CNN-based UNet for intra-slice features with Transformer attention for inter-slice propagation, capturing structural and semantic continuity to enable robust cross-object generalization. Across 44 diverse datasets, PAM outperformed MedSAM and SegVol, improving average DSC by 19.3%. It maintained stable performance under variations in prompts (<i>P</i> ≥ 0.5985) and propagation settings (<i>P</i> ≥ 0.6131), while achieving faster inference (<i>P</i> &lt; 0.001) and reducing user interaction time by 63.6%. Gains were strongest for irregular objects, with improvements negatively correlated with object regularity (<i>r</i> &lt; -0.1249). By delivering accurate 3D segmentations from minimal input, PAM lowers reliance on manual annotation and task-specific training, providing an efficient and generalizable tool for automated clinical imaging.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

PAM: a propagation-based model for segmenting any 3D objects across multi-modal medical images

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月2日

查看全文
  • Zifan Chen,
  • Xinyu Nan,
  • Jiazheng Li,
  • Jie Zhao,
  • Haifeng Li,
  • Ziling Lin,
  • Haoshen Li,
  • Heyun Chen,
  • Yiting Liu,
  • Lei Tang,
  • Li Zhang,
  • Bin Dong

摘要

Volumetric segmentation is a major challenge in medical imaging, as current methods require extensive annotations and retraining, limiting transferability across objects. We present PAM, a propagation-based framework that generates 3D segmentations from a minimal 2D prompt. PAM integrates a CNN-based UNet for intra-slice features with Transformer attention for inter-slice propagation, capturing structural and semantic continuity to enable robust cross-object generalization. Across 44 diverse datasets, PAM outperformed MedSAM and SegVol, improving average DSC by 19.3%. It maintained stable performance under variations in prompts (P ≥ 0.5985) and propagation settings (P ≥ 0.6131), while achieving faster inference (P < 0.001) and reducing user interaction time by 63.6%. Gains were strongest for irregular objects, with improvements negatively correlated with object regularity (r < -0.1249). By delivering accurate 3D segmentations from minimal input, PAM lowers reliance on manual annotation and task-specific training, providing an efficient and generalizable tool for automated clinical imaging.