Scholarlink

<p>Accurate delineation of pulmonary nodules in chest computed tomography (CT) is essential for early lung cancer diagnosis and treatment planning. However, voxel-wise segmentation methods often produce fragmented masks and inconsistent topology due to low contrast, anatomical variability, and imaging noise. We propose CoreFormer, a segmentation framework that models nodules through structural core anchoring and geodesic shape decoding. CoreFormer identifies the intrinsic topological core of each nodule and generates continuous boundaries guided by anatomy-aware geodesic paths. It is built upon a Swin Transformer backbone and a dual-branch decoder consisting of a Structural Core Predictor and a Context-Aware Shape Decoder, enhanced by Feature Manifold Regularization for discriminative feature learning. Extensive experiments on four public datasets-LIDC-IDRI, LNDb, Tianchi-Lung (MosMedData), and NSCLC-Radiomics-demonstrate that CoreFormer achieves state-of-the-art boundary accuracy and topological fidelity, offering robust and high-fidelity pulmonary nodule segmentation.</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

CoreFormer high fidelity pulmonary nodule segmentation with structural core priors and geodesic implicit fields

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月12日

查看全文
  • Yong Xi,
  • Chuan Xu,
  • Fan Ye,
  • Min Yuan,
  • Chunlin Ye,
  • Lei Jiang,
  • Yunhe Huang,
  • Jingtao Zhang,
  • Mengjie Liu,
  • Xiaoming Liu,
  • Bentong Yu

摘要

Accurate delineation of pulmonary nodules in chest computed tomography (CT) is essential for early lung cancer diagnosis and treatment planning. However, voxel-wise segmentation methods often produce fragmented masks and inconsistent topology due to low contrast, anatomical variability, and imaging noise. We propose CoreFormer, a segmentation framework that models nodules through structural core anchoring and geodesic shape decoding. CoreFormer identifies the intrinsic topological core of each nodule and generates continuous boundaries guided by anatomy-aware geodesic paths. It is built upon a Swin Transformer backbone and a dual-branch decoder consisting of a Structural Core Predictor and a Context-Aware Shape Decoder, enhanced by Feature Manifold Regularization for discriminative feature learning. Extensive experiments on four public datasets-LIDC-IDRI, LNDb, Tianchi-Lung (MosMedData), and NSCLC-Radiomics-demonstrate that CoreFormer achieves state-of-the-art boundary accuracy and topological fidelity, offering robust and high-fidelity pulmonary nodule segmentation.