Scholarlink

<p>The development of robust algorithms for lung and lobe segmentation is essential for diagnosing and monitoring pulmonary diseases. Obtaining manual or automatic annotations is challenging, especially in patients with severe abnormalities due to poorly visible lobar fissures. We present LobePrior, an automated lung lobe segmentation method combining deep neural networks and probabilistic models. Segmentation occurs in three stages: a coarse stage processing downsampled images, a high-resolution stage where specialized AttUNets segment each lobe, and a final post-processing stage. Probabilistic models derived from label fusion guide the network in regions with severe abnormalities, and synthetic lesion generation provides augmentation during training. Performance was evaluated on LOLA11 and three additional datasets with cancerous nodules or COVID-19 consolidations. LobePrior achieved accurate segmentations compared to manual ground truth, reaching state-of-the-art performance even in challenging cases. On the LOCCA dataset, it obtained a Dice score of 0.966, with similar improvements on a COVID-19 CT dataset (Dice 0.978). Statistically significant improvements over competing methods were observed across all datasets. These results demonstrate that LobePrior effectively integrates anatomical priors and deep learning to provide reliable lobe segmentation in the presence of severe pulmonary abnormalities.</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

LobePrior segments lung lobes on computed tomography images in the presence of severe abnormalities

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月10日

查看全文
  • Jean Antonio Ribeiro,
  • Diedre Santos do Carmo,
  • Fabiano Reis,
  • Ricardo Siufi Magalhães,
  • Sergio San Juan Dertkigil,
  • Simone Appenzeller,
  • Letícia Rittner

摘要

The development of robust algorithms for lung and lobe segmentation is essential for diagnosing and monitoring pulmonary diseases. Obtaining manual or automatic annotations is challenging, especially in patients with severe abnormalities due to poorly visible lobar fissures. We present LobePrior, an automated lung lobe segmentation method combining deep neural networks and probabilistic models. Segmentation occurs in three stages: a coarse stage processing downsampled images, a high-resolution stage where specialized AttUNets segment each lobe, and a final post-processing stage. Probabilistic models derived from label fusion guide the network in regions with severe abnormalities, and synthetic lesion generation provides augmentation during training. Performance was evaluated on LOLA11 and three additional datasets with cancerous nodules or COVID-19 consolidations. LobePrior achieved accurate segmentations compared to manual ground truth, reaching state-of-the-art performance even in challenging cases. On the LOCCA dataset, it obtained a Dice score of 0.966, with similar improvements on a COVID-19 CT dataset (Dice 0.978). Statistically significant improvements over competing methods were observed across all datasets. These results demonstrate that LobePrior effectively integrates anatomical priors and deep learning to provide reliable lobe segmentation in the presence of severe pulmonary abnormalities.