Scholarlink

The development of efficient and robust algorithms for segmenting the lung and its lobes is useful for the diagnosis and monitoring of lung diseases that cause lung abnormalities, such as pneumonia caused by COVID-19 and lung cancer. The amount of available manual annotations of the lobes in patients with severe lung abnormalities such as consolidations and ground glass opacities is scarce, due to the difficulty of visualization of the lobar fissures. This work aims to develop a method for automated segmentation of lung lobes using deep neural networks in computed tomography images of the lungs of patients with severe abnormalities, named LobePrior. LobePrior is based on probabilistic models (probabilistic templates) built from label fusion, used not only to guide the deep neural networks while learning to segment the lobes but also for postprocessing the network prediction to obtain the final segmentation. Segmentation is performed in two stages: a coarse stage working on downsampled images and a second high-resolution stage, where specialized AttUNets compete for each lobe’s segmentation. Probabilistic models are used to correct the automated labels in places where severe abnormalities caused holes in the segmentation. The performance of the proposed approach was assessed using two public datasets with lobe annotations, in the presence of cancer nodules and COVID-19 consolidations. Open source implementation is available at https://github.com/MICLab-Unicamp/LobePrior .

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

Deep Learning with Probabilistic Models for Segmenting Lung Lobes on Computed Tomography Images with Severe Abnormalities

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Jean Antonio Ribeiro,
  • Diedre Santos do Carmo,
  • Fabiano Reis,
  • Leticia Rittner

摘要

The development of efficient and robust algorithms for segmenting the lung and its lobes is useful for the diagnosis and monitoring of lung diseases that cause lung abnormalities, such as pneumonia caused by COVID-19 and lung cancer. The amount of available manual annotations of the lobes in patients with severe lung abnormalities such as consolidations and ground glass opacities is scarce, due to the difficulty of visualization of the lobar fissures. This work aims to develop a method for automated segmentation of lung lobes using deep neural networks in computed tomography images of the lungs of patients with severe abnormalities, named LobePrior. LobePrior is based on probabilistic models (probabilistic templates) built from label fusion, used not only to guide the deep neural networks while learning to segment the lobes but also for postprocessing the network prediction to obtain the final segmentation. Segmentation is performed in two stages: a coarse stage working on downsampled images and a second high-resolution stage, where specialized AttUNets compete for each lobe’s segmentation. Probabilistic models are used to correct the automated labels in places where severe abnormalities caused holes in the segmentation. The performance of the proposed approach was assessed using two public datasets with lobe annotations, in the presence of cancer nodules and COVID-19 consolidations. Open source implementation is available at https://github.com/MICLab-Unicamp/LobePrior .