Bronchovascular Tree-Guided Weakly Supervised Learning Method for Pulmonary Segment Segmentation

• URL: http://arxiv.org/abs/2505.13911v1
• Date: Tue, 20 May 2025 04:23:12 GMT
• Title: Bronchovascular Tree-Guided Weakly Supervised Learning Method for Pulmonary Segment Segmentation
• Authors: Ruijie Zhao, Zuopeng Tan, Xiao Xue, Longfei Zhao, Bing Li, Zicheng Liao, Ying Ming, Jiaru Wang, Ran Xiao, Sirong Piao, Rui Zhao, Qiqi Xu, Wei Song,
• Abstract summary: We propose a weakly supervised learning (WSL) method, termed Anatomy-Hierarchy Supervised Learning (AHSL)<n>WSL consults the precise clinical anatomical definition of pulmonary segments to perform pulmonary segment segmentation.<n>We introduce a two-stage segmentation strategy that incorporates bronchovascular priori information.
• Score: 10.281872642318957
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Pulmonary segment segmentation is crucial for cancer localization and surgical planning. However, the pixel-wise annotation of pulmonary segments is laborious, as the boundaries between segments are indistinguishable in medical images. To this end, we propose a weakly supervised learning (WSL) method, termed Anatomy-Hierarchy Supervised Learning (AHSL), which consults the precise clinical anatomical definition of pulmonary segments to perform pulmonary segment segmentation. Since pulmonary segments reside within the lobes and are determined by the bronchovascular tree, i.e., artery, airway and vein, the design of the loss function is founded on two principles. First, segment-level labels are utilized to directly supervise the output of the pulmonary segments, ensuring that they accurately encompass the appropriate bronchovascular tree. Second, lobe-level supervision indirectly oversees the pulmonary segment, ensuring their inclusion within the corresponding lobe. Besides, we introduce a two-stage segmentation strategy that incorporates bronchovascular priori information. Furthermore, a consistency loss is proposed to enhance the smoothness of segment boundaries, along with an evaluation metric designed to measure the smoothness of pulmonary segment boundaries. Visual inspection and evaluation metrics from experiments conducted on a private dataset demonstrate the effectiveness of our method.

Related papers

• Shape-aware synthesis of pathological lung CT scans using CycleGAN for enhanced semi-supervised lung segmentation [0.0]
  This paper emphasizes the use of CycleGAN for unpaired image-to-image translation. It provides an augmentation method able to generate fake pathological images matching an existing ground truth. Preliminary results from this research demonstrate significant qualitative and quantitative improvements.
  arXiv  Detail & Related papers  (2024-05-14T12:45:49Z)
• Semi- and Weakly-Supervised Learning for Mammogram Mass Segmentation with Limited Annotations [49.33388736227072]
  We propose a semi- and weakly-supervised learning framework for mass segmentation. We use limited strongly-labeled samples and sufficient weakly-labeled samples to achieve satisfactory performance. Experiments on CBIS-DDSM and INbreast datasets demonstrate the effectiveness of our method.
  arXiv  Detail & Related papers  (2024-03-14T12:05:25Z)
• BRONCO: Automated modelling of the bronchovascular bundle using the Computed Tomography Images [32.586316762855944]
  We propose a segmentation pipeline for the bronchovascular bundle based on Computed Tomography images. We tested our method on both low-dose CT and standard-dose CT, with various pathologies, reconstructed with various slice thicknesses, and acquired from various machines.
  arXiv  Detail & Related papers  (2023-09-18T00:38:25Z)
• What Makes for Automatic Reconstruction of Pulmonary Segments [50.216231776343115]
  3D reconstruction of pulmonary segments plays an important role in surgical treatment planning of lung cancer. However, automatic reconstruction of pulmonary segments remains unexplored in the era of deep learning. We propose ImPulSe, a deep implicit surface model designed for pulmonary segment reconstruction.
  arXiv  Detail & Related papers  (2022-07-07T04:24:17Z)
• BronchusNet: Region and Structure Prior Embedded Representation Learning for Bronchus Segmentation and Classification [53.53758990624962]
  We propose a region and structure prior embedded framework named BronchusNet to achieve accurate bronchial analysis. For bronchus segmentation, we propose an adaptive hard region-aware UNet that incorporates multi-level prior guidance of hard pixel-wise samples. For the classification of bronchial branches, we propose a hybrid point-voxel graph learning module.
  arXiv  Detail & Related papers  (2022-05-14T02:32:33Z)
• Improving Classification Model Performance on Chest X-Rays through Lung Segmentation [63.45024974079371]
  We propose a deep learning approach to enhance abnormal chest x-ray (CXR) identification performance through segmentations. Our approach is designed in a cascaded manner and incorporates two modules: a deep neural network with criss-cross attention modules (XLSor) for localizing lung region in CXR images and a CXR classification model with a backbone of a self-supervised momentum contrast (MoCo) model pre-trained on large-scale CXR data sets.
  arXiv  Detail & Related papers  (2022-02-22T15:24:06Z)
• Pulmonary Fissure Segmentation in CT Images Based on ODoS Filter and Shape Features [3.7006330637320897]
  We adopt an ODoS filter by merging the orientation information and magnitude information to highlight structure features for fissure enhancement. Considering the shape difference between pulmonary fissures and tubular structures in magnitude field, a shape measure approach and a 3D skeletonization model are combined to segment pulmonary fissures for clutters removal.
  arXiv  Detail & Related papers  (2022-01-23T02:43:03Z)
• CoRSAI: A System for Robust Interpretation of CT Scans of COVID-19 Patients Using Deep Learning [133.87426554801252]
  We adopted an approach based on using an ensemble of deep convolutionalneural networks for segmentation of lung CT scans. Using our models we are able to segment the lesions, evaluatepatients dynamics, estimate relative volume of lungs affected by lesions and evaluate the lung damage stage.
  arXiv  Detail & Related papers  (2021-05-25T12:06:55Z)
• Deep Residual 3D U-Net for Joint Segmentation and Texture Classification of Nodules in Lung [91.3755431537592]
  We present a method for lung nodules segmentation, their texture classification and subsequent follow-up recommendation from the CT image of lung. Our method consists of neural network model based on popular U-Net architecture family but modified for the joint nodule segmentation and its texture classification tasks and an ensemble-based model for the follow-up recommendation.
  arXiv  Detail & Related papers  (2020-06-25T07:20:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.