Adversarial Transformer for Repairing Human Airway Segmentation
This work addresses robust segmentation of distal small airways for lung disease diagnosis and prognosis, though it is incremental as it refines existing models rather than introducing a new paradigm.
The paper tackled the problem of discontinuity and missing bronchioles in automated airway segmentation from CT images, which limits clinical applications, by proposing a patch-scale adversarial refinement network that improved detected length and branch ratios by over 15% across datasets including healthy, cystic fibrosis, and COVID-19 cases.
Discontinuity in the delineation of peripheral bronchioles hinders the potential clinical application of automated airway segmentation models. Moreover, the deployment of such models is limited by the data heterogeneity across different centres, and pathological abnormalities also make achieving accurate robust segmentation in distal small airways difficult. Meanwhile, the diagnosis and prognosis of lung diseases often rely on evaluating structural changes in those anatomical regions. To address this gap, this paper presents a patch-scale adversarial-based refinement network that takes in preliminary segmentation along with original CT images and outputs a refined mask of the airway structure. The method is validated on three different datasets encompassing healthy cases, cases with cystic fibrosis and cases with COVID-19. The results are quantitatively evaluated by seven metrics and achieved more than a 15% rise in detected length ratio and detected branch ratio, showing promising performance compared to previously proposed models. The visual illustration also proves our refinement guided by a patch-scale discriminator and centreline objective functions is effective in detecting discontinuities and missing bronchioles. Furthermore, the generalizability of our refinement pipeline is tested on three previous models and improves their segmentation completeness significantly.