Topology Repairing of Disconnected Pulmonary Airways and Vessels: Baselines and a Dataset
This work addresses a critical problem for medical imaging in pulmonary disease diagnosis and treatment, though it is incremental as it builds on existing segmentation methods.
The paper tackles the disconnectivity issue in deep learning-based segmentation of pulmonary airways and vessels by proposing a post-processing approach that formulates topology repair as a keypoint detection task, achieving improved connectivity in tubular structures.
Accurate segmentation of pulmonary airways and vessels is crucial for the diagnosis and treatment of pulmonary diseases. However, current deep learning approaches suffer from disconnectivity issues that hinder their clinical usefulness. To address this challenge, we propose a post-processing approach that leverages a data-driven method to repair the topology of disconnected pulmonary tubular structures. Our approach formulates the problem as a keypoint detection task, where a neural network is trained to predict keypoints that can bridge disconnected components. We use a training data synthesis pipeline that generates disconnected data from complete pulmonary structures. Moreover, the new Pulmonary Tree Repairing (PTR) dataset is publicly available, which comprises 800 complete 3D models of pulmonary airways, arteries, and veins, as well as the synthetic disconnected data. Our code and data are available at https://github.com/M3DV/pulmonary-tree-repairing.