What Makes for Automatic Reconstruction of Pulmonary Segments
This work addresses a previously unexplored task in deep learning for medical imaging, specifically benefiting surgical planning in lung cancer treatment, though it appears incremental as it adapts existing implicit surface techniques to a new domain.
The paper tackles the problem of automatic 3D reconstruction of pulmonary segments for lung cancer surgery planning, proposing ImPulSe, a deep implicit surface model that achieves accurate results with continuous predictions at arbitrary resolutions, higher training efficiency, and fewer parameters compared to canonical segmentation methods.
3D reconstruction of pulmonary segments plays an important role in surgical treatment planning of lung cancer, which facilitates preservation of pulmonary function and helps ensure low recurrence rates. However, automatic reconstruction of pulmonary segments remains unexplored in the era of deep learning. In this paper, we investigate what makes for automatic reconstruction of pulmonary segments. First and foremost, we formulate, clinically and geometrically, the anatomical definitions of pulmonary segments, and propose evaluation metrics adhering to these definitions. Second, we propose ImPulSe (Implicit Pulmonary Segment), a deep implicit surface model designed for pulmonary segment reconstruction. The automatic reconstruction of pulmonary segments by ImPulSe is accurate in metrics and visually appealing. Compared with canonical segmentation methods, ImPulSe outputs continuous predictions of arbitrary resolutions with higher training efficiency and fewer parameters. Lastly, we experiment with different network inputs to analyze what matters in the task of pulmonary segment reconstruction. Our code is available at https://github.com/M3DV/ImPulSe.