RibSeg Dataset and Strong Point Cloud Baselines for Rib Segmentation from CT Scans
This work addresses the need for efficient and accurate rib segmentation in medical imaging, which is critical for clinical applications like rib measurement and visualization, but it is incremental as it builds on existing morphology-based algorithms and focuses on a specific domain.
The authors tackled the problem of labor-intensive manual rib segmentation in CT scans by creating a publicly available dataset (RibSeg) with 490 scans and 11,719 ribs, and developed a point cloud-based method that achieves state-of-the-art segmentation with a Dice score of approximately 95% and is 10 to 40 times faster than prior methods.
Manual rib inspections in computed tomography (CT) scans are clinically critical but labor-intensive, as 24 ribs are typically elongated and oblique in 3D volumes. Automatic rib segmentation methods can speed up the process through rib measurement and visualization. However, prior arts mostly use in-house labeled datasets that are publicly unavailable and work on dense 3D volumes that are computationally inefficient. To address these issues, we develop a labeled rib segmentation benchmark, named \emph{RibSeg}, including 490 CT scans (11,719 individual ribs) from a public dataset. For ground truth generation, we used existing morphology-based algorithms and manually refined its results. Then, considering the sparsity of ribs in 3D volumes, we thresholded and sampled sparse voxels from the input and designed a point cloud-based baseline method for rib segmentation. The proposed method achieves state-of-the-art segmentation performance (Dice~$\approx95\%$) with significant efficiency ($10\sim40\times$ faster than prior arts). The RibSeg dataset, code, and model in PyTorch are available at https://github.com/M3DV/RibSeg.