RibSeg Dataset and Strong Point Cloud Baselines for Rib Segmentation from CT Scans

TL;DR

This paper introduces RibSeg, a publicly available rib segmentation dataset from CT scans, along with a point cloud-based baseline method that achieves high accuracy and efficiency, advancing automatic rib segmentation.

Contribution

The paper provides a new labeled rib segmentation benchmark dataset and a novel point cloud-based segmentation method that outperforms previous approaches in accuracy and speed.

Findings

Achieved state-of-the-art segmentation accuracy with Dice ~95%.

Significantly faster (10-40x) than prior methods.

Provided publicly available dataset, code, and models.

Abstract

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.