Bonnet: Ultra-fast whole-body bone segmentation from CT scans

TL;DR

Bonnet is an ultra-fast, accurate whole-body bone segmentation method from CT scans that significantly reduces inference time using a novel sparse-volume pipeline, enabling rapid clinical and research applications.

Contribution

This paper introduces Bonnet, a novel sparse-volume pipeline that achieves rapid bone segmentation from CT scans with high accuracy, outperforming existing voxel-based models in speed.

Findings

Achieves bone segmentation in 2.69 seconds per scan

Reduces inference time by approximately 25x compared to baselines

Maintains high Dice scores across multiple anatomical regions

Abstract

This work proposes Bonnet, an ultra-fast sparse-volume pipeline for whole-body bone segmentation from CT scans. Accurate bone segmentation is important for surgical planning and anatomical analysis, but existing 3D voxel-based models such as nnU-Net and STU-Net require heavy computation and often take several minutes per scan, which limits time-critical use. The proposed Bonnet addresses this by integrating a series of novel framework components including HU-based bone thresholding, patch-wise inference with a sparse spconv-based U-Net, and multi-window fusion into a full-volume prediction. Trained on TotalSegmentator and evaluated without additional tuning on RibSeg, CT-Pelvic1K, and CT-Spine1K, Bonnet achieves high Dice across ribs, pelvis, and spine while running in only 2.69 seconds per scan on an RTX A6000. Compared to strong voxel baselines, Bonnet attains a similar accuracy but reduces inference time by roughly 25x on the same hardware and tiling setup. The toolkit and pre-trained models will be released at https://github.com/HINTLab/Bonnet.