Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhu, Hanjiang, Rezende, Pedro Martelleto, Yang, Zhang, Ye, Tong, Gao, Bruce Z., Luo, Feng, Huang, Siyu, Yang, Jiancheng
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2601.22576
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908799158190080
author Zhu, Hanjiang
Rezende, Pedro Martelleto
Yang, Zhang
Ye, Tong
Gao, Bruce Z.
Luo, Feng
Huang, Siyu
Yang, Jiancheng
author_facet Zhu, Hanjiang
Rezende, Pedro Martelleto
Yang, Zhang
Ye, Tong
Gao, Bruce Z.
Luo, Feng
Huang, Siyu
Yang, Jiancheng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_22576
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Bonnet: Ultra-fast whole-body bone segmentation from CT scans
Zhu, Hanjiang
Rezende, Pedro Martelleto
Yang, Zhang
Ye, Tong
Gao, Bruce Z.
Luo, Feng
Huang, Siyu
Yang, Jiancheng
Image and Video Processing
Computer Vision and Pattern Recognition
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.
title Bonnet: Ultra-fast whole-body bone segmentation from CT scans
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.22576