← Back to all news
arXiv Computer Vision By Lixing Tan, Hongye Hao, Tianrun Gu, Qing Xia, Yuting Guo, Shuai Li, Aimin Hao

CUFormer: Modality-Aware CT-Ultrasound Point Cloud Registration for Orthopedic Navigation

Read the original on arXiv Computer Vision →

CUFormer is a modality-aware registration framework that aligns intraoperative ultrasound (US) bone-surface point clouds with preoperative computed tomography (CT) models, addressing challenges from differing imaging physics and partial surface coverage. It introduces a Modality-Aware Transformer (MAT) that encodes modality through identity embeddings and uses modality-specific adapters within a shared geometric matcher, while modeling imaging visibility to weight correspondences. On two CT-US datasets (UltraBones100k and UltraBonesHip) and the CT-RGB-D SpineDepth dataset, CUFormer achieves the lowest mean registration errors, notably reducing RMSE by 65.8% on UltraBones100k compared to the best baseline.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Sep 11

UBone3D: Physics-Rectified Conditional Flow Matching for Anatomical 3D Shape Completion from Ultrasound

UBone3D is a new framework that completes 3D anatomical shapes from partial ultrasound point clouds using physics-rectified conditional flow matching. It models ultrasound artifacts with a simulated physics proxy and applies test-time physics rectification to guide the completion. The method combines a CT-trained generative shape prior and a physics consistency network, achieving higher reconstruction accuracy and anatomical fidelity than existing baselines.

By Weiying Chen, Yuchong Gao, Siyuan Li, Marek Reformat, Rui Zheng, Edmond Lou
diffusioncomputer-vision
More like this →
arXiv Computer Vision
Oct 16

Bridging the Markerless Tracking Validation Gap: Intraoperative X-ray Workflow Integration

The paper presents a clinically viable pipeline that uses routine intraoperative C‑arm fluoroscopy to derive per‑vertebra 6‑DoF poses, which are co‑registered to an RGB‑D camera via a multimodal fiducial array. This approach provides independent subsurface ground truth for validating markerless spinal tracking methods without adding radiation or altering standard surgical workflows. Ex vivo tests show an end‑to‑end accuracy of about 2 mm and 3.3°, and the framework is applied to evaluate two markerless registration strategies on real surgical data.

By Connor Daly, Salvatore Russo, Jinendra Ekanayake, Daniel S. Elson, Ferdinando Rodriguez y Baena
multimodalbenchmarks
More like this →
arXiv Computer Vision
Aug 26

C3VDReg: A Benchmark for Local-to-Local Colonoscopic Registration toward Anatomical Localization

C3VDReg is a benchmark for local-to-local colonoscopic registration that uses the Colonoscopy 3D Video Dataset (C3VD) to generate 10,015 partial-to-partial point cloud pairs, with 2,088 held‑out test pairs. Each pair consists of a source point cloud from depth reprojection and a target point cloud from CT mesh raycasting, evaluated under a standardized protocol of 8,192 points per cloud and fixed pose conventions. Experiments show that high geometric overlap does not guarantee reliable pose recovery, revealing translation ambiguity along repetitive tubular anatomy as a key failure mode.

By Linzhe Jiang, Jiayuan Huang, Sophia Bano, Matthew J. Clarkson, Zhehua Mao, Mobarak I. Hoque
benchmarks
More like this →