APCReg: Anatomical-Prior-Guided Coarse-to-Fine CBCT--IOS Registration via Multi-View Projection and Reliability-Controlled Residual Correction

• URL: http://arxiv.org/abs/2608.09993v1
• Date: Fri, 07 Aug 2026 09:06:05 GMT
• Title: APCReg: Anatomical-Prior-Guided Coarse-to-Fine CBCT--IOS Registration via Multi-View Projection and Reliability-Controlled Residual Correction
• Abstract summary: APCReg is an anatomical-prior-guided coarse-to-fine framework for global registration and reliability-controlled residual correction.<n>On 60 held-out jaw pairs, APCReg achieves a submillimeter mean Chamfer distance of 0.87 mm and a Hausdorff distance of 2.92 mm.
• Score: 11.081240599321724
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Registration between cone-beam computed tomography (CBCT) and intraoral scans (IOS) is essential for patient-specific surgical planning. However, disparate imaging modalities, limited overlap, and large pose offsets make automated registration unreliable. Consequently, clinical registration remains dependent on conventional geometry pipelines and manual clinician adjustment. To address these challenges, we propose APCReg, an anatomical-prior-guided coarse-to-fine framework for global registration and reliability-controlled residual correction. Specifically, multi-view anatomical coarse registration (MACR) performs ordered orthogonal projection alignment (buccal, proximal, and occlusal) to decompose the six-degree-of-freedom search before three-dimensional refinement. Overlap-aware residual registration (OARR) combines shared KPConv features, a folded arch-length cue, overlap-gated cross-attention, and Sinkhorn matching. Finally, dental-arch-structured hypothesis selection evaluates diverse poses on held-out reliable correspondences, while a ground-truth-free coarse-retention guard conditionally retains a geometrically reliable coarse pose. On 60 held-out jaw pairs, APCReg achieves a submillimeter mean Chamfer distance of 0.87 mm and a Hausdorff distance of 2.92 mm under this evaluation protocol, and ranks first across the six reported metrics among the evaluated open-source baselines.

Related papers

• THA-Flow Generative Model: Prosthesis Geometry Prediction from Preoperative CT [7.351430886602578]
  We present THA-Flow, a conditional flow-matching model that generates three-dimensional prosthesis geometry directly from preoperative CT.<n>Separate AutoencoderKL models compress preoperative bone anatomy and prosthesis geometry, while a three-dimensional UNet learns a rectified flow from Gaussian noise to the prosthesis latent space.
  arXiv  Detail & Related papers  (2026-08-26T14:22:06Z)
• MAC-XA: Multi-view Anatomy-Correspondence Fusion for Coronary Stenosis Reporting from X-ray Angiography [46.98348758460767]
  Multi-view reasoning in coronary X-ray angiography is inherently a cross-projection geometric problem.<n>We introduce a controllable synthetic angiography generation strategy to expose geometry-derived patch-level correspondence supervision.<n>Experiments on synthetic data and zero-shot transfer to real angiograms show that this alignment-constrained design improves correspondence consistency and structured stenosis reporting.
  arXiv  Detail & Related papers  (2026-07-07T13:33:25Z)
• Contour-Constrained Deformable Registration with Parameter Characterization for Head and Neck Surgical Guidance [1.77256810223988]
  We present a biomechanics-driven deformable registration framework that corrects post-resection tissue deformation to provide intraoperative guidance.<n>Across nine specimens from skin, buccal mucosa, and tongue sites, the overall mean target registration error was $11.11 pm 4.07$ mm using rigid registration.<n>The proposed contour-constrained deformable registration further reduced the error to $5.62 pm 2.28$ mm, a 49.41% reduction relative to rigid registration.
  arXiv  Detail & Related papers  (2026-06-18T04:07:26Z)
• Paired-CSLiDAR: Height-Stratified Registration for Cross-Source Aerial-Ground LiDAR Pose Refinement [46.13526676100776]
  We introduce Paired-CSLiDAR, a cross-source aerial-ground LiDAR benchmark for single-scan pose refinement.<n>The benchmark contains 12,683 ground-aerial pairs across 6 evaluation sites.<n>We propose Residual-Guided Stratified Registration (RGSR), a training-free, geometry-only refinement pipeline.
  arXiv  Detail & Related papers  (2026-05-01T13:14:20Z)
• Point Cloud Registration for Fusion between SPECT MPI and CTA Images [31.52555943262385]
  Cross-modality misregistration and reliance on manual landmarks can hinder accurate ischemia localization and lesion-level functional assessment.<n>We propose a registration and fusion framework for SPECT MPI and CTA that integrates functional and structural information for comprehensive cardiac evaluation.
  arXiv  Detail & Related papers  (2026-04-27T14:24:49Z)
• Training-free Detection and 6D Pose Estimation of Unseen Surgical Instruments [45.387920812487465]
  This work introduces a training-free pipeline for accurate multi-view 6D pose estimation of unseen surgical instruments.<n>The proposed method was rigorously evaluated on real-world surgical data from the MVPSP dataset.
  arXiv  Detail & Related papers  (2026-03-26T09:28:19Z)
• ARIADNE: A Perception-Reasoning Synergy Framework for Trustworthy Coronary Angiography Analysis [11.092207850601488]
  We present ARIADNE, a two-stage framework coupling preference-aligned perception with RL-based diagnostic reasoning for stenosis detection.<n>On 1,400 clinical angiograms, ARIADNE achieves state-of-the-art centerline Dice of 0.838, reduces false positives by 41% compared to geometric baselines.
  arXiv  Detail & Related papers  (2026-03-19T17:25:19Z)
• CT-Enabled Patient-Specific Simulation and Contact-Aware Robotic Planning for Cochlear Implantation [41.386729124620366]
  Robotic cochlear-implant insertion requires precise prediction and regulation of contact forces to minimize intracochlear trauma.<n>This paper presents a unified CT-to-simulation pipeline for contact-aware insertion planning and validation.
  arXiv  Detail & Related papers  (2026-03-05T16:13:59Z)
• Preoperative-to-intraoperative Liver Registration for Laparoscopic Surgery via Latent-Grounded Correspondence Constraints [51.7011449975586]
  Land-Reg is a deformable registration framework that learns latent-grounded 2D-3D landmark correspondences.<n>For rigid registration, Land-Reg embraces a Cross-modal Latent Alignment module.<n>An Uncertainty-enhanced Overlap Landmark Detector with similarity matching is proposed to robustly estimate explicit 2D-3D landmark correspondences.
  arXiv  Detail & Related papers  (2026-03-02T10:44:03Z)
• Silhouette-to-Contour Registration: Aligning Intraoral Scan Models with Cephalometric Radiographs [10.70146635420186]
  We propose DentalSCR, a pose-stable, contour-guided framework for accurate and interpretable silhouette-to-contour registration.<n>We evaluate DentalSCR on 34 expert-annotated clinical cases.
  arXiv  Detail & Related papers  (2025-11-18T10:50:04Z)
• Skeleton Graph-based Ultrasound-CT Non-rigid Registration [40.40844749663152]
  We propose a skeleton graph-based non-rigid registration to adapt patient-specific properties using subcutaneous bone surface features. To validate the proposed approach, we manually extract the US cartilage point cloud from one volunteer and seven CT cartilage point clouds from different patients.
  arXiv  Detail & Related papers  (2023-05-14T19:21:43Z)
• The Brain Tumor Sequence Registration (BraTS-Reg) Challenge: Establishing Correspondence Between Pre-Operative and Follow-up MRI Scans of Diffuse Glioma Patients [31.567542945171834]
  We describe the Brain Tumor Sequence Registration (BraTS-Reg) challenge. BraTS-Reg is the first public benchmark environment for deformable registration algorithms. The aim of BraTS-Reg is to continue to serve as an active resource for research.
  arXiv  Detail & Related papers  (2021-12-13T19:25:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.