mlsanityData to 14 Oct 2026

Self-Supervised 2D/3D Registration for X-Ray to CT Image Fusion

arXiv 2210.07611 ↗First posted 14 Oct 2022eess.IV cs.CV cs.LGcited by 12

Not on the map. Why?

Abstract (arXiv)

Deep Learning-based 2D/3D registration enables fast, robust, and accurate X-ray to CT image fusion when large annotated paired datasets are available for training. However, the need for paired CT volume and X-ray images with ground truth registration limits the applicability in interventional scenarios. An alternative is to use simulated X-ray projections from CT volumes, thus removing the need for paired annotated datasets. Deep Neural Networks trained exclusively on simulated X-ray projections can perform significantly worse on real X-ray images due to the domain gap. We propose a self-supervised 2D/3D registration framework combining simulated training with unsupervised feature and pixel space domain adaptation to overcome the domain gap and eliminate the need for paired annotated datasets. Our framework achieves a registration accuracy of 1.83±1.16 mm with a high success ratio of 90.1% on real X-ray images showing a 23.9% increase in success ratio compared to reference annotation-free algorithms.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 31 of its 61 references that are in the map. First posted on arXiv 14 Oct 2022.

Builds on

31 of 61 references.

References · 31

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  4. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  5. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  6. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  7. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,838
  8. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,498
  9. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,082
  10. 2021VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learningcited by 1,057
  11. 2020Contrastive Learning for Unpaired Image-to-Image Translationcited by 639
  12. 2021Fake It Till You Make It: Face analysis in the wild using synthetic data alonecited by 200
19 more
  1. 2018MedGAN: Medical Image Translation using GANscited by 152
  2. 2020SynthMorph: learning contrast-invariant registration without acquired imagescited by 140
  3. 2019Deep Learning in Medical Image Registration: A Surveycited by 124
  4. 2019X2CT-GAN: Reconstructing CT from Biplanar X-Rays with Generative Adversarial Networkscited by 85
  5. 2018DeepDRR -- A Catalyst for Machine Learning in Fluoroscopy-guided Procedurescited by 55
  6. 2018Task Driven Generative Modeling for Unsupervised Domain Adaptation: Application to X-ray Image Segmentationcited by 49
  7. 2019Automatic Annotation of Hip Anatomy in Fluoroscopy for Robust and Efficient 2D/3D Registrationcited by 29
  8. 2019Learning with Known Operators reduces Maximum Training Error Boundscited by 25
  9. 2017Dilated FCN for Multi-Agent 2D/3D Medical Image Registrationcited by 22
  10. 2018X-ray-transform Invariant Anatomical Landmark Detection for Pelvic Trauma Surgerycited by 22
  11. 2021The Impact of Machine Learning on 2D/3D Registration for Image-guided Interventions: A Systematic Review and Perspectivecited by 22
  12. 2020Generalizing Spatial Transformers to Projective Geometry with Applications to 2D/3D Registrationcited by 21
  13. 2019Multiview 2D/3D Rigid Registration via a Point-Of-Interest Network for Tracking and Triangulation (POINT2)cited by 18
  14. 2021Adversarial Domain Feature Adaptation for Bronchoscopic Depth Estimationcited by 14
  15. 2018PnP-AdaNet: Plug-and-Play Adversarial Domain Adaptation Network with a Benchmark at Cross-modality Cardiac Segmentationcited by 12
  16. 2021Adapt Everywhere: Unsupervised Adaptation of Point-Clouds and Entropy Minimisation for Multi-modal Cardiac Image Segmentationcited by 11
  17. 2020Pose-dependent weights and Domain Randomization for fully automatic X-ray to CT Registrationcited by 7
  18. 2021Deep Iterative 2D/3D Registrationcited by 6
  19. 2021Learning the Update Operator for 2D/3D Image Registrationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 3; 2025: 6; 2026: 1.

12 papers.

  1. 2023A survey on deep learning in medical image registration: new technologies, uncertainty, evaluation metrics, and beyondcited by 55
  2. 2024Local Feature Matching Using Deep Learning: A Surveycited by 26
  3. 2023Intraoperative 2D/3D Image Registration via Differentiable X-ray Renderingcited by 24
  4. 2024DISCOVER: 2-D Multiview Summarization of Optical Coherence Tomography Angiography for Automatic Diabetic Retinopathy Diagnosiscited by 3
  5. 2025Advancing Embodied Intelligence in Robotic-Assisted Endovascular Procedures: A Systematic Review of AI Solutionscited by 2
  6. 2024UDCR: Unsupervised Aortic DSA/CTA Rigid Registration Using Deep Reinforcement Learning and Overlap Degree Calculationcited by 1
  7. 2025Automatic Multi-View X-Ray/CT Registration Using Bone Substructure Contourscited by 1
  8. 2025Intraoperative 2D/3D Registration via Spherical Similarity Learning and Differentiable Levenberg-Marquardt Optimizationcited by 1
  9. 2025Robust and Accurate Multi-view 2D/3D Image Registration with Differentiable X-ray Rendering and Dual Cross-view Constraintscited by 0
  10. 2025RadGS-Reg: Registering Spine CT with Biplanar X-rays via Joint 3D Radiative Gaussians Reconstruction and 3D/3D Registrationcited by 0
  11. 2025ReBrain: Brain MRI Reconstruction from Sparse CT Slice via Retrieval-Augmented Diffusioncited by 0
  12. 2026Patient-Agnostic Synthetic Pretraining for Efficient Patient-Specific Intraoperative 2D/3D Registrationcited by 0