pith. sign in

arxiv: 2503.16309 · v2 · pith:BR3MG7NJnew · submitted 2025-03-20 · 📡 eess.IV · cs.CV· physics.med-ph

Rapid patient-specific neural networks for intraoperative X-ray to volume registration

Vivek Gopalakrishnan , David-Dimitris Chlorogiannis , Andrew Abumoussa , Anna M. Larson , Nazim Haouchine , Darren B. Orbach , Sarah Frisken , Neel Dey
show 1 more author
Polina Golland
This is my paper

Pith reviewed 2026-05-22 23:08 UTC · model grok-4.3

classification 📡 eess.IV cs.CVphysics.med-ph
keywords 2D/3D registrationfluoroscopypatient-specific neural networksself-supervised learningimage-guided surgeryX-ray to volume registrationintraoperative imaging
0
0 comments X

The pith

Patient-specific neural networks register preoperative 3D volumes to intraoperative X-rays in seconds with order-of-magnitude accuracy gains across anatomies.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces xvr, a self-supervised framework that trains patient-specific neural networks on physics-based simulations derived from each patient's own preoperative CT or MRI scan to align those 3D volumes with 2D fluoroscopy images. Existing intensity-based methods demand per-patient tuning while deep learning approaches require large labeled datasets restricted to narrow anatomies; xvr avoids both by pretraining a foundation model on thousands of whole-body scans and adapting it in five minutes. The largest evaluation on real fluoroscopy data to date reports high accuracy achieved in seconds across structures, modalities, and hospitals, with an order-of-magnitude improvement over prior techniques. A reader would care because precise 2D/3D registration underpins navigation in image-guided interventions and surgical robotics, and the method removes the main barriers to broad clinical use.

Core claim

xvr achieves automatic 2D/3D rigid registration by combining patient-specific neural networks with gradient-based optimization, where the networks are trained self-supervised on training data generated through physics-based simulation from the patient's preoperative volume. A foundation model pretrained on thousands of whole-body scans enables adaptation to any anatomical region in five minutes of finetuning. On the largest set of real fluoroscopy cases evaluated to date, the approach reaches high accuracy in seconds across diverse anatomical structures, imaging modalities, and hospitals while improving accuracy over existing methods by an order of magnitude.

What carries the argument

Patient-specific neural network finetuned in five minutes on physics-simulated X-ray projections from the preoperative scan and combined with gradient-based optimization for registration.

If this is right

  • Registration no longer requires careful per-subject hyperparameter tuning of intensity-based optimizers.
  • Manually labeled datasets specific to each anatomy are no longer needed.
  • A single foundation model supports pan-anatomical application after brief patient-specific adaptation.
  • Open-source release makes the method immediately usable by clinical and research communities.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The approach could support real-time guidance in robotic surgery platforms once inference speed is further optimized for continuous tracking.
  • Similar simulation-driven patient-specific adaptation might apply to other 2D/3D problems such as ultrasound-to-CT alignment.
  • If domain shift remains small, the same pretraining strategy could reduce data requirements in related medical image registration tasks.

Load-bearing premise

The physics-based simulation used to generate training data from preoperative scans produces images sufficiently similar to real intraoperative fluoroscopy that the trained network generalizes without large domain shift.

What would settle it

A comparison on a broad collection of real fluoroscopy cases showing that accuracy does not exceed existing methods by an order of magnitude or that performance collapses on new hospitals or anatomical regions would falsify the central performance claim.

Figures

Figures reproduced from arXiv: 2503.16309 by Andrew Abumoussa, Anna M. Larson, Darren B. Orbach, David-Dimitris Chlorogiannis, Nazim Haouchine, Neel Dey, Polina Golland, Sarah Frisken, Vivek Gopalakrishnan.

Figure 1
Figure 1. Figure 1: Rapidly trained patient-specific neural networks with [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: xvr implements a physics-based differentiable renderer that simulates the geometry of an X-ray C-arm to generate photorealistic X-ray images from 3D volumes. (A) Our renderer requires two inputs: a 3D volume from which to generate synthetic X-rays and the pose of the C-arm (represented with a camera frustum). Our renderer is differentiable with respect to the C-arm pose, allowing us to use gradient-based o… view at source ↗
Figure 3
Figure 3. Figure 3: Pretraining on publicly available datasets enables minutes-long patient-specific finetuning. [PITH_FULL_IMAGE:figures/full_fig_p005_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Differentiable pose refinement achieves submillimeter registration accuracy. [PITH_FULL_IMAGE:figures/full_fig_p007_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: xvr enables the rapid registration of large volumes of real-world clinical data. (A) A patient-agnostic pose estimation model was trained using synthetic X-rays rendered from 61 preregistered head CTs in the TotalSegmentator dataset. Using this model and iterative pose refinement, 122 intraoperative X-rays acquired from 50 neurosurgical patients at Brigham and Women’s Hospital were registered to their corr… view at source ↗
read the original abstract

Advanced navigation techniques in image-guided interventions and surgical robotics require the rapid and precise alignment of 3D preoperative volumes (e.g., CT, MRI) to 2D intraoperative images (e.g., X-ray fluoroscopy). However, existing 2D/3D registration methods fail to generalize across the broad spectrum of fluoroscopy-guided procedures: traditional intensity-based optimizers require careful hyperparameter tuning for each subject, while deep learning approaches demand extensive manually labeled datasets and remain constrained to the specific anatomy on which they were trained. To address these limitations, we present xvr, a self-supervised framework that combines patient-specific neural networks with gradient-based optimization for automatic 2D/3D registration. xvr leverages physics-based simulation to generate training data from a patient's own preoperative scan, eliminating the need for manual annotation. We present a foundation model pretrained on thousands of whole-body scans, achieving patient-specific adaptation for any anatomical region in only 5 minutes of finetuning. In the largest evaluation of 2D/3D registration on real fluoroscopy to date, xvr achieves high accuracy in seconds across diverse anatomical structures, imaging modalities, and hospitals, improving upon the accuracy of existing methods by an order of magnitude. xvr makes pan-anatomical 2D/3D rigid registration accessible to broad clinical and research communities through open-source software at https://xvr.csail.mit.edu.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The manuscript presents xvr, a self-supervised framework for 2D/3D rigid registration that trains patient-specific neural networks on physics-based simulations generated from a patient's preoperative CT/MRI scan. A foundation model pretrained on thousands of whole-body scans enables 5-minute adaptation per patient; the central claim is that this yields high accuracy in seconds on real intraoperative fluoroscopy across diverse anatomies, modalities, and hospitals, representing an order-of-magnitude improvement over prior intensity-based and learning-based methods, with open-source release.

Significance. If the central claims hold, the work would be significant for image-guided interventions by removing the need for manual labels or per-subject hyperparameter tuning while achieving pan-anatomical applicability. The combination of patient-specific simulation-based training with a foundation model and the scale of the real-fluoroscopy evaluation are strengths that could broaden access to accurate registration in clinical and research settings.

major comments (2)
  1. [Abstract; Evaluation] The abstract and evaluation sections claim an order-of-magnitude accuracy improvement on real fluoroscopy without reporting quantitative verification that the physics-based forward model reproduces real C-arm intensity statistics, scatter, noise, and geometric properties (e.g., no histogram comparisons, perceptual metrics, or phantom-based sim-vs-real registration error). This assumption is load-bearing for the generalization claim.
  2. [Evaluation] The results do not specify data exclusion criteria, exact baseline implementations and hyperparameter settings, or statistical tests supporting the cross-hospital and cross-modality superiority claims, making it impossible to assess whether the reported accuracy gains are robust.
minor comments (2)
  1. [Methods] Notation for the neural network architecture and loss terms could be clarified with an explicit equation reference in the methods.
  2. [Figures] Figure captions should include the number of test cases and exact error metrics shown.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback. We address each major comment below and will revise the manuscript accordingly to improve clarity and rigor.

read point-by-point responses

  1. Referee: [Abstract; Evaluation] The abstract and evaluation sections claim an order-of-magnitude accuracy improvement on real fluoroscopy without reporting quantitative verification that the physics-based forward model reproduces real C-arm intensity statistics, scatter, noise, and geometric properties (e.g., no histogram comparisons, perceptual metrics, or phantom-based sim-vs-real registration error). This assumption is load-bearing for the generalization claim.

    Authors: We agree that direct quantitative validation of simulation fidelity would strengthen the paper. The forward model follows established physics-based principles from prior X-ray simulation literature, and the strong real-fluoroscopy results across sites provide indirect support. However, the manuscript lacks explicit sim-to-real metrics. We will add a supplementary section with intensity histogram comparisons, perceptual metrics, and phantom-based registration error analysis to better substantiate the claims. revision: yes

  2. Referee: [Evaluation] The results do not specify data exclusion criteria, exact baseline implementations and hyperparameter settings, or statistical tests supporting the cross-hospital and cross-modality superiority claims, making it impossible to assess whether the reported accuracy gains are robust.

    Authors: We acknowledge that additional methodological transparency is required. The revised manuscript will specify data exclusion criteria, provide exact baseline implementations with hyperparameter settings, and include statistical tests (e.g., paired comparisons with p-values) to support the reported gains across hospitals and modalities. revision: yes

Circularity Check

0 steps flagged

No significant circularity in derivation chain

full rationale

The paper trains patient-specific networks via physics-based simulation from preoperative CT/MRI volumes and evaluates registration accuracy on held-out real fluoroscopy images across multiple sites and anatomies. No step equates a claimed prediction or result to its own fitted inputs by construction, nor does any load-bearing premise reduce to a self-citation chain or imported uniqueness theorem. The sim-to-real generalization is an empirical assumption tested by external real-data evaluation rather than a definitional equivalence, leaving the reported accuracy gains independent of the training procedure itself.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

Review performed on abstract only; full details of any learned parameters or modeling assumptions are unavailable.

axioms (1)
  • domain assumption Physics-based simulation of X-ray images from preoperative volumes produces data distribution close enough to real fluoroscopy for effective self-supervised training
    Central to generating training data without manual labels.

pith-pipeline@v0.9.0 · 5827 in / 1248 out tokens · 57731 ms · 2026-05-22T23:08:17.437020+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

83 extracted references · 83 canonical work pages · 1 internal anchor

  1. [1]

    Patient exposure from radiologic and nuclear medicine procedures in the united states and worldwide: 2009–2018

    Mahadevappa Mahesh, Armin J Ansari, and Fred A Mettler Jr. Patient exposure from radiologic and nuclear medicine procedures in the united states and worldwide: 2009–2018. Radiology, 307(1):e221263, 2022

    work page 2009

  2. [2]

    Intraoperative image guidance in neurosurgery: devel- opment, current indications, and future trends

    Chris Schulz, Stephan Waldeck, and Uwe Max Mauer. Intraoperative image guidance in neurosurgery: devel- opment, current indications, and future trends. Radiol- ogy research and practice, 2012(1):197364, 2012

    work page 2012

  3. [3]

    The role of imaging in the develop- ment of neurosurgery

    Matthew A Kirkman. The role of imaging in the develop- ment of neurosurgery. Journal of Clinical Neuroscience, 22(1):55–61, 2015

    work page 2015

  4. [4]

    Image guided orthopaedic surgery design and analy- sis

    R Phillips, WJ Viant, AMMA Mohsen, JG Griffiths, MA Bell, TJ Cain, KP Sherman, and MRK Karpinski. Image guided orthopaedic surgery design and analy- sis. Transactions of the Institute of Measurement and Control, 17(5):251–264, 1995

    work page 1995

  5. [5]

    Image-guided surgery: from x-rays to virtual reality

    Terry M Peters. Image-guided surgery: from x-rays to virtual reality. Computer methods in biomechanics and biomedical engineering, 4(1):27–57, 2001

    work page 2001

  6. [6]

    Endovascular image-guided interventions (eigis)

    Stephen Rudin, Daniel R Bednarek, and Kenneth R Hoffmann. Endovascular image-guided interventions (eigis). Medical physics, 35(1):301–309, 2008

    work page 2008

  7. [7]

    Image guidance for endovascular repair of complex aortic aneurysms: comparison of two- dimensional and three-dimensional angiography and image fusion

    Vania Tacher, MingDe Lin, Pascal Desgranges, Jean- Francois Deux, Thijs Grünhagen, Jean-Pierre Bec- quemin, Alain Luciani, Alain Rahmouni, and Hicham Kobeiter. Image guidance for endovascular repair of complex aortic aneurysms: comparison of two- dimensional and three-dimensional angiography and image fusion. Journal of Vascular and Interventional Radiolo...

    work page 2013

  8. [8]

    X-ray volumetric imaging in image-guided radiotherapy: the new standard in on-treatment imaging

    Catherine A McBain, Ann M Henry, Jonathan Sykes, Ali Amer, Tom Marchant, Christopher M Moore, Julie Davies, Julia Stratford, Claire McCarthy, Bridget Por- ritt, et al. X-ray volumetric imaging in image-guided radiotherapy: the new standard in on-treatment imaging. International Journal of Radiation Oncology* Biology* Physics, 64(2):625–634, 2006

    work page 2006

  9. [9]

    Advances in image-guided radiation therapy

    Laura A Dawson and David A Jaffray. Advances in image-guided radiation therapy. Journal of clinical on- cology, 25(8):938–946, 2007

    work page 2007

  10. [10]

    Image-guided radiotherapy: a new dimension in radiation oncology

    Florian Sterzing, Rita Engenhart-Cabillic, Michael Flen- tje, and Jürgen Debus. Image-guided radiotherapy: a new dimension in radiation oncology. Deutsches Aerzteblatt International, 108(16):274, 2011

    work page 2011

  11. [11]

    The interventionalism of medicine: in- terventional radiology, cardiology, and neuroradiology

    Shaheen E Lakhan, Anna Kaplan, Cyndi Laird, and Y aacov Leiter. The interventionalism of medicine: in- terventional radiology, cardiology, and neuroradiology. International archives of medicine, 2(1):27, 2009

    work page 2009

  12. [12]

    Diagnostic and interventional radiology

    Thomas J Vogl, Wolfgang Reith, and Ernst J Rummeny. Diagnostic and interventional radiology. Springer, 2016

    work page 2016

  13. [13]

    Imaging in interventional radi- ology: 2043 and beyond

    Kristy K Brock, Stephen R Chen, Rahul A Sheth, and Jeffrey H Siewerdsen. Imaging in interventional radi- ology: 2043 and beyond. Radiology, 308(1):e230146, 2023

    work page 2043

  14. [14]

    Importance of dose settings in the x-ray systems used for interventional radiology: a national survey.Car- diovascular and interventional radiology, 32:121–126, 2009

    E Vano, R Sanchez, JM Fernandez, F Rosales, MA Gar- cia, J Sotil, J Hernandez, F Carrera, J Ciudad, MM Soler, et al. Importance of dose settings in the x-ray systems used for interventional radiology: a national survey.Car- diovascular and interventional radiology, 32:121–126, 2009

    work page 2009

  15. [15]

    Five-year outcomes of transcatheter or surgical aortic-valve replacement

    Raj R Makkar, Vinod H Thourani, Michael J Mack, Susheel K Kodali, Samir Kapadia, John G Webb, Sung- Han Y oon, Alfredo Trento, Lars G Svensson, Howard C Herrmann, et al. Five-year outcomes of transcatheter or surgical aortic-valve replacement. New England Journal of Medicine, 382(9):799–809, 2020

    work page 2020

  16. [16]

    RM Greenhalgh. Comparison of endovascular aneurysm repair with open repair in patients with ab- dominal aortic aneurysm (evar trial 1), 30-day opera- tive mortality results: randomised controlled trial. The Lancet, 364(9437):843–848, 2004

    work page 2004

  17. [17]

    Imaging of interventional therapies in oncology: Image guidance, robotics, and fusion systems

    Francois H Cornelis, Omar Dzaye, Helmut Schoellnast, and Stephen B Solomon. Imaging of interventional therapies in oncology: Image guidance, robotics, and fusion systems. Interventional Oncology: A Multidis- ciplinary Approach to Image-Guided Cancer Therapy, pages 1–17, 2023

    work page 2023

  18. [18]

    Wrong-sided and wrong-level neurosurgery: a national survey

    Balraj S Jhawar, Demytra Mitsis, and Neil Duggal. Wrong-sided and wrong-level neurosurgery: a national survey. Journal of Neurosurgery: Spine, 7(5):467–472, 2007

    work page 2007

  19. [19]

    The prevalence of wrong level surgery among spine sur- geons

    Milan G Mody, Ali Nourbakhsh, Daniel L Stahl, Mark Gibbs, Mohammad Alfawareh, and Kim J Garges. The prevalence of wrong level surgery among spine sur- geons. Spine, 33(2):194–198, 2008

    work page 2008

  20. [20]

    Handbook of interventional radiologic procedures

    Krishna Kandarpa and Lindsay Machan. Handbook of interventional radiologic procedures. Lippincott Williams & Wilkins, 2011

    work page 2011

  21. [21]

    Role of 3d intraoperative imaging in orthopedic and trauma surgery

    Jérôme Tonetti, Mehdi Boudissa, Gael Kerschbaumer, and Olivier Seurat. Role of 3d intraoperative imaging in orthopedic and trauma surgery. Orthopaedics & Trau- matology: Surgery & Research, 106(1):S19–S25, 2020

    work page 2020

  22. [22]

    Machine learning for automated and real-time two-dimensional to three- dimensional registration of the spine using a single radiograph

    Andrew Abumoussa, Vivek Gopalakrishnan, Benjamin Succop, Michael Galgano, Sivakumar Jaikumar, Yueh Z Lee, and Deb A Bhowmick. Machine learning for automated and real-time two-dimensional to three- dimensional registration of the spine using a single radiograph. Neurosurgical Focus, 54(6):E16, 2023

    work page 2023

  23. [23]

    Method and device for displaying a first image and a second image of an object, March 6 2018

    Pieter Maria Mielekamp and Nicolaas Jan Noordhoek. Method and device for displaying a first image and a second image of an object, March 6 2018. US Patent 9,910,958

    work page 2018

  24. [24]

    A hybrid 3d-2d image registration framework for pedicle screw trajectory registration between intraoper- ative x-ray image and preoperative ct image

    Roshan Ramakrishna Naik, Anitha Hoblidar, Shyama- sunder N Bhat, Nishanth Ampar, and Raghuraj Kundan- gar. A hybrid 3d-2d image registration framework for pedicle screw trajectory registration between intraoper- ative x-ray image and preoperative ct image. Journal of Imaging, 8(7):185, 2022

    work page 2022

  25. [25]

    Patient specific 4d coronary models from ecg-gated cta data for intra-operative dynamic alignment of cta with x-ray images

    Coert T Metz, Michiel Schaap, Stefan Klein, Lisan A Neefjes, Ermanno Capuano, Carl Schultz, Robert Jan Van Geuns, Patrick W Serruys, Theo Van Walsum, and Wiro J Niessen. Patient specific 4d coronary models from ecg-gated cta data for intra-operative dynamic alignment of cta with x-ray images. In Medical Im- 19 age Computing and Computer-Assisted Intervent...

    work page 2009

  26. [26]

    Epipolar consistency in transmission imaging

    André Aichert, Martin Berger, Jian Wang, Nicole Maass, Arnd Doerfler, Joachim Hornegger, and Andreas K Maier. Epipolar consistency in transmission imaging. IEEE transactions on medical imaging , 34(11):2205– 2219, 2015

    work page 2015

  27. [27]

    4d interventional device recon- struction from biplane fluoroscopy

    Martin Wagner, Sebastian Schafer, Charles Strother, and Charles Mistretta. 4d interventional device recon- struction from biplane fluoroscopy. Medical physics, 43 (3):1324–1334, 2016

    work page 2016

  28. [28]

    Image registration and data fusion in radiation therapy

    Marc L Kessler. Image registration and data fusion in radiation therapy. The British Institute of Radiology, 79: S99–S108, 2006

    work page 2006

  29. [29]

    Artificial intelligence in radiation oncol- ogy

    Elizabeth Huynh, Ahmed Hosny, Christian Guthier, Danielle S Bitterman, Steven F Petit, Daphne A Haas- Kogan, Benjamin Kann, Hugo JWL Aerts, and Ray- mond H Mak. Artificial intelligence in radiation oncol- ogy. Nature Reviews Clinical Oncology , 17(12):771– 781, 2020

    work page 2020

  30. [30]

    A robotic electromagnetic navigation bronchoscopy with integrated tool-in-lesion- tomosynthesis technology: The MATCH study

    Krish Bhadra, Otis B Rickman, Amit K Mahajan, and Douglas Kyle Hogarth. A robotic electromagnetic navigation bronchoscopy with integrated tool-in-lesion- tomosynthesis technology: The MATCH study. Journal of Bronchology & Interventional Pulmonology , 31(1): 23–29, 2024

    work page 2024

  31. [31]

    Telerobotic neurovascular interventions with mag- netic manipulation

    Y oonho Kim, Emily Genevriere, Pablo Harker, Jaehun Choe, Marcin Balicki, Robert W Regenhardt, Justin E Vranic, Adam A Dmytriw, Aman B Patel, and Xuanhe Zhao. Telerobotic neurovascular interventions with mag- netic manipulation. Science Robotics, 7(65):eabg9907, 2022

    work page 2022

  32. [32]

    The impact of machine learning on 2D/3D registration for image-guided interventions: A systematic review and perspective

    Mathias Unberath, Cong Gao, Yicheng Hu, Max Judish, Russell H Taylor, Mehran Armand, and Robert Grupp. The impact of machine learning on 2D/3D registration for image-guided interventions: A systematic review and perspective. Frontiers in Robotics and AI , 8:716007, 2021

    work page 2021

  33. [33]

    Patient setup error measurement using 3d intensity-based im- age registration techniques

    S Ébastien Clippe, David Sarrut, Claude Malet, Serge Miguet, Chantal Ginestet, and Christian Carrie. Patient setup error measurement using 3d intensity-based im- age registration techniques. International Journal of Radiation Oncology* Biology* Physics, 56(1):259–265, 2003

    work page 2003

  34. [34]

    A patient-to-computed-tomography image reg- istration method based on digitally reconstructed radio- graphs

    L Lemieux, R Jagoe, DR Fish, ND Kitchen, and DGT Thomas. A patient-to-computed-tomography image reg- istration method based on digitally reconstructed radio- graphs. Medical physics, 21(11):1749–1760, 1994

    work page 1994

  35. [35]

    A comparison of similarity measures for use in 2-d-3-d medical image registration

    Graeme P Penney, Jürgen Weese, John A Little, Paul Desmedt, Derek LG Hill, et al. A comparison of similarity measures for use in 2-d-3-d medical image registration. IEEE transactions on medical imaging, 17(4):586–595, 1998

    work page 1998

  36. [36]

    Effective intensity- based 2d/3d rigid registration between fluoroscopic x- ray and ct

    Dotan Knaan and Leo Joskowicz. Effective intensity- based 2d/3d rigid registration between fluoroscopic x- ray and ct. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 351–358. Springer, 2003

    work page 2003

  37. [37]

    2d-3d rigid registration of x-ray fluoroscopy and ct im- ages using mutual information and sparsely sampled histogram estimators

    L Zollei, Eric Grimson, Alexander Norbash, and W Wells. 2d-3d rigid registration of x-ray fluoroscopy and ct im- ages using mutual information and sparsely sampled histogram estimators. In Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, volume 2, pages II–II. IEEE, 2001

    work page 2001

  38. [38]

    Fast auto- differentiable digitally reconstructed radiographs for solv- ing inverse problems in intraoperative imaging

    Vivek Gopalakrishnan and Polina Golland. Fast auto- differentiable digitally reconstructed radiographs for solv- ing inverse problems in intraoperative imaging. In Work- shop on Clinical Image-Based Procedures, pages 1–11. Springer, 2022

    work page 2022

  39. [39]

    A robust method for reg- istration of three-dimensional knee implant models to two-dimensional fluoroscopy images

    Mohamed R Mahfouz, William A Hoff, Richard D Komis- tek, and Douglas A Dennis. A robust method for reg- istration of three-dimensional knee implant models to two-dimensional fluoroscopy images. IEEE transactions on medical imaging, 22(12):1561–1574, 2003

    work page 2003

  40. [40]

    In vivo measurement of 3-d skeletal kinematics from sequences of biplane radiographs: application to knee kinematics

    B-M Y ou, Pepe Siy, William Anderst, and Scott Tashman. In vivo measurement of 3-d skeletal kinematics from sequences of biplane radiographs: application to knee kinematics. IEEE transactions on medical imaging, 20 (6):514–525, 2001

    work page 2001

  41. [41]

    Generalizing spatial transformers to projective geome- try with applications to 2d/3d registration

    Cong Gao, Xingtong Liu, Wenhao Gu, Benjamin Killeen, Mehran Armand, Russell Taylor, and Mathias Unberath. Generalizing spatial transformers to projective geome- try with applications to 2d/3d registration. In Medical Image Computing and Computer Assisted Intervention– MICCAI 2020: 23rd International Conference, Lima, Peru, October 4–8, 2020, Proceedings, ...

    work page 2020

  42. [42]

    Extended capture range of rigid 2d/3d registration by estimating riemannian pose gra- dients

    Wenhao Gu, Cong Gao, Robert Grupp, Javad Fotouhi, and Mathias Unberath. Extended capture range of rigid 2d/3d registration by estimating riemannian pose gra- dients. In Machine Learning in Medical Imaging: 11th International Workshop, MLMI 2020, Held in Conjunc- tion with MICCAI 2020, Lima, Peru, October 4, 2020, Proceedings 11, pages 281–291. Springer, 2020

    work page 2020

  43. [43]

    A fully differentiable framework for 2d/3d registration and the projective spatial transformers

    Cong Gao, Anqi Feng, Xingtong Liu, Russell H Tay- lor, Mehran Armand, and Mathias Unberath. A fully differentiable framework for 2d/3d registration and the projective spatial transformers. IEEE transactions on medical imaging, 2023

    work page 2023

  44. [44]

    A review of 3d/2d registration methods for image-guided interventions

    Primoz Markelj, Dejan Tomaževiˇc, Bostjan Likar, and Franjo Pernuš. A review of 3d/2d registration methods for image-guided interventions. Medical image analysis, 16(3):642–661, 2012

    work page 2012

  45. [45]

    Pose estimation of periacetabular osteotomy fragments with intraoperative x-ray navigation

    Robert B Grupp, Rachel A Hegeman, Ryan J Mur- phy, Clayton P Alexander, Y oshito Otake, Benjamin A McArthur, Mehran Armand, and Russell H Taylor. Pose estimation of periacetabular osteotomy fragments with intraoperative x-ray navigation. IEEE transactions on biomedical engineering, 67(2):441–452, 2019

    work page 2019

  46. [46]

    Learning to detect anatomical landmarks of the 20 pelvis in x-rays from arbitrary views

    Bastian Bier, Florian Goldmann, Jan-Nico Zaech, Javad Fotouhi, Rachel Hegeman, Robert Grupp, Mehran Ar- mand, Greg Osgood, Nassir Navab, Andreas Maier, et al. Learning to detect anatomical landmarks of the 20 pelvis in x-rays from arbitrary views. International jour- nal of computer assisted radiology and surgery , 14: 1463–1473, 2019

    work page 2019

  47. [47]

    Towards fully auto- matic x-ray to ct registration

    Javier Esteban, Matthias Grimm, Mathias Unberath, Guillaume Zahnd, and Nassir Navab. Towards fully auto- matic x-ray to ct registration. In Medical Image Comput- ing and Computer Assisted Intervention–MICCAI 2019: 22nd International Conference, Shenzhen, China, Oc- tober 13–17, 2019, Proceedings, Part VI 22 , pages 631–639. Springer, 2019

    work page 2019

  48. [48]

    X-ray to ct rigid registration using scene coordinate regression

    Pragyan Shrestha, Chun Xie, Hidehiko Shishido, Yuichi Y oshii, and Itaru Kitahara. X-ray to ct rigid registration using scene coordinate regression. InInternational Con- ference on Medical Image Computing and Computer- Assisted Intervention, pages 781–790. Springer, 2023

    work page 2023

  49. [49]

    Rayemb: Arbitrary landmark detection in x-ray images using ray embedding subspace

    Pragyan Shrestha, Chun Xie, Yuichi Y oshii, and Itaru Kitahara. Rayemb: Arbitrary landmark detection in x-ray images using ray embedding subspace. arXiv preprint arXiv:2410.08152, 2024

    work page arXiv 2024

  50. [50]

    A cnn regres- sion approach for real-time 2d/3d registration

    Shun Miao, Z Jane Wang, and Rui Liao. A cnn regres- sion approach for real-time 2d/3d registration. IEEE transactions on medical imaging , 35(5):1352–1363, 2016

    work page 2016

  51. [51]

    X-ray posenet: 6 dof pose estimation for mobile x-ray devices

    Mai Bui, Shadi Albarqouni, Michael Schrapp, Nassir Navab, and Slobodan Ilic. X-ray posenet: 6 dof pose estimation for mobile x-ray devices. In 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), pages 1036–1044. IEEE, 2017

    work page 2017

  52. [52]

    A patient-specific self-supervised model for automatic x-ray/ct registra- tion

    Baochang Zhang, Shahrooz Faghihroohi, Moham- mad Farid Azampour, Shuting Liu, Reza Ghotbi, Herib- ert Schunkert, and Nassir Navab. A patient-specific self-supervised model for automatic x-ray/ct registra- tion. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 515–524. Springer, 2023

    work page 2023

  53. [53]

    In- traoperative 2D/3D image registration via differentiable X-ray rendering

    Vivek Gopalakrishnan, Neel Dey, and Polina Golland. In- traoperative 2D/3D image registration via differentiable X-ray rendering. arXiv preprint arXiv:2312.06358, 2023

    work page arXiv 2023

  54. [54]

    Automatic annotation of hip anatomy in fluoroscopy for robust and efficient 2D/3D registration

    Robert B Grupp, Mathias Unberath, Cong Gao, Rachel A Hegeman, Ryan J Murphy, Clayton P Alexan- der, Y oshito Otake, Benjamin A McArthur, Mehran Ar- mand, and Russell H Taylor. Automatic annotation of hip anatomy in fluoroscopy for robust and efficient 2D/3D registration. International journal of computer assisted radiology and surgery, 15:759–769, 2020

    work page 2020

  55. [55]

    Synthetic data accelerates the devel- opment of generalizable learning-based algorithms for x-ray image analysis

    Cong Gao, Benjamin D Killeen, Yicheng Hu, Robert B Grupp, Russell H Taylor, Mehran Armand, and Math- ias Unberath. Synthetic data accelerates the devel- opment of generalizable learning-based algorithms for x-ray image analysis. Nature Machine Intelligence, 5(3): 294–308, 2023

    work page 2023

  56. [56]

    Fast calculation of the exact radio- logical path for a three-dimensional CT array

    Robert L Siddon. Fast calculation of the exact radio- logical path for a three-dimensional CT array. Medical physics, 12(2):252–255, 1985

    work page 1985

  57. [57]

    AI in health and medicine.Nature Medicine, 28(1):31–38, 2022

    Pranav Rajpurkar, Emma Chen, Oishi Banerjee, and Eric J Topol. AI in health and medicine.Nature Medicine, 28(1):31–38, 2022

    work page 2022

  58. [58]

    Artificial intelligence in surgery

    Chris Varghese, Ewen M Harrison, Greg O’Grady, and Eric J Topol. Artificial intelligence in surgery. Nature Medicine, pages 1–12, 2024

    work page 2024

  59. [59]

    Artificial intelligence meets medical robotics

    Michael Yip, Septimiu Salcudean, Ken Goldberg, Kas- par Althoefer, Arianna Menciassi, Justin D Opfermann, Axel Krieger, Krithika Swaminathan, Conor J Walsh, He Huang, et al. Artificial intelligence meets medical robotics. Science, 381(6654):141–146, 2023

    work page 2023

  60. [60]

    3D-2D registration of cerebral angiograms: A method and evaluation on clinical images

    Uroš Mitrovi´c, Žiga Špiclin, Boštjan Likar, and Franjo Pernuš. 3D-2D registration of cerebral angiograms: A method and evaluation on clinical images. IEEE trans- actions on medical imaging, 32(8):1550–1563, 2013

    work page 2013

  61. [61]

    Deep learning to segment pelvic bones: large- scale CT datasets and baseline models

    Pengbo Liu, Hu Han, Yuanqi Du, Heqin Zhu, Yinhao Li, Feng Gu, Honghu Xiao, Jun Li, Chunpeng Zhao, Li Xiao, et al. Deep learning to segment pelvic bones: large- scale CT datasets and baseline models. International Journal of Computer Assisted Radiology and Surgery, 16:749–756, 2021

    work page 2021

  62. [62]

    The ANTsX ecosystem for quanti- tative biological and medical imaging

    Nicholas J Tustison, Philip A Cook, Andrew J Holbrook, Hans J Johnson, John Muschelli, Gabriel A Devenyi, Jeffrey T Duda, Sandhitsu R Das, Nicholas C Cullen, Daniel L Gillen, et al. The ANTsX ecosystem for quanti- tative biological and medical imaging. Scientific reports, 11(1):9068, 2021

    work page 2021

  63. [63]

    Mag- netic resonance angiography atlas dataset, 2017

    NeuroImaging Tools & Resources Collaboratory. Mag- netic resonance angiography atlas dataset, 2017. URL https://www.nitrc.org/projects/icbmmra/

    work page 2017

  64. [64]

    VesselBoost: A Python toolbox for small blood vessel segmentation in human magnetic resonance angiography data

    Marshall Xu, Fernanda L Ribeiro, Markus Barth, Michaël Bernier, Steffen Bollmann, Soumick Chatterjee, Francesco Cognolato, Omer Faruk Gulban, Vaibhavi Itkyal, Siyu Liu, et al. VesselBoost: A Python toolbox for small blood vessel segmentation in human magnetic resonance angiography data. bioRxiv, pages 2024–05, 2024

    work page 2024

  65. [65]

    Adam: A Method for Stochastic Optimization

    Diederik P Kingma. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014

    work page internal anchor Pith review Pith/arXiv arXiv 2014

  66. [66]

    U- net: Convolutional networks for biomedical image seg- mentation

    Olaf Ronneberger, Philipp Fischer, and Thomas Brox. U- net: Convolutional networks for biomedical image seg- mentation. In Medical image computing and computer- assisted intervention–MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, pro- ceedings, part III 18, pages 234–241. Springer, 2015

    work page 2015

  67. [67]

    A robust O(n) solution to the Perspective-n-Point problem

    Shiqi Li, Chi Xu, and Ming Xie. A robust O(n) solution to the Perspective-n-Point problem. IEEE transactions on pattern analysis and machine intelligence , 34(7): 1444–1450, 2012

    work page 2012

  68. [68]

    Vascular hetero- geneity and specialization in development and disease

    Michael Potente and Taija Mäkinen. Vascular hetero- geneity and specialization in development and disease. Nature Reviews Molecular Cell Biology, 18(8):477–494, 2017

    work page 2017

  69. [69]

    TotalSegmentator: robust segmentation of 104 anatomic structures in CT images

    Jakob Wasserthal, Hanns-Christian Breit, Manfred T Meyer, Maurice Pradella, Daniel Hinck, Alexander W Sauter, Tobias Heye, Daniel T Boll, Joshy Cyriac, Shan Y ang, et al. TotalSegmentator: robust segmentation of 104 anatomic structures in CT images. Radiology: Artificial Intelligence, 5(5), 2023

    work page 2023

  70. [70]

    Patch-based image similarity for intraoperative 2d/3d pelvis registration during periacetabular osteotomy

    Robert B Grupp, Mehran Armand, and Russell H Taylor. Patch-based image similarity for intraoperative 2d/3d pelvis registration during periacetabular osteotomy. In 21 OR 2.0 Context-Aware Operating Theaters, Computer Assisted Robotic Endoscopy, Clinical Image-Based Pro- cedures, and Skin Image Analysis: First International Workshop, OR 2.0 2018, 5th Intern...

    work page 2018

  71. [71]

    Deep learning in medical image regis- tration: Magic or mirage? In The Thirty-eighth Annual Conference on Neural Information Processing Systems,

    Rohit Jena, Deeksha Sethi, Pratik Chaudhari, and James Gee. Deep learning in medical image regis- tration: Magic or mirage? In The Thirty-eighth Annual Conference on Neural Information Processing Systems,

    work page

  72. [72]

    URL https://openreview.net/forum?id=lZJ0 WYI5YC

    work page

  73. [73]

    Convexadam: Self-configuring dual-optimisation-based 3d multitask medical image registration

    Hanna Siebert, Christoph Großbröhmer, Lasse Hansen, and Mattias P Heinrich. Convexadam: Self-configuring dual-optimisation-based 3d multitask medical image registration. IEEE Transactions on Medical Imaging , 2024

    work page 2024

  74. [74]

    Wong, Clinton Wang, Mengwei Ren, Ellen Grant, Adrian V Dalca, and Polina Golland

    Neel Dey, Benjamin Billot, Hallee E. Wong, Clinton Wang, Mengwei Ren, Ellen Grant, Adrian V Dalca, and Polina Golland. Learning general-purpose biomedical volume representations using randomized synthesis. In The Thirteenth International Conference on Learning Representations, 2025. URL https://openreview.n et/forum?id=xOmC5LiVuN

    work page 2025

  75. [75]

    Automated detection and reacquisition of motion- degraded images in fetal HASTE imaging at 3 T

    Borjan Gagoski, Junshen Xu, Paul Wighton, M Dylan Tisdall, Robert Frost, Wei-Ching Lo, Polina Golland, An- dre van Der Kouwe, Elfar Adalsteinsson, and P Ellen Grant. Automated detection and reacquisition of motion- degraded images in fetal HASTE imaging at 3 T. Mag- netic resonance in medicine, 87(4):1914–1922, 2022

    work page 1914

  76. [76]

    Demon- stration of an ai-driven workflow for autonomous high- resolution scanning microscopy

    Saugat Kandel, Tao Zhou, Anakha V Babu, Zichao Di, Xinxin Li, Xuedan Ma, Martin Holt, Antonino Miceli, Charudatta Phatak, and Mathew J Cherukara. Demon- stration of an ai-driven workflow for autonomous high- resolution scanning microscopy. Nature Communica- tions, 14(1):5501, 2023

    work page 2023

  77. [77]

    Model- agnostic meta-learning for fast adaptation of deep net- works

    Chelsea Finn, Pieter Abbeel, and Sergey Levine. Model- agnostic meta-learning for fast adaptation of deep net- works. In International conference on machine learning, pages 1126–1135. PMLR, 2017

    work page 2017

  78. [78]

    Deep equilibrium models

    Shaojie Bai, J Zico Kolter, and Vladlen Koltun. Deep equilibrium models. Advances in neural information processing systems, 32, 2019

    work page 2019

  79. [79]

    Deep implicit optimization for robust and flexible image regis- tration

    Rohit Jena, Pratik Chaudhari, and James C Gee. Deep implicit optimization for robust and flexible image regis- tration. arXiv preprint arXiv:2406.07361, 2024

    work page arXiv 2024

  80. [80]

    Py- torch: An imperative style, high-performance deep learn- ing library

    Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. Py- torch: An imperative style, high-performance deep learn- ing library. Advances in neural information processing systems, 32, 2019

    work page 2019

Showing first 80 references.