During percutaneous coronary intervention, conventional 2D X-ray imaging lacks depth information, making it difficult for clinicians to determine the 3D position of the guidewire. While some recent approaches incorporate micro-sensors to assist with pose estimation, many rely on implanted electromagnetic sensors, which can introduce additional clinical risks. In the paper, we present a non-invasive alternative by using an external 3-axis electronic magnetometer array. We further propose a Local-Global Magneto-Visual Network framework (LG-MagNet) that fuses magnetic field information with image data to enable precise 3D pose estimation of the guidewire. Specifically, we first perform a shared encoder for cross-modal feature fusion. Then we employ convolutional operations that integrate local and global features. Finally, we utilize a lightweight prediction head for end-to-end depth regression. We constructed experimental equipment and collected a clinical simulation datasets. Results show a root mean square error (RMSE) of (0.797 ± 0.095 mm) for depth prediction along the Z-axis and an overall RMSE of (1.216 ± 0.072) mm for 3D guidewire shape reconstruction. Quantitative analysis indicates that fusing external magnetometer data with 2D imaging improves pose estimation stability, particularly in regions with curvature.
AbubakarMJavedIRasoolHF, et al. Advancements in percutaneous coronary intervention techniques: a comprehensive literature review of mixed studies and practice guidelines. Cureus2023; 15: e41311. https://doi.org/10.7759/cureus.41311
2.
BakaNMetzCTSchultzC, et al. Statistical coronary motion models for 2D+t/3D registration of X-ray coronary angiography and CTA. Med Image Anal2013; 17(6). 698–709. https://doi.org/10.1016/j.media.2013.03.003
3.
DalrympleNCPrasadSRFreckletonMW, et al. Introduction to the language of three-dimensional imaging with multidetector CT. Radiographics2005; 25(5). 1409–1428. https://doi.org/10.1148/rg.255055044
4.
AlterovitzRBranickyMGoldbergK. Motion planning under uncertainty for image-guided medical needle steering. Int J Rob Res2008; 27(11-12): 1361–1374.
5.
DupontPELockJItkowitzB, et al. Design and control of concentric-tube robots. IEEE Trans Robot2009; 26(2): 209–225.
6.
GreigarnTJacksonRLiuT, et al. Experimental validation of the pseudo-rigid-body model of the MRI-actuated catheter. In: 2017 IEEE international conference on robotics and automation (ICRA), 2017, pp. 3600–3605. IEEE. https://doi.org/10.1109/ICRA.2017.7989414
7.
RendaFCacuccioloVDiasJ, et al. Discrete Cosserat approach for soft robot dynamics: a new piece-wise constant strain model with torsion and shears. In: 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2016, pp. 5495–5502. IEEE. https://doi.org/10.1109/IROS.2016.7759808
8.
George ThuruthelTFaloticoEMantiM, et al. Learning closed loop kinematic controllers for continuum manipulators in unstructured environments. Soft Robot2017; 4(3). 285–296. https://doi.org/10.1089/soro.2016.0051
9.
TsoumakidouGSaltielSVillardN, et al. Image-guided marking techniques in interventional radiology: a review of current evidence. Diagn Interven Imaging2021; 102(12). 699–707. https://doi.org/10.1016/j.diii.2021.07.002
10.
HoffmannMBrostAJakobC, et al. Reconstruction method for curvilinear structures from two views. In: IiiDRHYanivZR (eds) Medical Imaging 2013: Image-guided procedures, robotic interventions, and modeling. International Society for Optics and Photonics, SPIE, 2013, p. 86712F. Vol. 8671.
11.
HoffmannMBrostAKochM, et al. Electrophysiology catheter detection and reconstruction from two views in fluoroscopic images. IEEE Trans Med Imaging2016; 35(2). 567–579. https://doi.org/10.1109/TMI.2015.2482539
LawsonJChitaleRSimaanN. Model-based pose estimation of steerable catheters under bi-plane image feedback. In: 2023 IEEE international conference on robotics and automation (ICRA), 2023, pp. 4789–4796. IEEE. https://doi.org/10.1109/ICRA48891.2023.10161314.
14.
SoltanpourMBoulangerPBuckB. CT perfusion map synthesis from CTP dynamic images using a learned LSTM generative adversarial network for acute ischemic stroke assessment. J Med Syst2024; 48(1). 37. https://doi.org/10.1007/s10916-024-02054-2
15.
BaurCMilletariFBelagiannisV, et al. Automatic 3D reconstruction of electrophysiology catheters from two-view monoplane C-arm image sequences. Int J Comput Assist Radiol Surg2016; 11(7). 1319–1328. https://doi.org/10.1007/s11548-015-1325-8
16.
BaurCAlbarqouniSDemirciS, et al. CathNets: Detection and single-view depth prediction of catheter electrodes. In: ZhengGLiaoHJanninP, et al. (eds) Medical imaging and augmented reality. Springer International Publishing, 2016, pp. 38–49, Vol. 9805. Series Title: Lecture Notes in Computer Science.
17.
TrivisonneRKerrienECotinS. Constrained stochastic state estimation of deformable 1D objects: application to single-view 3D reconstruction of catheters with radio-opaque markers. Comput Med Imaging Graph2020; 81: 101702. https://doi.org/10.1016/j.compmedimag.2020.101702
18.
OtakeYMurphyRJKutzerMD, et al. Piecewise-rigid 2D-3D registration for pose estimation of snake-like manipulator using an intraoperative X-ray projection. In: Proc. SPIE 9036, medical imaging 2014: image-guided procedures, robotic interventions, and modeling, 2014, p.90360Q. https://doi.org/10.1117/12.2043242
19.
RalovichKJohnMCamusE, et al. 6DoF catheter detection, application to intracardiac echocardiography. In: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2014, 2014, pp. 635–642, vol. 8674. Springer International Publishing. Series Title: Lecture Notes in Computer Science. https://doi.org/10.1007/978-3-319-10470-6_79
20.
HattCRSpeidelMARavalAN. Real-time pose estimation of devices from X-ray images: application to X-ray/echo registration for cardiac interventions. Med Image Anal2016; 34: 101–108. https://doi.org/10.1016/j.media.2016.04.008
21.
Al-AhmadOOurakMVan RoosbroeckJ, et al. Improved FBG-based shape sensing methods for vascular catheterization treatment. IEEE Robot Autom Lett2020; 5(3): 4687–4694. https://doi.org/10.1109/LRA.2020.3003291
22.
ChenXYZhangYNShenLY, et al. Fabrication and shape detection of a catheter using fiber Bragg grating. Adv Manuf2020; 8(1). 107–118. https://doi.org/10.1007/s40436-019-00284-z
23.
KhanFDenasiABarreraD, et al. Multi-core optical fibers with Bragg gratings as shape sensor for flexible medical instruments. IEEE Sens J2019; 19(14). 5878–5884. https://doi.org/10.1109/JSEN.2019.2905010
24.
WangFJiangQLiJ. Shape sensing for continuum robots using FBG sensors array considering bending and twisting. IEEE Sens J2024; 24(2). 1546–1554. https://doi.org/10.1109/JSEN.2023.3337419
25.
OurakMBuckSDHaXT, et al. Fusion of biplane fluoroscopy with fiber Bragg grating for 3D catheter shape reconstruction. IEEE Robot Autom Lett2021; 6(4). 6505–6512. https://doi.org/10.1109/LRA.2021.3094238
26.
AnfinogentovVKarimovKKuznetsovA, et al. Algorithm of FBG spectrum distortion correction for optical spectra analyzers with CCD elements. Sensors2021; 21(8). 2817. https://doi.org/10.3390/s21082817
27.
FranzAMHaideggerTBirkfellnerW, et al. Electromagnetic tracking in Medicine—a review of technology, validation, and applications. IEEE Trans Med Imaging2014; 33(8). 1702–1725. https://doi.org/10.1109/TMI.2014.2321777
28.
PengWWuWZhangJ, et al. An automatic framework for estimating the pose of the catheter distal section using a coarse-to-fine network. Comput Methods Programs Biomed2022; 225: 107036. https://doi.org/10.1016/j.cmpb.2022.107036
29.
MooreERobsonAJCrispAR, et al. Study of the structure of hyperbranched polyglycerol coatings and their antibiofouling and antithrombotic applications. Adv Healthc Mater2024; 13: 2401545. https://doi.org/10.1002/adhm.202401545
30.
MarianiELisignoliGBorzìRM, et al. Biomaterials: foreign bodies or tuners for the immune response?Int J Mol Sci2019; 20(3): 636. https://doi.org/10.3390/ijms20030636
31.
PedrazaZSLiuBWangX. Materials advancements for the safety and patency of implantable cardiovascular devices. Nano Res2024; 17(10). 8977–8989. https://doi.org/10.1007/s12274-024-6808-x
32.
HuangXLiGHuB, et al. The safety and feasibility of using a 5-Fr guiding catheter with a 0.035-inch guidewire in place for cerebral angiography. Medicine2024; 103(1). e36896. https://doi.org/10.1097/MD.0000000000036896
33.
JaganathanSRyanSGuptaA, et al. Guide-wire: a revisit to the basic building blocks. What an interventionist need to know?J Vasc Interv Radiol2016; 27(3). S223. https://doi.org/10.1016/j.jvir.2015.12.574
34.
Medical Advisory Secretariat. Hydrophilic catheters: an evidence-based analysis. Ont Heal Technol Assess Ser2006; 6(9): 1–31.
35.
AjdnikULuxbacherTVeselA, et al. Polysaccharide-based bilayer coatings for biofilm-inhibiting surfaces of medical devices. Materials2021; 14: 4720. https://doi.org/10.3390/ma14164720
36.
JiaYYangYZhangH. Comparative study on the lubrication mechanism and performance of two representative ionic and nonionic self-adhesive polymer coatings. Langmuir2024; 40(15). 8271–8283. https://doi.org/10.1021/acs.langmuir.4c00539
37.
ShareiHAlderliestenTvan den DobbelsteenJJ, et al. Navigation of guidewires and catheters in the body during intervention procedures: a review of computer-based models. J Med Imaging2018; 5(1). 1. https://doi.org/10.1117/1.JMI.5.1.010902
38.
YamamotoAIshiharaATomitaM, et al. Permanent magnet with MgB2 bulk superconductor. Appl Phys Lett2014; 105(3). 032601. https://doi.org/10.1063/1.4890724
39.
ZhouFFLiuYHGePC, et al. Coronary artery diameter is inversely associated with the severity of coronary lesions in patients undergoing coronary angiography. Cell Physiol Biochem2017; 43(3). 1247–1257. https://doi.org/10.1159/000481765
40.
ZhaoYLiweiSWeiW, et al. Intraoperative 3D shape estimation of magnetic soft guidewire. In: 2025 IEEE international conference on robotics and automation (ICRA 2025), Atlanta, 19–23 May 2025, pp. 10674–10680.
41.
BansalDGuptaSHKaurH. Design and analysis of a 4x4 antenna array. In: 2024 10th International conference on advanced computing and communication systems (ICACCS), 2014, pp. 1409–1415. IEEE. https://doi.org/10.1109/ICACCS60874.2024.10716947.
42.
CharlesRQSuHKaichunM, et al. PointNet: deep learning on point sets for 3D classification and segmentation. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 77–85. IEEE. https://doi.org/10.1109/CVPR.2017.16.
43.
ÇatalbaşBand Morgül Ö. Deep learning with extendeD Exponential Linear Unit (DELU). Neural Comput Appl2023; 35(30). 22705–22724. https://doi.org/10.1007/s00521-023-08932-z
44.
ClevertDAUnterthinerTHochreiterS. Fast and accurate deep network learning by exponential linear units (ELUs). arXiv:1511.07289, 2016. https://doi.org/10.48550/arXiv.1511.07289
45.
ZhangZ. A flexible new technique for camera calibration. IEEE Trans Pattern Anal Mach Intell2000; 22(11). 1330–1334. https://doi.org/10.1109/34.888718
46.
HartleyRI. In defense of the eight-point algorithm. IEEE Trans Pattern Anal Mach Intell1997; 19(6). 580–593. https://doi.org/10.1109/34.601246
47.
JäckleSGarcía-VázquezVVon HaxthausenF, et al. 3D catheter guidance including shape sensing for endovascular navigation. In: Medical Imaging 2020: Image-Guided Procedures, Robotic Interventions, and Modeling, 2020, p.3. SPIE. https://doi.org/10.1117/12.2548094.
48.
GuptaAChhikaraSVijayvergiyaR, et al. Radiation exposure reduction and patient outcome by using very low frame rate fluoroscopy protocol (3.8 + 7.5 fps) during percutaneous coronary intervention. Front Cardiovasc Med2021; 8: 625873. https://doi.org/10.3389/fcvm.2021.625873
