Harmonic-Aware Transformer for Real-Time Catheter Localization in Interventional Procedures of Magnetic Particle Imaging

• URL: http://arxiv.org/abs/2607.02919v1
• Date: Fri, 03 Jul 2026 03:24:27 GMT
• Title: Harmonic-Aware Transformer for Real-Time Catheter Localization in Interventional Procedures of Magnetic Particle Imaging
• Abstract summary: This study proposes a harmonic-aware transformer framework that directly predicts catheter tip positions from raw MPI voltage signals.<n>The framework incorporates frequency-domain preprocessing to isolate the 2nd to 8th drive-field harmonics, enhancing the signal-to-noise ratio.<n>The proposed method achieves sub-millimeter localization accuracy, with a minimum L2 error of 0.103 +/- 0.092 mm.
• Score: 3.1202994773978734
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Magnetic particle imaging (MPI) enables real-time, radiation-free tracking of magnetic nanoparticle-coated instruments, making it highly suitable for interventional procedures. This study proposes a harmonic-aware transformer framework that directly predicts catheter tip positions from raw MPI voltage signals, eliminating the need for image reconstruction and reducing computational latency. The framework incorporates frequency-domain preprocessing to isolate the 2nd to 8th drive-field harmonics, enhancing the signal-to-noise ratio while preserving motion-relevant features. A transformer architecture with six encoder layers and eight attention heads is employed to learn spatio-temporal dependencies across the three receive axes (x, y, z) for accurate three-dimensional position estimation. The model is trained on simulated MPI signals and evaluated on real in vitro datasets under standard, bending, and heartbeat-like motion conditions. The proposed method achieves sub-millimeter localization accuracy, with a minimum L2 error of 0.103 +/- 0.092 mm and mean absolute errors (MAEs) of 0.039 +/- 0.046 mm, 0.054 +/- 0.049 mm, and 0.060 +/- 0.044 mm along the (x, y, z) axes, respectively, for the bending dataset. Across all datasets, the MAE ranges from 0.165 mm to 0.655 mm, demonstrating consistent performance. The optimized inference achieves a latency of 0.55 ms per frame and a throughput of approximately 1800 frames per second, confirming real-time capability. Compared with conventional MPI-guided approaches relying on image reconstruction, the proposed framework provides improved accuracy, reduced latency, and enhanced robustness under complex motion conditions. These results highlight the potential of harmonic-aware transformer models as efficient and scalable solutions for real-time catheter localization in interventional MPI.

Related papers

• Efficient Conversion of Optical to Mechanical States Close to the Single-Quantum Level [38.53693460708997]
  We show efficient low-noise photon-phonon state transfer close to the single-quantum regime in an optomechanical crystal operated at Millikelvin temperatures.<n>We achieve a record-level photon-phonon conversion efficiency of $=0.76$, a mechanical storage lifetime of $T_mathrm1=7.3s$, and a tunable conversion bandwidth exceeding 4.5 MHz.
  arXiv  Detail & Related papers  (2026-09-03T17:43:22Z)
• Magnetically Self-Sealed MR Haptic Actuator With PWM-Based Excitation and High-Fidelity Torque Control [10.326757545448457]
  Magnetorheological fluid (MRF)-based actuators offer a compact and rapidly controllable solution for haptic feedback.<n>Practical implementation requires reliable fluid sealing, low-hysteresis, accurate torque control, and stable long-duration operation.<n>This article presents an integrated MRF haptic system featuring a compact magnetically self-sealed rotary actuator.
  arXiv  Detail & Related papers  (2026-08-20T05:04:25Z)
• Beyond Control Points: Arcsecond Relative-Motion Estimation of Vision Measurement Platforms With Incomplete or Absent Control Fields [43.43572961146893]
  We develop a control-adaptive differential framework that estimates platform motion directly from image displacements and known 3D points.<n>We derive the rotation observability condition, a leakage bound for unmodeled translation and nonrigid point motion, and the single-point axial-prior bias law.
  arXiv  Detail & Related papers  (2026-08-14T03:41:30Z)
• Differential 6-DOF Pose Estimation with Provable First-Order Immunity to Camera Calibration Errors [39.41872679860813]
  Conventional 3D-2D methods estimate absolute camera poses independently each time and recover platform motion through camera-to-platform poses.<n>We present a differential pose estimation method that directly recovers platform motion from inter-frame image displacements and known 3D control points.<n>We prove that extrinsic errors cancel exactly, while rotational errors induce a bounded perturbation determined by calibration error, motion, magnitude and observation geometry.
  arXiv  Detail & Related papers  (2026-08-05T10:36:04Z)
• MimicIK: Real-Time Generative Inverse Kinematics from Teleoperation with FK Consistency [25.059681949019488]
  Inverse kinematics (IK) remains a critical bottleneck for real-time robot manipulation.<n>MimicIK is a real-time generative inverse kinematics framework that learns smooth and robust joint-space motion priors from teleoperation demonstrations.<n>MimicIK achieves a mean position error of 4.65 mm, a 10 mm success rate of 92.01%, and a trajectory spike rate of only 7.99%.
  arXiv  Detail & Related papers  (2026-06-13T06:32:08Z)
• Valley-Aware Optimal Control of Spin Shuttling Using Cryogenic Integrated Electronics [33.72751145910978]
  An end-to-end co-simulation framework combines disorder-informed valley maps with transistor-level cryogenic circuit simulations.<n>A fully integrated cryogenic shuttling-signal generator tailored to velocity modulation enables period-wise waveform shaping.<n>Across simulated valley and noise realizations in our co-simulation framework, the optimized velocity-modulation waveforms improve transport performance.
  arXiv  Detail & Related papers  (2026-04-22T12:14:16Z)
• Spatiotemporal Gaussian representation-based dynamic reconstruction and motion estimation framework for time-resolved volumetric MR imaging (DREME-GSMR) [6.0648709483311185]
  Time-resolved MR imaging that reconstructs a 3D MRI within sub-seconds to resolve deformable motion robustness is essential for motion-adaptive radiotherapy.<n>We developed a framework which enables time-resolved dynamic MRI reconstruction from a pre-resolved 3D MR scan without any anatomical/motion model.<n>DREME-R reconstructs MRIs of a 400ms temporal resolution, with an inference time of 10ms/time.
  arXiv  Detail & Related papers  (2026-04-07T21:34:54Z)
• QDsiM: A Noise-Aware Simulation Toolkit for Quantum Diamond Microscope [10.814244923718405]
  The nitrogen-vacancy (NV) center in diamond is a leading solid-state platform for room-temperature quantum magnetometry.<n>We present a comprehensive simulation framework, for continuous-wave wide-field ODMR in NV-center ensembles.
  arXiv  Detail & Related papers  (2026-01-15T09:13:39Z)
• Res-MoCoDiff: Residual-guided diffusion models for motion artifact correction in brain MRI [4.893666625661374]
  Motion artifacts in brain MRI, mainly from rigid head motion, degrade image quality and hinder downstream applications.<n>This study introduces Res-MoCoDiff, an efficient denoising diffusion probabilistic model specifically designed for MRI motion artifact correction.<n>The proposed method demonstrated superior performance in removing motion artifacts across minor, moderate, and heavy distortion levels.
  arXiv  Detail & Related papers  (2025-05-06T13:02:40Z)
• Future frame prediction in chest cine MR imaging using the PCA respiratory motion model and dynamically trained recurrent neural networks [0.0]
  Lung radiotherapy treatment systems are subject to a latency that leads to uncertainty in the estimated tumor location and high irradiation of healthy tissue. This work addresses future frame prediction in chest dynamic MRI sequences to compensate for that delay using RNNs trained with online learning algorithms.
  arXiv  Detail & Related papers  (2024-10-08T10:21:43Z)
• Direct Zernike Coefficient Prediction from Point Spread Functions and Extended Images using Deep Learning [36.136619420474766]
  Existing adaptive optics systems rely on iterative search algorithm to correct for aberrations and improve images. This study demonstrates the application of convolutional neural networks to characterise the optical aberration.
  arXiv  Detail & Related papers  (2024-04-23T17:03:53Z)
• Near-video frame rate quantum sensing using Hong-Ou-Mandel interferometry [3.882519884342634]
  Hong-Ou-Mandel interference has emerged as a promising tool for quantum sensing. We show the generation of photon-pairs with flexible spectral-bandwidth using single-frequency, continuous-wave diode laser.
  arXiv  Detail & Related papers  (2023-04-26T05:57:42Z)
• Digital noise spectroscopy with a quantum sensor [57.53000001488777]
  We introduce and experimentally demonstrate a quantum sensing protocol to sample and reconstruct the auto-correlation of a noise process. Walsh noise spectroscopy method exploits simple sequences of spin-flip pulses to generate a complete basis of digital filters. We experimentally reconstruct the auto-correlation function of the effective magnetic field produced by the nuclear-spin bath on the electronic spin of a single nitrogen-vacancy center in diamond.
  arXiv  Detail & Related papers  (2022-12-19T02:19:35Z)
• Centimeter-Wave Free-Space Time-of-Flight Imaging [25.15384123485028]
  We propose a computational imaging method for all-optical free-space correlation before photo-conversion that achieves micron-scale depth resolution. We propose an imaging approach with resonant polarization modulators and devise a novel optical dual-pass frequency-doubling which achieves high modulation contrast at more than 10GHz. We validate the proposed method in simulation and experimentally, where it achieves micron-scale depth precision.
  arXiv  Detail & Related papers  (2021-05-25T01:57:10Z)

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.