Harmonic-aware transformer for real-time catheter localization in interventional procedures of magnetic particle...

Objective.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.Approach.The framework incorporates frequency-domain preprocessing to isolate the 2nd-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 realin vitrodatasets under standard, bending, and heartbeat-like motion conditions.Main results.The proposed method achieves sub-millimeter localization accuracy, with a minimumL2error of0.103±0.092mm and mean absolute errors (MAEs) of0.039±0.046mm,0.054±0.049mm, and0.060±0.044mm along the(x,y,z)axes, respectively, for the bending dataset. Across all datasets, the MAE ranges from0.165mm to0.655mm, demonstrating consistent performance. The optimized inference achieves a latency of0.55ms per frame and a throughput of approximately1800frames s-1, confirming real-time capability.Significance.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.