EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep learning–based prospective slice tracking for continuous catheter visualization during MRI ‐guided cardiac catheterization

Alexander Paul Neofytou iD, Grzegorz Kowalik, Rohini Vidya Shankar, Karl Kunze, Tracy Moon, Nina Mellor, Radhouene Neji, Reza Razavi, Kuberan Pushparajah, Sébastien Roujol iD

Magnetic Resonance in Medicine · 2025

DOI: 10.1002/mrm.30574 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Magnetic Resonance in Medicine, 2025. Verfasst von Alexander Paul Neofytou und 9 weiteren Autor:innen. Beteiligte Einrichtung: School of Biomedical Engineering and Imaging Sciences, Faculty of Life Sciences and Medicine, King's College London, London, UK. Hauptthemen laut MEDLINE: Deep Learning, Cardiac Catheterization, Magnetic Resonance Imaging, Magnetic Resonance Imaging, Interventional. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Siemens Healthineers, King's College London, British Heart Foundation (BHF).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

This proof‐of‐concept study introduces a novel, deep learning–based, parameter‐free, automatic slice‐tracking technique for continuous catheter tracking and visualization during MR‐guided cardiac catheterization.

Methods

The proposed sequence includes Calibration and Runtime modes. Initially, Calibration mode identifies the catheter tip's three‐dimensional coordinates using a fixed stack of contiguous slices. A U‐Net architecture with a ResNet‐34 encoder is used to identify the catheter tip location. Once identified, the sequence then switches to Runtime mode, dynamically acquiring three contiguous slices automatically centered on the catheter tip. The catheter location is estimated from each Runtime stack using the same network and fed back to the sequence, enabling prospective slice tracking to keep the catheter in the central slice. If the catheter remains unidentified over several dynamics, the sequence reverts to Calibration mode. This artificial intelligence (AI)–based approach was evaluated prospectively in a three‐dimensional‐printed heart phantom and 3 patients undergoing MR‐guided cardiac catheterization. This technique was also compared retrospectively in 2 patients with a previous non‐AI automatic tracking method relying on operator‐defined parameters.

Results

In the phantom study, the tracking framework achieved 100% accuracy/sensitivity/specificity in both modes. Across all patients, the average accuracy/sensitivity/specificity were 100 ± 0/100 ± 0/100 ± 0% ( Calibration ) and 98.4 ± 0.8/94.1 ± 2.9/100.0 ± 0.0% ( Runtime ). The parametric, non‐AI technique and the proposed parameter‐free AI‐based framework yielded identical accuracy (100%) in Calibration mode and similar accuracy range in Runtime mode (Patients 1 and 2: 100%–97%, and 100%–98%, respectively).

Conclusion

An AI‐based prospective slice‐tracking framework was developed for real‐time, parameter‐free, operator‐independent, automatic tracking of gadolinium‐filled balloon catheters. Its feasibility was successfully demonstrated in patients undergoing MRI‐guided cardiac catheterization.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningCardiac CatheterizationMagnetic Resonance ImagingMagnetic Resonance Imaging, InterventionalImage Processing, Computer-AssistedHumansPhantoms, ImagingProspective StudiesHeartImaging, Three-DimensionalAlgorithmsCalibration

Stichwörter der Autor:innen

MR guidancecardiac catheterizationdeep learningpassive trackingreal time

Autor:innen und Institutionen

  • School of Biomedical Engineering and Imaging Sciences, Faculty of Life Sciences and Medicine, King's College London, London, UK.
  • MR Research Collaborations, Siemens Healthcare Limited, Camberley, UK.
  • Department of Paediatric Cardiology, Evelina London Children's Hospital, London, UK.

ORCID-Profile: Alexander Paul Neofytou, Sébastien Roujol

Förderung

  • Siemens Healthineers
  • King's College London
  • British Heart Foundation (BHF)
  • Guy's and St Thomas' National Health Service (NHS)
  • National Institute for Health Research (NIHR) Biomedical Research Centre
  • EPSRC Doctoral Training Partnership
  • Engineering and Physical Sciences Research Council (EPSRC)
  • Wellcome Trust

Zitieren

APA

Neofytou, A. P., Kowalik, G., Vidya Shankar, R., Kunze, K., Moon, T., Mellor, N., Neji, R., Razavi, R., Pushparajah, K., & Roujol, S. (2025). Deep learning–based prospective slice tracking for continuous catheter visualization during MRI ‐guided cardiac catheterization. Magnetic Resonance in Medicine. https://doi.org/10.1002/mrm.30574

Vancouver

Neofytou AP, Kowalik G, Vidya Shankar R, Kunze K, Moon T, Mellor N, et al. Deep learning–based prospective slice tracking for continuous catheter visualization during MRI ‐guided cardiac catheterization. Magnetic Resonance in Medicine. 2025. doi:10.1002/mrm.30574

BibTeX
@article{Neofytou2025,
  author = {Neofytou, Alexander Paul and Kowalik, Grzegorz and Vidya Shankar, Rohini and Kunze, Karl and Moon, Tracy and Mellor, Nina and Neji, Radhouene and Razavi, Reza and Pushparajah, Kuberan and Roujol, Sébastien},
  title = {Deep learning–based prospective slice tracking for continuous catheter visualization during MRI ‐guided cardiac catheterization},
  journal = {Magnetic Resonance in Medicine},
  year = {2025},
  doi = {10.1002/mrm.30574}
}
Kostenlos starten →