Real-Time Deep-Learning Image Reconstruction and Instrument Tracking in MR-Guided Biopsies

📚 Citation

C. R. Noordman, S. J. W. Borgers, M. F. Boomsma, T. C. Kwee, M. M. G. van der Lees, C. G. Overduin, M. de Rooij, D. Yakar, J. J. Fütterer and H. J. Huisman, "Deep learning–based temporal MR image reconstruction for accelerated interventional imaging during in-bore biopsies" Journal of Medical Imaging 12, 3 (2025).

This paper is open access! →

Real-Time Deep-Learning Image Reconstruction and Instrument Tracking in MR-Guided Biopsies

📚 Citation

C. R. Noordman, L. P. W. te Molder, M. C. Maas, C. G. Overduin, J. J. Fütterer and H. J. Huisman, "Real-Time Deep-Learning Image Reconstruction and Instrument Tracking in MR-Guided Biopsies" Journal of Magnetic Resonance Imaging 63, 2 (2026).

This paper is open access! →

📖 Abstract

Background

Transrectal in-bore MR-guided biopsy (MRGB) is accurate but time-consuming, limiting clinical throughput. Faster imaging could improve workflow and enable real-time instrument tracking. Existing acceleration methods often use simulated data and lack validation in clinical settings.

Purpose

To accelerate MRGB by using deep learning for undersampled image reconstruction and instrument tracking, trained on multi-slice MR DICOM images and evaluated on raw k-space acquisitions.

Study Type Prospective feasibility study.

Population Briefly, 1289 male patients (aged 44–87, median age 68) for model training, 8 male patients (aged 59–78, median age 65) for prospective feasibility testing.

Field Strength/Sequence 2D Cartesian balanced steady-state free precession, 3 T.

Statistical Tests In a segmentation validation experiment, a one-sample t-test tested if the mean ITP error was below 5 mm. Statistical significance was defined as p < 0.05. In the tracking experiments, the mean, standard deviation, and Wilson 95% CI of the ITP success rate were computed per sample, across undersampling levels.

Results ITP was first evaluated independently on 201 fully sampled scans, yielding an ITP error of 1.55 ± 1.01 mm (95% CI: 1.41–1.69). Tracking performance was assessed across increasing undersampling factors, achieving high ITP success rates from 97.5% ± 5.8% (68.8%–99.9%) at 8× up to 92.5% ± 10.3% (62.5%–98.9%) at 16× undersampling. Performance declined at 18×, dropping to 74.6% ± 33.6% (43.8%–91.7%).

Data Conclusion Results confirm stable needle guide tip prediction accuracy and support the robustness of the reconstruction model for tracking at high undersampling.

**Evidence Level ** 2.

**Technical Efficacy ** Stage 2.