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

TL;DR

This study uses AI to speed up MRI-guided prostate biopsies by reconstructing images from less data and tracking the biopsy needle in real-time.

Contribution

A deep-learning method for real-time image reconstruction and instrument tracking in MR-guided biopsies, validated in clinical settings.

Findings

The AI achieved high accuracy in predicting the needle tip position with up to 16× undersampled data.

Tracking success rates remained above 90% at 8× and 16× undersampling, but dropped at 18×.

The method supports faster procedures and improved scanner efficiency in clinical practice.

Abstract

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.

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.

Prospective feasibility study.

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.

2D Cartesian balanced steady‐state free precession, 3 T.

Segmentation and reconstruction models were trained on 8464 MRGB confirmation scans containing a biopsy needle guide instrument and evaluated on 10 prospectively acquired dynamic k‐space samples. Needle guide tracking accuracy was assessed using instrument tip prediction (ITP) error, computed per frame as the Euclidean distance from reference positions defined via pre‐ and post‐movement scans. Feasibility was measured by the proportion of frames with < 5 mm error. Additional experiments tested model robustness under increasing undersampling rates.

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.

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%).

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

2.

Stage 2.

Prostate biopsies guided by MRI are accurate but slow. This paper discusses a method to speed it up using artificial intelligence (AI). The method creates medical images from less data, allowing for the tracking of the biopsy needle guide tip in near real‐time. The AI was trained using 8464 scans of 1289 men and was then tested in 8 patients. Success was defined as the tip being within 5 mm of its actual position. The method stayed accurate with as little as one‐sixteenth of the usual data. Such speed‐ups could shorten procedures and free up scanner time.

Figures