Fast Machine Learning Image Reconstruction of Radially Undersampled K-Space Data for Low-Latency Real-Time MRI

MCML Authors

Johanna Topalis

→ Group Michael Ingrisch
 Clinical Data Science in Radiology

Jakob Dexl

→ Group Michael Ingrisch
 Clinical Data Science in Radiology

Katharina Jeblick

Dr.

→ Group Michael Ingrisch
 Clinical Data Science in Radiology

Andreas Mittermeier

Dr.

→ Group Michael Ingrisch
 Clinical Data Science in Radiology

Balthasar Schachtner

Dr.

→ Group Michael Ingrisch
 Clinical Data Science in Radiology

Theresa Stüber

→ Group Michael Ingrisch
 Clinical Data Science in Radiology

Tobias Weber

* Former Member

→ Group Bernd Bischl
 Statistical Learning and Data Science

Philipp Wesp

Dr.

→ Group Michael Ingrisch
 Clinical Data Science in Radiology

Michael Ingrisch

Prof. Dr.

Principal Investigator

Clinical Data Science in Radiology

Abstract

Fast data acquisition and fast image reconstruction are essential to enable low-latency real-time magnetic resonance (MR) imaging applications with high temporal resolution such as interstitial percutaneous needle interventions or MR-guided radiotherapy. To accelerate the image reconstruction of radially undersampled 2D k-space data, we propose a machine learning (ML) model that consists of a single fully connected linear layer to interpolate radial k-space data to a Cartesian grid, followed by a conventional 2D inverse fast Fourier transform. This k-space-to-image ML model was trained on synthetic data from natural images. It was evaluated with respect to image quality (mean squared error (MSE) compared to ground truth where available) and reconstruction time both on synthetic data with undersampling factors R between 2 and 10 as well as on radial k-space data from MR measurements on two different MRI systems. For comparison, conventional non-iterative zero-filling non-uniform fast Fourier transform (NUFFT) reconstruction and compressed sensing (CS) reconstruction were used. On synthetic data, the ML model achieved better median MSE values than the non-iterative NUFFT reconstruction. The interquartile ranges of the MSE distributions overlapped for the ML and CS reconstructions for all R. Reconstruction times of the ML approach were shorter than for NUFFT and substantially shorter than for CS reconstructions. The generalizability (for real MRI data) of the ML model was demonstrated by reconstructing 0.35-tesla MR-Linac dynamic measurements of three volunteers and phantom data from a diagnostic 1.5-tesla MRI system; the median reconstruction time for the coil-combined images was much shorter than for the conventional approach (ML: ; NUFFT: ). The proposed ML model reconstructs MR data with reduced streaking artifacts compared to non-iterative NUFFT techniques and with extremely short reconstruction times; thus, it is ideally suited for rapid low-latency real-time MR applications.

article TDJ+25

PLOS One

Authors

Links

Research Areas

 A1 | Statistical Foundations & Explainability

 C1 | Medicine