arXiv subjects

Simon Weinmüller

Publications and source records attributed to Simon Weinmüller.

5 recordsLinked to original sources

arXiv2026

Agentic MR sequence development: leveraging LLMs with MR skills for automatic physics-informed sequence development

Purpose: Novel MR sequence developments still today allow generation of new diagnostic tools or novel imaging biomarkers. Programming MRI pulse sequences, however, is time-consuming and requires deep expertise in sequence design, restrictions by hardware constraints and MRI physics; even small modifications often require substantial debugging and validation. LLMs can assist when given structured prompts and error feedback, but many generated sequences still exhibit physical inconsistencies. We present Agent4MR, an agent-based framework that automatically generates and refines PyPulseq sequences using a structured, physics-aware validation report. These agents can perform also autonomous research. Methods: We evaluated Agent4MR on a spin-echo EPI task across three state-of-the-art LLMs and compared it to a context-only baseline (LLM4MR) and to a human developer with the same tools. We tested an MR autoresearch on a fluid-suppressed spin-echo EPI challenge for three different model generations. Results: Across all models, Agent4MR consistently produced artifact-free, physically valid sequences in a single user interaction, reducing the number of required interactions below the human baseline while maintaining correct timing and k-space coverage. Autonomous agents could then improve a sequence to match a given target contrast in an autoresearch approach. Conclusion: An appropriate agentic harness with physics-based validation can turn general-purpose LLMs into reliable MRI sequence developers and may ultimately enable non-experts to refine or innovate MR sequences guided by biological or clinical questions, or let swarms of agents realize sequence programming for them. Keywords: MRI; pulse sequence; PyPulseq; large language models; agents; autoresearch, sequence development.

physics.med-ph↗

arXiv2024

Controlling sharpness, SNR and SAR for 3D FSE at 7T by end-to-end learning

Purpose: To non-heuristically identify dedicated variable flip angle (VFA) schemes optimized for the point-spread function (PSF) and signal-to-noise ratio (SNR) of multiple tissues in 3D FSE sequences with very long echo trains at 7T. Methods: The proposed optimization considers predefined SAR constraints and target contrast using an end-to-end learning framework. The cost function integrates components for contrast fidelity (SNR) and a penalty term to minimize image blurring (PSF) for multiple tissues. By adjusting the weights of PSF/SNR cost-function components, PSF- and SNR-optimized VFAs were derived and tested in vivo using both the open-source Pulseq standard on two volunteers as well as vendor protocols on a 7T MRI system with parallel transmit extension on three volunteers. Results: PSF-optimized VFAs resulted in significantly reduced image blurring compared to standard VFAs for T2w while maintaining contrast fidelity. Small white and gray matter structures, as well as blood vessels, are more visible with PSF-optimized VFAs. Quantitative analysis shows that the optimized VFA yields 50% less deviation from a sinc-like reference PSF than the standard VFA. The SNR-optimized VFAs yielded images with significantly improved SNR in a white and gray matter region relative to standard (81.2\pm18.4 vs. 41.2\pm11.5, respectively) as trade-off for elevated image blurring. Conclusion: This study demonstrates the potential of end-to-end learning frameworks to optimize VFA schemes in very long echo trains for 3D FSE acquisition at 7T in terms of PSF and SNR. It paves the way for fast and flexible adjustment of the trade-off between PSF and SNR for 3D FSE.

physics.med-ph↗

arXiv2024

MR-zero meets FLASH -- Controlling the transient signal decay in gradient- and rf-spoiled gradient echo sequences

Abstract Purpose The complex signal decay during the transient FLASH MRI readout can lead to artifacts in magnitude and phase images. We show that target-driven optimization of individual rf flip angles and phases can realize near-ideal signal behavior and mitigate artifacts. Methods The differentiable end-to-end optimization framework MR-zero is used to optimize rf trains of the FLASH sequence. We focus herein on minimizing deviations from the ideally spoiled signal by using a mono-exponential Look-Locker target. We first obtain the transient FLASH signal decay substructure, and then minimize the deviation to the Look-Locker decay by optimizing the individual (i) flip angles, (ii) rf phases and (iii) flip angles and rf phases. Comparison between measurement and simulation are performed using Pulseq in 1D and 2D. Results We could reproduce the complex substructure of the transient FLASH signal decay. All three optimization objectives can bring the real FLASH signal closer to the ideal case, with best results when both flip angles and rf phases are adjusted jointly. This solution outperformed all tested conventional quadratic rf cyclings in terms of (i) matching the Look-Locker target signal, (ii) phase stability, (iii) PSF ideality, (iv) robustness against parameter changes, and (v) magnitude and phase image quality. Other target functions for the signal could as well be realized, yet, their response is not as general as for the Look-Locker target and need to be optimized for a specific context. Conclusion Individual flip angle and rf phase optimization improves the transient signal decay of FLASH MRI sequences.

physics.med-ph↗

arXiv2022

snapshot CEST++ : the next snapshot CEST for fast whole-brain APTw imaging at 3T

CEST suffers from two main problems long acquisitin times or restricted coverage as well as incoherent protocol settings. In this paper we give suggestions on how to optimise your protocol settings fro CEST and present one setting for APT CEST. To increase the coverage while keeping the acquisition time constant we suggest using a spatial temporal Compressed Sensing approach. Finally, 1.8mm isotropic whole brain APT CEST maps can be acquired in a little bit less than 2min with a fully integrated online reconstruction. This will pave the way to an even further clinical use of CEST.

physics.med-ph↗

arXiv2021

MRzero -- Fully automated discovery of MRI sequences using supervised learning

Purpose: A supervised learning framework is proposed to automatically generate MR sequences and corresponding reconstruction based on the target contrast of interest. Combined with a flexible, task-driven cost function this allows for an efficient exploration of novel MR sequence strategies. Methods: The scanning and reconstruction process is simulated end-to-end in terms of RF events, gradient moment events in x and y, and delay times, acting on the input model spin system given in terms of proton density, T1 and T2, and $Δ$B0. As a proof of concept, we use both conventional MR images and T1 maps as targets and optimize from scratch using the loss defined by data fidelity, SAR penalty, and scan time. Results: In a first attempt, \textit{MRzero} learns gradient and RF events from zero, and is able to generate a target image produced by a conventional gradient echo sequence. Using a neural network within the reconstruction module allows arbitrary targets to be learned successfully. Experiments could be translated to image acquisition at the real system (3T Siemens, PRISMA) and could be verified in the measurements of phantoms and a human brain \textit{in vivo}. Conclusions: Automated MR sequence generation is possible based on differentiable Bloch equation simulations and a supervised learning approach.

physics.med-ph↗