Amr Aly | Searcharxiv

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

Verifying Shortest Paths in Linear Time

In this paper we propose a linear-time certifying algorithm for the single-source shortest-path problem capable of verifying graphs with positive, negative, and zero arc weights. Previously proposed linear-time approaches only work for graphs with positive arc weights.

cs.DS↗

arXiv2022

Model-Based Approaches to Channel Charting

We present new ways of producing a channel chart [1] employing model-based approaches. We estimate the angle of arrival theta and the distance rho between the base station and the user equipment by employing our algorithms, inverse of the root sum squares of channel coefficients (ISQ) algorithm, linear regression (LR) algorithm, and MUSIC/MUSIC (MM) algorithm. We compare these methods with the channel charting algorithms principal component analysis (PCA), Sammon's method (SM), and autoencoder (AE) [1]. We show that ISQ, LR, and MM surpass PCA, SM, and AE in performance. We also compare our algorithm MM with an algorithm from the literature that uses the MUSIC algorithm jointly on theta and rho. We call this algorithm the JM algorithm. JM performs very slightly better than MM but at a substantial increase in complexity. Finally, we introduce the rotate-and-sum (RS) algorithm which has about the same performance as the MM and JM algorithms. Unlike MUSIC, RS does not employ eigenvalue and eigenvector analysis. Thus, it is more suitable for direct register transfer logic (RTL) implementation.

cs.ET↗