Agentic LLM Workflow for MR Spectroscopy Volume-of-Interest Placements in Brain Tumors

TL;DR

This paper introduces an agentic LLM workflow that generates and selects optimal VOI placements for brain tumor MRS, improving coverage and customization based on clinical preferences.

Contribution

It presents a novel LLM-based workflow that generates multiple VOI options and selects the best one, enhancing flexibility and accuracy in tumor spectroscopy.

Findings

Improved tumor coverage in clinical cases

Enhanced necrosis avoidance based on preferences

Flexible VOI placement without retraining models

Abstract

Magnetic resonance spectroscopy (MRS) provides clinically valuable metabolic characterization of brain tumors, but its utility depends on accurate placement of the spectroscopy volume-of-interest (VOI). However, VOI placement typically has a broad operating window: for a given tumor there are multiple possible VOIs that would lead to high-quality MRS measurements. Thus, a VOI place-ment can be tuned for clinician preference, case-specific anatomy, and clinical pri-orities, which leads to high inter-operator variability, especially for heterogeneous tumors. We propose an agentic large language model (LLM) workflow that de-composes VOI placement into generation of diverse candidate VOIs, from which the LLM selects an optimal one based on quantitative metrics. Candidate VOIs are generated by vision transformer-based placement models trained with differ-ent objective function preferences, which allows selection from acceptable alterna-tives rather than a single deterministic placement. On 110 clinical brain tumor cas-es, the agentic workflow achieves improved solid tumor coverage and necrosis avoidance depending on the user preferences compared to the general-purpose expert placements. Overall, the proposed workflow provides a strategy to adapt VOI placement to different clinical objectives without retraining task-specific models.