NeuroAgent: LLM Agents for Multimodal Neuroimaging Analysis and Research
Lujia Zhong, Yihao Xia, Jianwei Zhang, Shuo huang, Jiaxin Yue, Mingyang Xia, Yonggang Shi
Why It Matters
What makes this one worth your time
This work addresses significant barriers in neuroimaging analysis, potentially accelerating research and improving reproducibility in a critical area of medical science.
NeuroAgent automates neuroimaging analysis, enhancing reproducibility and efficiency in Alzheimer's research.
Summary
The paper introduces NeuroAgent, an LLM-driven framework that automates preprocessing and analysis of multimodal neuroimaging data, demonstrating its effectiveness through evaluations on a large dataset related to Alzheimer's Disease.
Key contributions
- Development of an LLM-driven agentic framework for neuroimaging analysis.
- Implementation of a feedback-driven Generate-Execute-Validate engine for error recovery.
- Demonstration of high intent-parsing accuracy and effective multimodal classification performance.
Notable insights
- The use of a hierarchical multi-agent architecture allows for modular and scalable processing of diverse neuroimaging modalities.
- The feedback-driven Generate-Execute-Validate engine enhances robustness by autonomously recovering from errors during preprocessing.
Possible limitations
- Not stated in the abstract.
Abstract
arXiv:2605.06584v1 Announce Type: new Abstract: Multimodal neuroimaging analysis often involves complex, modality-specific preprocessing workflows that require careful configuration, quality control, and coordination across heterogeneous toolchains. Beyond preprocessing, downstream statistical analysis and disease classification commonly require task-specific code, evaluation protocols, and data-format conventions, creating additional barriers between raw acquisitions and reproducible scientific analysis. We present NeuroAgent, an LLM-driven agentic framework that automates key preprocessing and analysis steps for heterogeneous neuroimaging data, including sMRI, fMRI, dMRI, and PET, and supports interactive downstream analysis through natural-language queries. NeuroAgent employs a hierarchical multi-agent architecture with a feedback-driven Generate-Execute-Validate engine: agents autonomously generate executable preprocessing code, detect and recover from runtime errors, and validate output integrity. We evaluate the system on 1,470 subjects pooled across all ADNI phases (CN=1,000, AD=470), where all subjects have sMRI and tabular data, with subsets also having Tau-PET (n=469), fMRI (n=278), and DTI ($n=620$). Pipeline ablation studies across multiple LLM backends show that capable models reach up to 100% intent-parsing accuracy, with the strongest backend (Qwen3.5-27B) reaching 84.8% end-to-end preprocessing step correctness. Automated recovery limits manual intervention to edge cases where human review is required via the Human-In-The-Loop interface. For Alzheimer's Disease classification using automatically preprocessed multimodal data, our agent ensemble achieves an AUC of 0.9518 with four modalities, outperforming all single-modality baselines. These results show that NeuroAgent can reduce the manual effort required for neuroimaging preprocessing and enable end-to-end automated analysis pipelines for neuroimaging research.