Closed-Loop Agentic AI for Executable and Reproducible Neuroimaging Research

Raw-Data-Aware Orchestration

NeuroClaw starts from raw multimodal data and uses dataset semantics, BIDS metadata, and workflow stage context to keep downstream analyses scientifically coherent.

Executable Harness Engineering

Managed Python environments, Docker support, GPU setup, checkpoints, artifact checks, and audit logs make neuroimaging toolchains easier to rerun and verify.

Hierarchical Skill Architecture

A three-tier interface, subagent, and base-skill design decomposes long neuroimaging workflows into controlled, reusable operations across tools, modalities, datasets, and models.

Benchmark-Grounded Evaluation

NeuroBench evaluates planning completeness, tool-use reasonableness, and command/code correctness under realistic neuroimaging tasks with and without NeuroClaw skills.

1. Basic Processing

1.1 Data I/O and BIDS: BIDS organization, DICOM→NIfTI, NIfTI→DICOM, metadata checks, and low-level NIfTI/FreeSurfer I/O with Nibabel.

1.2 Environment and Engineering: Conda, Docker, dependency planning, shell execution, Git workflows, Overleaf, harness utilities, and skill updates.

1.3 Research Discovery: academic literature search, multi-engine evidence collection, research idea generation, and method design support.

2. Tool-Centric Skills

2.1 Structural and Functional Toolchains: FreeSurfer, FSL, Nilearn, fMRIPrep, CONN, and HCP Pipelines for reconstruction, segmentation, registration, GLM, ICA, and connectivity.

2.2 Diffusion and Electrophysiology: DIPY, QSIPrep, and MNE support denoising, tensor metrics, tractography, EEG cleaning, and feature extraction.

2.3 Visualization and Clinical Interop: brain network visualization, zALFF regional summaries, FreeSurfer mesh export, and DICOM-compatible output conversion.

3. Modality-Centric Skills

3.1 sMRI: T1/T2 preprocessing, tissue segmentation, cortical parcellation, FreeSurfer surfaces, and WMH segmentation from FLAIR+T1w inputs.

3.2 fMRI: preprocessing, denoising, ROI time series, seed/ROI connectivity, task GLM, resting-state ICA, and effective connectivity routes.

3.3 DWI + EEG: eddy correction, diffusion tensor metrics, tractography, connectome construction, EEG artifact removal, spectral analysis, and feature extraction.

3.4 PET: SUVR computation with tracer-specific reference regions (PiB/FDG/tau), partial volume correction, multi-frame dynamic PET support, and ROI-based quantification.

3.5 ASL: CBF quantification via the Buxton model (pCASL/CASL/PASL), M0 normalization, partial volume correction, and ROI-based perfusion extraction.

3.6 MEG: source localization (MNE/dSPM/beamformer), time-frequency analysis (Morlet/multitaper), inter-trial coherence, and sensor/source-space connectivity.

4. Dataset-Centric Skills (29 public datasets)

4.1 UK Biobank: large-scale brain imaging data access, BIDS organization, multimodal sMRI/fMRI/dMRI processing, and phenotype extraction, covering ~50,000 participants.

4.2 ADNI: acquisition guidance, BIDS organization, preprocessing, ROI analysis, phenotype modeling, and derived dataset generation.

4.3 HCP Young Adult: download, BIDS staging, and multimodal sMRI/fMRI/dMRI processing across 7 task paradigms (motor, emotion, gambling, language, relational, social, working memory) and resting-state, with cognitive phenotype extraction and QC integration.

4.4 ABCD Study: download via NIMH Data Archive, BIDS organization, multimodal sMRI/fMRI/dMRI processing, phenotype extraction, and QC integration, covering ~11,500 participants aged 9-10.

Also covers HCP Aging, HCP Development, HCP Early Psychosis, AIBL, AOMIC, NIFD, OASIS, PNC, PPMI, REST-meta-MDD, SEED-IV, SEED-VIG, TCP, UCLA CNP, Cam-CAN, IXI, MS Challenge, MND, NSD, ABIDE, ADHD-200, BOLD5000, COBRE, DMT-HAR-MED, and HBN.

5. Model-Centric Skills

5.1 Deep Learning: BrainGNN, FM-APP, and NeuroStorm for phenotype prediction and neuroimaging representation learning.

5.2 Statistical and Classical ML: GLM, ICA, DictLearning, SVM, SpaceNet, K-means, hierarchical clustering, filtering, and detrending.

5.3 Model Routing: unified model entry with preprocessing dependency checks, input/output mapping, executable plans, and benchmark-friendly evaluation steps.

6. Research Workflow Skills

6.1 End-to-End Pipelines: single-modality chains for sMRI, fMRI, DWI, EEG, PET, ASL, and MEG, plus dataset-specific pipelines for 29 public neuroimaging datasets.

6.2 Experiment Control: METHOD-to-experiment execution, Git-based setup, ablations, checkpoints, verification, audit logs, and resumable runs.

6.3 Research Output: manuscript writing, clean dialogue logs, visualization assets, reproducibility reports, and maintainable skill-library updates.