skills.rest
CUHK-AIM-Group
CUHK-AIM-GroupOFFICIAL
Explore all skills by this author →
WebsiteGitHub

adhd200-skill

Orchestrates ADHD-200 dataset download, BIDS staging, and multimodal MRI processing workflows.

89|5|Updated Mar 25, 2026
Search Tags:#quality control#neuroimaging#fmri#nifti#bids#phenotype extraction#adhd-200
One-click install
npx skills add https://github.com/CUHK-AIM-Group/NeuroDiscovery --skill adhd200-skill-cuhk-aim-group
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: adhd200-skill
Source: https://github.com/CUHK-AIM-Group/NeuroDiscovery/tree/main/skills/adhd200-skill
Command: npx skills add https://github.com/CUHK-AIM-Group/NeuroDiscovery --skill adhd200-skill-cuhk-aim-group

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, and includes scripts (resource) components.

What problem does it solve? Working with the ADHD-200 dataset requires coordinating downloads from the FCP/INDI repository, converting heterogeneous multi-site raw NIfTI files into BIDS-compliant structure, merging scattered phenotype tables, and generating quality-control summaries. This Skill automates that entire orchestration so researchers avoid manual file wrangling across 8 imaging sites. ## Core Features & Use Cases - BIDS Reorganization: Converts raw ADHD-200 subject/site directories into BIDS-compliant layout with normalized subject IDs, modality routing (T1w to anat, rs-fMRI to func), sidecar preservation, and generated dataset_description.json plus participants.tsv. - Phenotype Extraction: Merges ADHD-200 phenotype CSV files (diagnosis, ADHD measures, demographics, medication), normalizes column names, filters by imaging subject IDs, and drops high-missingness columns. - QC Summaries: Parses fMRIPrep confounds files to compute per-subject mean/max framewise displacement and produces exclusion lists based on configurable FD thresholds. - Use Case: A researcher downloads ADHD-200 data from Peking and NYU sites, runs the reorganization script to produce a BIDS dataset, merges phenotype tables filtered to imaged subjects, and generates a QC exclusion list before running connectivity analysis. ## Quick Start Ask the agent to reorganize your local raw ADHD-200 NIfTI folders into a BIDS-compliant dataset with participants.tsv and dataset_description.json, optionally in dry-run mode first.

Frequently Asked Questions about adhd200-skill

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert ADHD-200 raw data to BIDS format?▼

Run the reorganize_adhd200.py script with --input pointing to the raw ADHD-200 directory and --output for the BIDS target. It normalizes numeric subject IDs to sub- labels, routes T1w to anat and resting-state fMRI to func, and writes dataset_description.json and participants.tsv. Use --dry-run to preview first.

How do I merge ADHD-200 phenotype CSV files?▼

Use extract_adhd200_phenotype.py with --phenotype-dir or --phenotype-file pointing to the phenotype CSVs. It standardizes column names like DX to diagnosis, merges on subject_id, and can filter to imaged subjects via a participants.tsv file with --imaging-ids.

Does ADHD-200 include task-based fMRI data?▼

No, ADHD-200 only includes T1-weighted structural MRI and resting-state fMRI; there is no task-fMRI. The dataset spans 8 sites with heterogeneous acquisition parameters, so site effects must be addressed in downstream analysis.

How do I exclude ADHD-200 subjects with high motion?▼

Run adhd200_qc_summary.py against your fMRIPrep output directory. It computes mean and max framewise displacement per subject and flags exclusions when mean FD exceeds 0.3 mm or max FD exceeds 5.0 mm, both configurable via thresholds.

What are the limitations of ADHD-200 BIDS conversion?▼

Subject IDs are numeric and vary in length across sites, and diagnosis labels differ by site, so the script encodes site in participants.tsv for later harmonization. Files whose modality cannot be detected from names are skipped and reported as failures.

Related Skills

Explore More Education & Research Skills→
D-RoboticsD-Robotics
3

bsp-image-build

Builds flashable RDK X3/X5 system images using pack_image.sh with explicit configuration selection.

Official
Intermediate
CUHK-AIM-GroupCUHK-AIM-Group
78

adni-skill

Orchestrate ADNI workflows from raw NIfTI to BIDS-ready outputs with fMRIPrep and DK68 ROI extraction.

Official
Advanced
ai-service-incubatorai-service-incubator
1

verify-product

Verify cosmetic product information against official sources and generate structured reports.

Official
Advanced
dengzhe-houdengzhe-hou

eeg-preprocess

Preprocess raw EEG recordings into ICA-ready data with filtering and artifact removal.

Community
Advanced