nifd-skill

Orchestrates BIDS validation and multimodal processing of the NIFD frontotemporal dementia dataset.

89|5|Updated Mar 25, 2026
One-click install
npx skills add https://github.com/CUHK-AIM-Group/NeuroDiscovery --skill nifd-skill-cuhk-aim-group
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: nifd-skill
Source: https://github.com/CUHK-AIM-Group/NeuroDiscovery/tree/main/skills/nifd-skill
Command: npx skills add https://github.com/CUHK-AIM-Group/NeuroDiscovery --skill nifd-skill-cuhk-aim-group

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Processing the NIFD frontotemporal dementia dataset requires coordinating BIDS validation, structural MRI, resting-state fMRI, and diffusion MRI pipelines plus phenotype extraction, which is error-prone when done manually across separate tools. ## Core Features & Use Cases - BIDS Validation: Validates NIFD directory structure, diagnostic group completeness, and modality presence, producing a compliance CSV report. - Multimodal Delegation: Delegates sMRI, rs-fMRI, and dMRI processing to dedicated modality skills and organizes outputs into a clean nifd_output/ layout. - Phenotype & QC Extraction: Merges diagnosis and cognitive scores (CDR, MMSE, neuropsychological battery) into a phenotype table and generates per-subject QC summaries with exclusion lists. - Use Case: A researcher with approved LONI IDA access stages a NIFD export, validates its BIDS structure, then runs the full multimodal pipeline to compare atrophy and connectivity patterns across bvFTD, svPPA, and nfvPPA groups. ## Quick Start Ask the agent to validate my local NIFD BIDS dataset and run the full multimodal processing workflow for structural, functional, and diffusion MRI.

Frequently Asked Questions about nifd-skill

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

FAQPage Schema
How do I process the NIFD frontotemporal dementia dataset?

Obtain approved access through the NIFD/FTLDNI project in LONI IDA, stage the export into BIDS format, then run BIDS validation followed by delegated sMRI, rs-fMRI, and dMRI processing. Outputs are organized into an nifd_output/ directory with derivatives, phenotype tables, and QC summaries.

How to validate NIFD BIDS structure before processing?

Run the validate_nifd.py script with --input pointing to the BIDS directory and --output for the report path. It checks each subject for T1w, task-rest BOLD, and DWI files and writes a CSV compliance report with missing files and warnings.

Can I download NIFD data from OpenNeuro?

No, the previously cited OpenNeuro dataset ds004403 was deleted as a duplicate. NIFD is a controlled dataset that requires an approved application and DUA acceptance through the LONI IDA portal before download.

What modalities and diagnostic groups does NIFD include?

NIFD contains roughly 120 participants scanned on a 3T Siemens TIM Trio with T1w sMRI, resting-state fMRI, and diffusion MRI. Diagnostic groups include bvFTD, svPPA, nfvPPA, and age-matched healthy controls, with clinical measures like CDR and MMSE.

Why are subjects excluded in the NIFD QC summary?

The QC script flags subjects whose mean framewise displacement from fMRIPrep confounds exceeds the 0.3 mm threshold. Excluded subjects and their reasons are written to a separate exclusion list CSV for review.