atlas-free-brain-network-transformer

Generate subject-level embeddings from rs-fMRI data using atlas-free parcellation.

2|Updated Feb 12, 2026

Search Tags:#transformer #neuroimaging #rs-fmri #individualized-parcellation #roi-to-voxel #brain-network-transformer

Ready to run

npx skills add https://github.com/hiyenwong/ai_collection --skill atlas-free-brain-network-transformer

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: atlas-free-brain-network-transformer
Source: https://github.com/hiyenwong/ai_collection/tree/main/collection/skills/atlas-free-brain-network-transformer
Command: npx skills add https://github.com/hiyenwong/ai_collection --skill atlas-free-brain-network-transformer

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Traditional atlas-based brain network analyses rely on fixed parcellations that can misalign with individual anatomy, reducing sensitivity to subject-specific patterns and hindering cross-subject comparability.

Core Features & Use Cases

Atlas-free individualized parcellation derived directly from subject rs-fMRI data to minimize atlas bias.
ROI-to-voxel connectivity features enabling transformer-based, subject-level embeddings.
Suitable for downstream neuroimaging tasks such as cross-subject analysis, brain-age estimation, and biomarker discovery.

Quick Start

Provide subject-level embeddings from rs-fMRI data using atlas-free parcellation and ROI-to-voxel connectivity.

Frequently Asked Questions about atlas-free-brain-network-transformer

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

FAQPage Schema

How do I generate subject-level embeddings from rs-fMRI data without relying on a fixed atlas?▼

To generate subject-level embeddings from rs-fMRI data without an atlas, use atlas-free individualized parcellation and ROI-to-voxel connectivity features. This approach minimizes atlas bias and feeds into a transformer model to create subject-specific brain network embeddings.

What is atlas-free individualized parcellation in neuroimaging analyses?▼

Atlas-free individualized parcellation is a neuroimaging technique that derives brain regions directly from subject rs-fMRI data. It avoids fixed parcellations that misalign with individual anatomy, thereby improving sensitivity to subject-specific brain network patterns.

How do I use transformer models for cross-subject brain network comparisons?▼

You can use transformer models for cross-subject comparisons by inputting ROI-to-voxel connectivity features derived from individualized parcellation. The transformer generates subject-level embeddings that capture unique network properties for direct comparison across individuals.

Does atlas-free brain network transformer work for brain-age estimation and biomarker discovery?▼

Yes, the atlas-free brain network transformer works for brain-age estimation and biomarker discovery. By generating subject-level embeddings from rs-fMRI data, it captures individualized network patterns suitable for these downstream neuroimaging tasks.

Why do fixed atlas-based parcellations reduce sensitivity in cross-subject neuroimaging analyses?▼

Fixed atlas-based parcellations reduce sensitivity because they can misalign with individual anatomy. This misalignment hinders cross-subject comparability and masks subject-specific patterns, which atlas-free parcellation solves by deriving regions directly from rs-fMRI data.

What connectivity features are required for transformer-based brain network embedding generation?▼

Transformer-based brain network embedding generation requires ROI-to-voxel connectivity features. These features, derived from atlas-free individualized parcellation of rs-fMRI data, provide the spatial relationship inputs needed for the transformer model.