dicom-processing

Converts, organizes, and anonymizes DICOM/NIfTI medical imaging data for research workflows.

13|5|Updated May 4, 2026

Search Tags:#dicom #medical-imaging #de-identification #nifti #bids #hcls

Ready to run

npx skills add https://github.com/awslabs/hcls-agent-skills --skill dicom-processing-awslabs

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: dicom-processing
Source: https://github.com/awslabs/hcls-agent-skills/tree/main/skills/dicom-processing
Command: npx skills add https://github.com/awslabs/hcls-agent-skills --skill dicom-processing-awslabs

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pydicom, dcm2niix, nibabel.

What problem does it solve?

This skill solves the complexity of managing medical imaging data by automating the conversion between DICOM and NIfTI formats while ensuring rigorous PHI de-identification.

Core Features & Use Cases

Format Conversion: Seamlessly convert DICOM series to BIDS-compliant NIfTI volumes using dcm2niix.
Automated De-identification: Scrub PHI from DICOM headers, remove private vendor tags, and regenerate UIDs to ensure patient privacy.
Use Case: A researcher needs to prepare a large cohort of MRI scans for machine learning; this skill automates the batch conversion, BIDS organization, and anonymization process in one pipeline.

Quick Start

Use the dicom-processing skill to convert all DICOM files in the input directory to BIDS-compliant NIfTI files in the output directory.

Frequently Asked Questions about dicom-processing

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

FAQPage Schema

How do I convert DICOM files to BIDS-compliant NIfTI volumes?▼

You can convert DICOM files to BIDS-compliant NIfTI volumes by using dcm2niix to process the input directory. This skill automates the batch conversion while maintaining geometric integrity for clinical research workflows.

What is the best way to de-identify DICOM headers and remove PHI for research?▼

Automated DICOM de-identification scrubs PHI from headers, removes private vendor tags, and regenerates UIDs to ensure patient privacy. This batch process ensures regulatory compliance for medical imaging research data.

Do I need pydicom and nibabel to maintain geometric integrity during DICOM conversion?▼

Yes, pydicom and nibabel are required dependencies to maintain geometric integrity during DICOM and NIfTI conversion. These libraries ensure spatial metadata remains accurate throughout the medical imaging transformation pipeline.

Can I batch process a large cohort of MRI scans for machine learning preparation?▼

You can batch process a large cohort of MRI scans for machine learning by automating DICOM conversion, BIDS organization, and anonymization in one pipeline. This prepares imaging data efficiently for downstream analysis.

Does this DICOM processing approach support both parsing and NIfTI format conversion?▼

Yes, this approach automates the conversion, parsing, and de-identification of both DICOM and NIfTI medical imaging data. It handles format conversion seamlessly while ensuring rigorous PHI removal for compliance.