---
title: "DICOM Metadata Extract — DICOM utility skill"
description: "Used for extracting selected metadata from one DICOM file and flagging standard-tag PHI presence. Not for anonymization or clinical use."
canonical: https://nvidia-medtech.github.io/skills/dicom-metadata-extract.html
audience: [engineer]
last_updated: 2026-06-10
source: skills/dicom-metadata-extract.html
---
# DICOM Metadata Extract

DICOM utility · no GPU required

DICOM utility

Used for extracting selected metadata from one DICOM file and flagging standard-tag PHI presence. Not for anonymization or clinical use.

[Skill on GitHub](https://github.com/NVIDIA-Medtech/medical-AI-skills/tree/dev/skills/dicom-metadata-extract) [Agent Skills spec](https://agentskills.io)

### Run it with an agent

Install the skill, then just ask your agent in plain language. `medagent.dicom_metadata_extract`

install skill Copy

```bash
npx skills add NVIDIA-Medtech/medical-AI-skills --skill dicom-metadata-extract
```

Try saying

“I have a DICOM file at fixtures/sample\_ct.dcm. Extract its metadata — I specifically need to know the modality, the study UID, and whether it contains any PHI before I share it externally.”

“Pull the patient orientation, pixel spacing, and series description from scan.dcm using dicom-metadata-extract.”

“Does this DICOM file carry any patient-identifying tags? Run dicom-metadata-extract and list which PHI tags are present.”

“Read the modality and acquisition date from study/0001.dcm and tell me whether it's a CT.”

[Skill on GitHub →](https://github.com/NVIDIA-Medtech/medical-AI-skills/tree/dev/skills/dicom-metadata-extract) [How agent skills work](https://agentskills.io)

Engineering & research use only — header-level utility, not de-identification or clinical clearance. Skills follow the open [Agent Skills spec](https://agentskills.io).