mcpField
D
dicom-metadata-extract

dicom-metadata-extract

github.com/nvidiaData & databases3.8k1.9k installsUpdated today
Repository

About dicom-metadata-extract

A skill that extracts selected metadata from one DICOM file and reports the presence of standard-tag PHI. It is a small Python-based example for metadata inspection, not a de-identification or clinical tool.

Key features

  1. 01Extracts selected DICOM metadata
  2. 02Reports standard-tag PHI presence
  3. 03Writes JSON output
  4. 04Uses a documented wrapper script
  5. 05Includes evidence review guidance

Use cases

  1. 01Inspect metadata from a DICOM file
  2. 02Produce JSON for a downstream workflow
  3. 03Review extracted metadata evidence

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/nvidia/skills --skill dicom-metadata-extract

After installing, type/dicom-metadata-extractin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

AGENTS.md
BENCHMARK.md
skill_manifest.yaml
skill-card.md
skill.oms.sig
evals/
baseline.yaml
evals.json
fixtures/
generate_sample.py
scripts/
extract_metadata.py
tests/
test_basic.py
validators/
output_schema.json

Details

From the project README

DICOM Metadata Extract

Purpose

  • Used for extracting selected metadata from one DICOM file and flagging standard-tag PHI presence. Not for anonymization or clinical use.
  • Use the wrapper exactly as documented; do not replace the upstream entrypoint with a handwritten implementation.
  • Manifest I/O: inputs are dicom_path; outputs are metadata_json.

Instructions

  • Read skill_manifest.yaml before changing arguments, side effects, or validation gates.
  • Run scripts/extract_metadata.py through the documented command below; keep outputs under a caller-provided run directory.
  • If a host agent exposes run_script, use run_script("scripts/extract_metadata.py", args=[...]); otherwise run the Bash/Python command shown below.
  • Check the emitted JSON and run medagent.verifiers.dicom_metadata_quality_v1 on evidence packs before treating the run as reviewed evidence.

Available Scripts

ScriptPurposeArguments
scripts/extract_metadata.pyPrimary entrypoint declared by skill_manifest.yaml.PATH_TO_DICOM [--output OUT.json]

Prerequisites

  • Runtime requirements: Python packages listed in runtime.side_effects.pip_packages.
  • Run commands from the repository root unless an existing section below says otherwise.

Limitations

  • Small PS3.15-inspired standard-tag subset only; not a complete Basic Application Confidentiality Profile implementation.
  • Private tags not checked
  • Burnt-in pixel PHI not detected
  • Multi-frame handling minimal
  • Not for clinical deployment, regulatory de-identification, autonomous diagnosis, patient-facing use.

Troubleshooting

ErrorCauseFix
Missing dependency or import errorRuntime package drift from skill_manifest.yaml.Install the packages declared in the manifest or use the documented setup command.
Empty or schema-invalid outputWrong input path, unsupported modality, or upstream failure.Re-run with a known fixture and inspect the wrapper JSON plus stderr.
Validation gate failureOutput violated a declared engineering invariant.Keep the failed evidence pack and use the gate message to repair inputs or wrapper code.

Reads one DICOM file with pydicom and emits JSON on stdout.

python scripts/extract_metadata.py PATH_TO_DICOM
python scripts/extract_metadata.py PATH_TO_DICOM --output result.json

Output includes transfer_syntax, modality, grouped study/series/image metadata, phi_present, and phi_tags_found.

Use this as the smallest end-to-end example of a Medical AI Skills skill. Do not use it for anonymization, private-tag review, pixel PHI detection, or clinical interpretation.

For second-pass evidence review, generate a trusted run:

python -m eval_engine.run_trusted skills/dicom-metadata-extract \
  --fixture skills/dicom-metadata-extract/fixtures/sample_ct.dcm \
  --out runs/dicom_metadata_trusted

Comments

Markdown supported