All skills
dicom-metadata-extract
Extract selected metadata from one DICOM file and flag standard-tag PHI presence.
- Part of NVIDIA/skills
- 1.9k installs
- Data · Document parsing
When to use it
You have a single DICOM file and need its modality, transfer syntax, and study/series/image fields as JSON before deciding on next steps.
For example
You say
Use dicom-metadata-extract on sample_ct.dcm and write the metadata to result.json.
You get
- result.json metadata
- phi_present flag
- phi_tags_found list
How it works
- Only a small standard-tag subset is checked; private tags and burnt-in pixel PHI are not detected.
- Not intended for anonymization or clinical use.
Before installing
Requires the Python packages listed in the skill manifest, including pydicom.
This skill includes 3 scripts your assistant may run on your computer.
More Document parsing skills
See all- instrument-data-to-allotrope2.5kConverts lab instrument files (PDF, CSV, Excel, TXT) into Allotrope JSON or flattened CSV for LIMS and analysis.
- odl-pdf45Extracts text, tables and structure from PDFs into Markdown, JSON or HTML using opendataloader-pdf, and checks the result.
- aryn-automation3Automates Aryn tasks through Composio, checking current tool schemas before each call.
- pdf-analysis3Extracts text, tables and chart captions from text or scanned PDFs, including multi-page scans and unit-aware calculations.
Also in this pack
- accelerated-computing-cudf3.2kGuides GPU DataFrame work with cuDF, including pandas acceleration, joins, groupby, file I/O and multi-GPU jobs.
- cuopt-developer2.8kModifies, builds, tests, and debugs NVIDIA cuOpt source code and prepares contributions.
- cuopt-install2.6kInstalls cuOpt for Python, C, or server via pip, conda, or Docker and verifies it works.
- data-designer2.6kGenerates a synthetic dataset from your description of the data you need.