pydicom
Analyze DICOM Files with pydicom
DICOM files contain complex image data and medical metadata that are hard to inspect safely. This skill guides Claude, Codex, and Claude Code through pydicom workflows for reading, converting, anonymizing, and extracting DICOM data.
Stop for confirmation before installing.
Review the plan and obtain explicit user consent before changing files.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "pydicom" from https://skillstore.io/skills/k-dense-ai-pydicom.md and its manifest at https://skillstore.io/api/skills/k-dense-ai-pydicom/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "pydicom". Convert a CT DICOM file for review.
Expected outcome:
A concise workflow that installs needed handlers, reads the file, applies VOI LUT windowing, normalizes pixels, exports PNG, and checks filenames for PHI.
Using "pydicom". Extract metadata for an audit.
Expected outcome:
A table-style summary of patient, study, series, and image fields with a warning that exported metadata may contain PHI.
Using "pydicom". Anonymize research images before sharing.
Expected outcome:
A checklist of tags to remove or replace, UID handling choices, and verification steps before sending files to collaborators.
Security Audit
High RiskMost static findings are false positives caused by Markdown code fences, DICOM terms, and documentation URLs. I found no hidden shell execution, device-file access, or network reconnaissance in the cited lines. Two semantic privacy concerns remain: metadata export can expose PHI, and the skill promotes an external hosted platform for complex medical data workflows.
Confirmed security concerns (2)
Risk Factors
📁 Filesystem access (4)
⚙️ External commands (53)
🌐 Network access (6)
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/k-dense-ai-pydicom/audits/7?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/k-dense-ai-pydicom?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/k-dense-ai-pydicom?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/k-dense-ai-pydicom/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/k-dense-ai-pydicom.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
K-Dense-AI. (2026). pydicom security audit report (audit version 7) [Author version unspecified]. Skillstore. https://skillstore.io/skills/k-dense-ai-pydicom/audits/7BibTeX citation
@techreport{k-dense-ai-k-dense-ai-pydicom-2026,
author = {K-Dense-AI},
title = {pydicom security audit report (audit version 7)},
institution = {Skillstore},
year = {2026},
number = {7},
url = {https://skillstore.io/skills/k-dense-ai-pydicom/audits/7},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "pydicom security audit report (audit version 7)"
version: "unspecified"
type: report
authors:
- name: "K-Dense-AI"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/k-dense-ai-pydicom/audits/7"
identifiers:
- type: other
value: "skillstore:k-dense-ai-pydicom:audit:7"
description: "Skillstore immutable audit report identifier"
Compare variants
2 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
k-dense-ai-pydicom
2026-08-21
davila7-pydicom
2026-08-21
Skillstore Score
Why this score Evidence Confidence: MediumWhat You Can Build
Metadata Export for Pipelines
Prepare DICOM metadata exports and image conversions for research pipelines while preserving needed study fields.
Research Dataset De-identification
Apply basic PHI removal steps, then review residual tags before sharing images with collaborators.
Imaging Tool Prototyping
Build pydicom scripts that read series, process pixels, and write compliant DICOM files.
Try These Prompts
Use the pydicom skill to read a DICOM file, list core metadata, and handle missing tags safely.
Use the pydicom skill to convert a DICOM image to PNG. Include windowing guidance and explain which optional packages may be required.
Use the pydicom skill to design a basic anonymization workflow for a folder of DICOM files. Include PHI tag checks and validation steps.
Use the pydicom skill to plan a Python workflow that reads a DICOM series, sorts slices, creates a 3D volume, and preserves spacing metadata.
Best Practices
- Check for missing tags with hasattr or get before reading optional attributes.
- Verify anonymization outputs manually before sharing files or metadata.
- Install only required pixel handlers for the compression formats in your dataset.
Avoid
- Do not treat converted images as de-identified without checking overlays and metadata.
- Do not run scripts on clinical originals without preserving backup copies.
- Do not upload DICOM data to external services without approval and privacy review.
Frequently Asked Questions
Can this skill read CT and MRI files?
Does it anonymize DICOM files completely?
Can it convert DICOM images to PNG or JPEG?
Does it support compressed DICOM data?
Can Claude Code or Codex use the helper scripts?
Is this a diagnostic medical tool?
Developer Details
Author
K-Dense-AILicense
https://github.com/pydicom/pydicom/blob/main/LICENSE
Skillstore revision
r1
Version notice
The author did not declare a version.
Repository
https://github.com/K-Dense-AI/claude-scientific-skills/tree/main/scientific-skills/pydicomRef
a25199bc7d6b82598536822d1738eb5d5f54025b
Maintenance freshness
7/18/2026
Usage
10 downloads · 205 views
File structure