De-identify radiology and imaging reports including DICOM metadata – CCPA/HIPAA-compliant de-identification per 45 CFR §164.514(b)(2)

Radiology reports and DICOM image files embed Safe Harbor identifiers in both narrative text and machine-readable DICOM header tags — patient name, MRN, date of birth, and acquisition dates appear across dozens of image frames per study. anonym.legal removes all 18 §164.514(b)(2) identifiers from report text and DICOM header attributes, producing de-identified studies for teleradiology, second-opinion networks, and medical education.

When this applies

Use this workflow when radiology reports or DICOM studies are shared with external radiologists for second-opinion review, included in medicolegal disclosures, or prepared as case-study materials for educational use, and patient identity must be removed under the Safe Harbor standard.

  1. Upload the radiology report (PDF or DOCX) and/or export the DICOM study; the engine processes both document text and DICOM header tag format.
  2. For DICOM files, the engine reads all standard patient-identifiable tags (PatientName [0010,0010], PatientID [0010,0020], PatientBirthDate [0010,0030], StudyDate [0008,0020], AccessionNumber [0008,0050], InstitutionName [0008,0080]) and applies Safe Harbor transformations.
  3. All 18 Safe Harbor identifier categories are removed from the DICOM headers; synthetic UIDs are generated for StudyInstanceUID and SeriesInstanceUID to preserve multi-series study coherence.
  4. Report narrative text is processed separately: patient name, MRN, referring physician name, date of service, and institution address are detected and removed.
  5. Diagnostic findings, imaging measurements, Hounsfield unit values, and radiologist impressions are preserved in full.
  6. A de-identified DICOM export and a de-identified report PDF are produced with a combined compliance certificate.

What you provide

  • DICOM study export or radiology report PDF/DOCX
  • Accession number list (to verify study completeness)
  • Confirmation of whether burned-in pixel annotations are present in the DICOM series

Limitations & cautions

  • DICOM pixel data with burned-in patient annotations (overlaid patient name on the image pixels themselves) requires additional image-processing redaction beyond header tag removal; confirm whether your DICOM series contains burned-in PHI before relying solely on header de-identification.
  • Highly specialized imaging studies — for example, a single-institution case of a very rare tumor — may retain re-identification risk from the clinical presentation itself even after identifier removal.
  • DICOM de-identification is applied to tag-level data; custom private DICOM tags introduced by specific imaging vendors may require additional configuration to ensure complete PHI removal.

FAQ

Does DICOM tag-level de-identification satisfy HIPAA Safe Harbor?

Yes, provided all 18 identifier categories are addressed. DICOM tags such as PatientName, PatientID, PatientBirthDate, AccessionNumber, and InstitutionName correspond directly to Safe Harbor identifier categories and must be removed or generalized. The engine maps DICOM standard tags to Safe Harbor categories and processes them accordingly.

Are study instance UIDs replaced with new UIDs or removed entirely?

The engine replaces StudyInstanceUID, SeriesInstanceUID, and SOPInstanceUID with newly generated compliant UIDs. Full removal would break multi-series study coherence; replacement with synthetic UIDs preserves the structural relationship between images while eliminating the original patient-linked identifiers.

Can de-identified DICOM studies be uploaded to a public teaching case library?

Once de-identified under the Safe Harbor standard, the DICOM study is no longer PHI. However, clinical information in the imaging findings — a distinctive anatomical variant or a rare pathology — may make the case recognizable to treating clinicians. Review the clinical content before public release and consider Expert Determination for unusual cases.

Healthcare Records

About this page

We update this page when our platform or the law changes.

Read our founder note for how we work.

Each change shows up in the timestamp at the top.

We follow these rules

  • GDPR (EU 2016/679).
  • ISO/IEC 27001:2022.
  • NIS2 (EU 2022/2555).
  • HIPAA safe harbor under 45 CFR § 164.514(b)(2).

Our promise

We do not sell your data.

We do not train models on your text.

We store your files in Germany.

You can delete your account at any time.

You own your work.

Where we run

Our servers live in Falkenstein, Germany.

We use Hetzner. They hold ISO 27001 certification.

All data stays in the EU.

Backups run every day.

Need help?

Email support@anonym.legal.

We reply within one business day.

How we test

We run a full check suite on every release.

Each surface gets its own sweep script and report.

Human reviewers spot-check the output each week.

We track recall and precision on a labelled set.

Bad runs block the deploy.

What we never do

  • We never sell your information to third parties.
  • We never train models on what you upload.
  • We never keep your work after you delete it.
  • We never share keys with any outside firm.
  • We never run ads inside the product.

Plans in plain words

We sell credits, not seats.

One credit covers one short job.

Long jobs use a few credits each.

You can top up at any time.

Unused credits roll over each month.

Read the plans page for current rates.

Who built this

A small team of engineers and lawyers built this.

We ship from Europe and work in the open.

Our founder note spells out why we started.

Where to start

How the parts fit

A browser add-on cleans text inside Chrome.

A Word plug-in handles drafts in Office.

A small desktop tool works on whole folders.

An agent protocol link feeds large models safely.

All four share one core engine and one rule set.

Words from our team

We started this work after a lunch about cookies.

One friend kept getting odd ads on her phone.

We asked why a court file leaked through a draft.

We sketched the first build on a napkin that week.

By month three we had a tiny demo for a friend.

She used it on her first case the next day.

Common questions we hear

Can the tool read scanned PDFs? Yes, with OCR.

Does it work on long files? Yes, in small chunks.

Can I roll my own rule set? Yes, save it as a preset.

Does it run offline? The desktop build runs offline.

Do you keep my files? No, the cloud build wipes after each run.

Will it learn from my work? No, we never train on inputs.

A short tour of the workflow

Upload a file or paste a snippet of prose.

Pick the entities you want gone from the draft.

Choose a method: replace, mask, hash, encrypt, or redact.

Press run and watch the side panel show each hit.

Skim the result and tweak any rule that misfired.

Save the cleaned file or send it to a teammate.