Ultrasound de-identification is the removal of patient identifiers from the file. UK GDPR Art. 9 and the DPA 2018 govern health data. anonym.plus runs it on your own device. The measurements stay, but the text names no one.
When this applies
A sonography case fits a training set. The body of findings can stay, yet the name, the date, and the corner banner have to be hidden first.
How anonym.plus handles it
- Open the file (PDF, image, or scan) on your machine.
- Local OCR reads any text printed on the frame.
- The tool marks names, dates, and the banner line.
- Review each mark and keep the measurement values.
- Swap each ID for a label, or cover it with a box.
- Save the clean study. The source stays on your disk.
What you need to provide
- The file (PDF, JPEG, PNG, or image scan).
- An operator: Replace (swap), Redact (remove), or Mask (partial).
- Optional: a name map to re-link follow-ups.
Patient data entity types detected
| Category | anonym.plus entity type | Example |
|---|---|---|
| Names | PERSON | Priya Sharma → [PATIENT_1] |
| Dates | DATE_TIME | Exam 22/05/2026 → [DATE] |
| Record IDs | MEDICAL_RECORD_NUMBER | MRN 309845 → [MRN] |
| Identifiers | ID | Visit V-2207 → [VISIT] |
| Contact | PHONE_NUMBER | +44 20 7946 0102 → [PHONE] |
| Location | LOCATION | 5 Quay Road, Bristol → [ADDRESS] |
Compliance achieved
- Anonymisation under UK GDPR Art. 9 & DPA 2018.
- Once truly anonymous, the file leaves UK GDPR scope under Recital 26.
- Assessed against the ICO motivated-intruder test.
- Working files are kept safe with AES-256-GCM.
Anonymise ultrasound studies offline — see plans & start free →
Limitations & cautions
Obstetric frames may hold a name in the corner banner. OCR catches most of it. Faint banners can slip through, so check each frame before you share it.
Frequently asked questions
Does the banner with the patient name get hidden?
Yes. Local OCR reads the corner banner. You then box the text. The measurements in the middle stay clear while the name goes.
Will gestational age or other numbers be removed?
Only patient ages tied to a person are flagged. Pure measurement values are left alone, so the clinical numbers stay in place.
Can I batch a folder of these?
Yes. Point the app at a folder. It applies your rules to each file in turn, which suits a study set built for teaching.