Home / Radiology & medical imaging / Vara
MX Healthcare GmbH (Berlin, DE)Vara
AI for breast cancer screening that pre-sorts normal mammograms, drafts reports automatically and flags possibly missed findings. According to Vara, it runs in more than half of Germany's population screening programme.

- Provider based in the EU
Last checked: 23 October 2026 · How we check
Is this your tool? Fill in missing detailsWhat it does
Flagging possibly missed findings
Automatically drafted reportsComparable in radiology & medical imaging
Inceptoon request
Siemens Healthineers AI-Rad Companionon request (trial version available…
mediaire mdbrainper volume (on request)
Milvue TechCareMilvue Suite on request
Avicenna.AI CINAon request
contextflow ADVANCE Chest CTon requestthe language model used is not public (proprietary image analysis AI); CE class IIb (according to the provider); validated in the PRAIM study. Processing location of images not stated in the privacy statement. Many tools build on a large model from, for example, OpenAI or Anthropic. If in doubt, ask for the data processing agreement: it states where your data goes.
Questions about Vara
- Which AI model does Vara use?
- The maker of Vara does not disclose which AI model sits underneath. (proprietary image analysis AI); CE class IIb (according to the provider); validated in the PRAIM study. Processing location of images not stated in the privacy statement.
- How much does Vara cost?
- on request. Check the current price on the provider's website; rates change often.
- Who is Vara for?
- Vara focuses on radiology & medical imaging. It fits work such as detecting and marking abnormalities on X-ray, CT and MRI (fractures, nodules, emboli, bleeds), prioritising the worklist by urgency and pre-sorting normal studies, quantitative analysis of brain, lung and prostate images and comparison with prior scans.
- What should I look out for with AI in radiology & medical imaging?
- Image analysis AI is a medical device: only use software with a CE marking under the MDR (class IIa or higher) for the exact purpose you deploy it for, and document how you validate and keep monitoring performance locally. You process special category personal data: ask where images are processed (on-premise, EU cloud or outside), whether they are pseudonymised and whether they are used for training, and sign a data processing agreement. Many vendors run on AWS or Azure or have been acquired by US groups, so check the current data location. The radiologist remains ultimately responsible for the report.
Every Friday: what changed in AI for radiology & medical imaging
New models, prices, oversight and tools, with sources and what it means for you. One email a week, unsubscribe with one click.


