Vara

Vara (MX Healthcare GmbH)

Vara's Decision Referral Pathway ensures that each mammogram is analysed by AI and classified into one of three categories: "normal" (AI is confident there are no suspicious signs), "no classification" (AI is not confident about a classification), or "Safety Net" (AI is confident that it is highly suspicious). Vara pre-screens normal mammograms with very high confidence (pre-fills the report), allowing the reader to focus on potentially suspicious exams. Vara also post-screens mammograms with very high confidence for potentially missed exams (only triggered if the reader assigns BI-RADS <3).

Information source: Vendor
Last updated: March 3, 2025

General Information

General
Product name	Vara
Company	Vara (MX Healthcare GmbH)
Subspeciality	Breast
Modality	Mammography
Disease targeted	Breast cancer
Key-features	Triaging normal exams, safety net, report generation, AI-based workflow
Suggested use	Before: stratifying reading process (non, single, double read), adapting worklist order During: report suggestion After: diagnosis verification Without interference of a radiologist: AI-only diagnosis

Technical Specifications

Data characteristics
Population	Women of screening age
Input	2D mammograms of a screening study incl. prior images and patient history
Input format	DICOM
Output	Draft radiology report, segmentation overlay, model score, triaging recommendation, cancer recommendation
Output format	Proprietary viewer and worklist, HL7/XML/JSON
Technology
Integration	Integration RIS (Radiological Information System), Stand-alone webbased
Deployment	Cloud-based
Trigger for analysis	Automatically, right after the image acquisition
Processing time

Regulatory

Certification
CE	Certified, Class IIb , MDR
FDA	No or not yet
Intended Use Statements
Intended use (according to CE)	The software aids in assessing of compatible digital or digitized images of the human breast regarding the presence or absence of cancer findings using mathematical methods. It further supports the creation of machine-readable medical reports.

Market

Market presence
On market since	10-2019
Distribution channels
Countries present (clinical, non-research use)
Paying clinical customers (institutes)
Research/test users (institutes)
Pricing
Pricing model
Based on

Evidence

Evidence
Peer reviewed papers on performance	Nationwide real-world implementation of AI for cancer detection in population-based mammography screening (read) Combining the strengths of radiologists and AI for breast cancer screening : a retrospective analysis (read) AI-based prevention of interval cancers in a national mammography screening program (read)
Non-peer reviewed papers on performance
Other relevant papers