Vara offers an AI-powered platform that optimizes mammography screening by automating the triage of normal cases and highlighting suspicious findings for radiologists. This decision support tool enhances early breast cancer detection and reduces radiologist workload, improving patient outcomes.
Funding
$8.8M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
SFFounders
Product
Problem
Mammography screening programs face challenges in early breast cancer detection and managing radiologist workload. Many deadly cancers are missed or detected too late, impacting patient outcomes and increasing treatment costs. Existing workflows can lead to radiologist fatigue and inefficiencies in processing large volumes of mammograms.
Solution
Vara provides an AI-powered platform designed to optimize the entire breast cancer screening pathway. The platform integrates advanced AI algorithms into the mammography reading workflow, acting as a decision support tool for radiologists. It automates the triage of normal cases, significantly reducing the time spent on routine interpretations. For potentially suspicious cases, Vara's "safety net" feature highlights areas of concern, prompting radiologists to re-evaluate, thereby enhancing detection sensitivity. This approach aims to improve cancer detection rates, reduce radiologist workload, and ultimately lead to better patient outcomes by facilitating earlier diagnosis and treatment.
Target Audience
The primary target audience includes radiology departments, breast imaging centers, and national screening programs seeking to enhance the efficiency and accuracy of their mammography screening processes.
Features
- AI-driven decision referral system that categorizes mammograms into "normal," "safety net" (suspicious), or "unclassified" cases.
- Automated triage of normal mammograms, allowing radiologists to confirm AI classifications for a majority of scans, reducing average read time.
- "Safety net" functionality that identifies and localizes suspicious findings, prompting radiologists to review potentially missed cancers.
- Integration of longitudinal prior mammogram data to enhance AI prediction accuracy through the "Deep Prior Model."
- Automatic breast density classification and reporting in accordance with BI-RADS guidelines.
- Digital consensus and arbitration tools to facilitate radiologist collaboration on complex cases.
- On-demand second opinion feature for critical case review.
- Comprehensive analytics dashboards providing visibility into screening pathway performance, including AI-radiologist interactions, turnaround times, and cancer detection metrics.
- CE-marked (class IIb) medical device software with a web-based viewer optimized for high-volume screening.
- Compliance with European Medical Device Regulation (MDR).