Lunit INSIGHT MMG is an AI-powered computer-assisted detection and diagnosis software designed to help radiologists detect, localize, and characterize suspicious areas for breast cancer on mammograms. It works as an adjunct tool viewed after the initial physician read, providing visual marks and scores indicating the likelihood of malignancy to assist clinical decision-making and improve breast cancer detection during mammography screenings.
Lunit INSIGHT MMG is a radiological Computer-Assisted Detection and Diagnosis (CADe/x) software device based on an artificial intelligence algorithm intended to aid in the detection, localization, and characterization of suspicious areas for breast cancer on mammograms from compatible FFDM systems. As an adjunctive tool, the device is intended to be viewed by interpreting physicians after completing their initial read. It is not intended as a replacement for a complete physician’s review or their clinical judgement that takes into account other relevant information from the image or patient history.
Lunit INSIGHT MMG uses deep learning algorithms applied to FFDM breast images to identify suspicious lesions for breast cancer. It analyzes images received in DICOM format, de-identifies them, and produces visual maps and abnormality scores indicating likelihood of malignancy per lesion and per breast. The AI model is trained with large databases of biopsy-proven cases including cancerous, benign, and normal tissues.
The device demonstrated improved breast cancer detection compared to unaided radiologists in both standalone and clinical multi-reader multi-case studies. Standalone ROC AUC was 0.903, showing statistically significant performance over radiologists. A clinical reader study with 12 MQSA-qualified radiologists showed a significant ROC AUC improvement from 0.754 to 0.805 with device assistance, confirming safety and effectiveness comparable to the predicate device.
No predicate devices specified
Submission
6/1/2021
FDA Approval
11/17/2021
Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.
We respect your privacy. Unsubscribe at any time.