QuantX is a software tool that helps radiologists analyze breast MRI images by automatically segmenting lesions and calculating a score based on lesion characteristics. It compares lesions in a patient's MRI to a database of known cases to help in diagnosing breast abnormalities, potentially improving diagnostic accuracy and consistency. It supports viewing multimodal images and generates structured reports to assist clinical decision-making.
QuantX is a computer-aided diagnosis (CADx) software device used to assist radiologists in the assessment and characterization of breast abnormalities using MR image data.
The device is a software-only post-processing system that includes image registration, automated lesion segmentation based on a user-indicated seed point, and quantitative analysis of morphological and enhancement features from MR images. It extracts radiomic features from segmented lesions and applies a machine learning-based algorithm to calculate a QI score, comparing lesions to a database of biopsy-proven cases for reference and aiding diagnostic interpretation.
Performance testing included standalone algorithm evaluation and a multiple reader, multiple case (MRMC) clinical study. The QI Score achieved an AUC of 0.86 in standalone testing and 0.75 in an independent reader study, demonstrating improved reader diagnostic performance. The clinical study showed a statistically significant increase in AUC when radiologists used QuantX as an aid, with improved sensitivity and consistent specificity. Testing included retrospective and prospective datasets with biopsy-proven ground truth and follow-up data.
Submission
4/7/2017
FDA Approval
7/19/2017
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.