DrAid™ for Liver Segmentation is a web-based AI software that assists healthcare professionals in analyzing liver images from CT scans. It generates semi-automated liver segmentation and allows physicians to manually refine these segmentations and identify lesions, aiding in evaluation and treatment planning without providing direct diagnosis.
DrAid™ for Liver Segmentation is a web-based software, non-invasive image analysis application designed for the visualization, evaluation, and reporting of liver and physician identified lesions using multiphase images (with slice thickness <= 3.0mm) of patients aged and older than 22 years old obtained from CT scanners. It enables professionals to review and analyze multiphase volume datasets of the liver, providing semi-automated liver segmentation editable by physicians and tools for manual segmentation of lesions. The software outputs liver volume, lesion volume, and lesion dimensions to aid evaluation and treatment planning.
DrAid™ for Liver Segmentation is a web-based software application that processes multiphase CT DICOM images using an AI algorithm for semi-automated liver segmentation, combined with manual editing capabilities. It provides a DICOM processing module, liver segmentation viewer, measurement algorithms, and reporting tools. It operates on standard hospital/clinic workstations to assist physicians and technicians.
Performance testing included validation on 450 contrast-enhanced CT scans from US medical institutions, showing a mean Dice score of 0.9649 and HD95 of 1.7061 for liver segmentation, meeting or exceeding acceptance criteria. Liver volume measurement error was within 3% mean normalized volume error. Testing used ground truth annotations from 3 US board-certified radiologists and validated device robustness across various scanner types and patient subgroups.
No predicate devices specified
Submission
5/31/2024
FDA Approval
12/6/2024
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.