ChestView US
Gleamer SASChestView US is an AI software product that analyzes frontal and lateral chest X-rays to detect and mark suspicious areas such as lung nodules, pleural abnormalities, mediastinal/hilar abnormalities, and consolidations. It provides annotated images with highlighted regions to assist clinicians in reading chest radiographs, improving diagnostic accuracy as a concurrent reading aid.
Intended Use
ChestView US is a radiological Computer-Assisted Detection (CADe) software device that analyzes frontal and lateral chest radiographs of patients presenting with symptoms (e.g. dyspnea, cough, pain) or suspected for findings related to regions of interest (ROIs) in the lungs, airways, mediastinum/hila and pleural space.
Technology
ChestView US uses supervised deep learning algorithms to analyze chest X-rays and identify suspicious regions of interest classified into four categories: Nodule, Pleural space abnormality, Mediastinum/Hila abnormality, and Consolidation. The software processes DICOM images received from a PACS or radiographic system and generates annotated DICOM secondary capture images with bounding boxes indicating findings.
Performance
Performance was evaluated in standalone and clinical studies. Standalone testing on 3,884 chest radiographs showed high AUC values (0.922 to 0.973) and good sensitivity and specificity for detecting four ROI categories. A reader study with radiologists and emergency physicians showed significantly improved diagnostic accuracy (AUC) when aided by ChestView US compared to unaided reading for all categories (p<0.001).
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
6/5/2024
8 months - 2
FDA Approval
2/27/2025
Other devices from Gleamer SAS
- BoneMetrics (US)2025 • 510K
- BoneView2023 • 510K
- BoneView2022 • 510K
Ready to Sharpen Your Edge?
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.