Lung AI (LAI001) is a software tool that assists healthcare professionals by analyzing lung ultrasound scans to detect signs of consolidation/atelectasis and pleural effusion. It highlights regions of interest on ultrasound cine clips to help clinicians identify potential lung issues, improving review efficiency but not replacing clinical judgment or other diagnostic tests. It supports physicians particularly in emergency departments during point-of-care lung ultrasounds.
Intended Use
Lung AI software device is a Computer-Aided Detection (CADe) tool designed to assist in the detection of consolidation/atelectasis and pleural effusion during the review of lung ultrasound scans.
Technology
Lung AI processes lung ultrasound cine clips using supervised deep learning algorithms, including deep convolutional neural networks, to identify and mark regions of interest with consolidation/atelectasis and pleural effusion. The software functions as a post-processing module integrated into third-party ultrasound systems and does not include a built-in viewer.
Performance
Performance was validated on a test dataset of 465 lung scans from 359 patients, showing high sensitivity (~0.97) and specificity (~0.91-0.94) for detection of pleural effusion and consolidation/atelectasis. Localization accuracy showed sensitivity around 0.85-0.86 and specificity around 0.91-0.94. A multi-reader multi-case (MRMC) clinical study with emergency physicians demonstrated statistically significant improvements in diagnostic accuracy when using the device.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
10/10/2024
6 months - 2
FDA Approval
4/24/2025
Other devices from Exo Inc
- Strain AI (SAI001)2024 • 510K
- AI Platform (AIP001)2023 • 510K
- Bladder AI (AIBV01)2023 • 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.