BlineSlide
Deep Breathe, Inc.BlineSlide is a cloud-based AI software tool designed to assist physicians in interpreting lung ultrasound (LUS) videos. It analyzes ultrasound clips to detect the presence of B line artifacts, a key lung ultrasound feature, helping clinicians in the assessment of lung health. The software improves image-based lung evaluation and supports patient management decisions by providing automated, objective detection of lung ultrasound artifacts.
Intended Use
The device is intended for noninvasive processing of ultrasound images to detect, measure, and calculate relevant medical parameters of structures and function of patients aged 18 years or older with suspected disease.
Technology
BlineSlide is a cloud service application that processes user-uploaded B-mode lung ultrasound video clips (MP4 format) acquired from anterior or anterolateral chest regions. It uses AI-based analysis, specifically deep convolutional neural networks for detecting the presence or absence of B line artifacts, which are lung ultrasound features relevant to diagnosis. The software performs automated assessment but does not interface directly with ultrasound systems.
Performance
The software was validated through non-clinical verification including unit, integration, and system testing, confirming that all requirements were met. Risk assessment followed ISO 14971. A standalone performance test of the B Line Artifact Detection Module used 1005 diverse lung ultrasound cine clips separated from development data. Ground truth was established by expert consensus. The detection achieved a sensitivity of 0.91 and specificity of 0.84, with consistent performance across demographic and imaging cohorts. Clinical testing was not required.
Predicate Devices
No predicate devices specified
Ready to Sharpen Your Edge?
Subscribe to join 11k+ 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.