ChestView US

The ChestView US device is a Class II Medical Image Analyzer and Computer-Assisted Detection (CADe) software designed to aid radiologists and emergency medicine physicians in identifying abnormalities on frontal and lateral chest radiographs. It leverages machine learning to analyze images, marking regions of interest and demonstrating high accuracy and improved diagnostic performance in clinical studies, serving as a concurrent reading aid without replacing professional judgment.

A company received communication on February 27, 2025, regarding its ChestView US device, which has been identified as a Class II Medical Image Analyzer. Following a review of the device's premarket submission, it was determined to be substantially equivalent to existing, legally marketed devices for its specified indications for use. This determination allows the device to be marketed, subject to standard general market controls, including requirements for annual registration, device listing, good manufacturing practices, and labeling.ChestView US is a radiological Computer-Assisted Detection (CADe) software designed to analyze frontal and lateral chest radiographs. Utilizing machine learning, it identifies and marks regions of interest such as nodules, pleural space abnormalities, mediastinum/hila abnormalities, and consolidations. The device is intended as a concurrent reading aid for radiologists and emergency medicine physicians, supplementing but not replacing their professional judgment or other diagnostic testing. Performance data from standalone and clinical studies demonstrated high accuracy and improved diagnostic performance for users when aided by the device, confirming its safety and effectiveness relative to comparable technology.

AI Regulatory Concerns

Powered by

Jev reads the full FDA letter and returns calibrated concern probabilities per regulatory category. These are AI estimates, not regulatory advice.

• Q1. What specific machine learning algorithms does ChestView US employ, and how do they handle edge cases or atypical presentations of abnormalities?; How does the device's performance vary across different patient demographics or image acquisition protocols (e.g., portable versus fixed X-ray machines)?; What are the false positive and false negative rates for each identified region of interest (nodules, pleural space, mediastinum/hila, consolidations), and how do these impact clinical workflow?; Are there any known limitations or scenarios where the device's performance degrades, and what mitigation strategies are recommended for clinicians?; What ongoing post-market surveillance or validation studies are planned to monitor the device's long-term performance and impact on patient outcomes in real-world clinical settings?