Logo
RadAI Slice
Subscribe

Intended Use

HealthOST is an image processing software that provides qualitative and quantitative analysis of the spine from CT images to support clinicians in the evaluation and assessment of musculoskeletal disease of the spine. It labels T1-L4 vertebrae, measures height loss in each vertebra (T1-L4), and measures mean Hounsfield Units in vertebrae (T11-L4). Indicated for patients aged 50+ undergoing CT scans including these vertebrae, for FBP-reconstructed images only.

Technology

HealthOST uses deep-learning-based segmentation to identify and label vertebrae from CT images, computes vertebral height loss based on three measurements (anterior, middle, posterior) compared using Genant criteria, and calculates mean Hounsfield Unit bone attenuation within vertebrae. It runs standalone image processing software analyzing DICOM CT datasets, providing results to clinician workflow via IMA integration.

Performance

HealthOST underwent a stand-alone retrospective validation study with 150 anonymized CT scans (1425 vertebrae) compared against ground truth established by US board-certified radiologists and predicate device (AI-Rad Companion K193267). Results showed high agreement in vertebral naming (91.49%), height loss measurement, and bone attenuation with limits of agreement comparable or better than predicate. Testing included varied slice thicknesses and increments, with generalizability validated on additional US data.

View FDA documentation

Predicate Devices

No predicate devices specified

Device Timeline

  • 1

    Submission

    12/17/2021

    4 months
  • 2

    FDA Approval

    4/22/2022

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.