Intended Use

CoLumbo is an image post-processing and measurement software tool that provides quantitative spine measurements from previously-acquired DICOM lumbar spine MR images for users' review, analysis, and interpretation. It provides feature segmentation, feature measurement, threshold-based labeling of out-of-range measurements, and export of measurements to reports for user review and approval. It does not produce or recommend diagnosis or treatment and is intended for use only by hospitals and medical institutions on images of patients aged 18 and above without certain excluded conditions.

Technology

CoLumbo uses deep convolutional image-to-image neural networks for semi-automatic segmentation and measurement of lumbar spine features from DICOM MRI images. Users confirm, modify, and approve threshold-based labeling of out-of-range measurements. The tool outputs segmentations and quantitative measurements, which must be reviewed and validated by the user prior to reporting. The software supports visualization and measurement but is not diagnostic.

Performance

Performance testing included software verification and validation, cybersecurity, usability (human factors), and a standalone clinical performance study. The clinical study compared CoLumbo outputs to ground truth segmentations and measurements established by three radiologists on 101 MR studies across multiple US sites and manufacturers. Results showed measurement errors and segmentation Dice coefficients within predefined acceptance criteria, demonstrating accuracy across subgroups by age, sex, race, and scanner type. No clinical studies were conducted.

Predicate Devices

No predicate devices specified

Device Timeline

  • 1

    Submission

    2/22/2022

    4 months
  • 2

    FDA Approval

    6/23/2022

Other devices from Smart Soft Healthcare AD

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.