Search Results

The SpineUs™ system is a software-based, tracked, ultrasound imaging system and accessories, intended for diagnostic imaging. It is indicated for diagnostic ultrasound imaging in the following applications: musculoskeletal (conventional, superficial). The system is intended for use by trained chiropractors and radiologists in a hospital or medical clinic.

The SpineUs™ system is intended for assisting trained chiropractors and radiologists in acquiring, viewing, and measuring ultrasound images of the spine in both clinic and hospital settings. The SpineUs™ system is intended to be used as an adjunct to conventional imaging method that allows trained chiropractors and radiologists to measure spine-related anatomical components on images (e.g., intervertebral angles and spine curvature). The system also allows the review and management of patient measurement data. Clinical judgment of anatomy and experience are required to properly use the SpineUs™ system.

Patient management decisions should not be made based solely on the results of the SpineUs™ computer application. The user shall retain the ultimate responsibility of ascertaining the measurements based on standard practices and clinical judgement.

The SpineUs™ System is a diagnostic ultrasound system, which consists of the FDA cleared Clarius Ultrasound Scanner C3 HD3 (K213436), a consumer PC, a tracking system with OptiTrack cameras connected to a POE switch and active LED markers, and the SpineUs™ computer application.

The SpineUs™ computer application, installed in the consumer PC, processes the ultrasound imaging data received from the Clarius Ultrasound Scanner and the tracking data received from the tracking system. The SpineUs™ computer application allows the operator to view ultrasound images of the spine, segment the ultrasound images using artificial intelligence, generate and visualize 3D reconstructions of the surface of the spine in real-time, measure spine-related anatomical components (e.g., intervertebral angles and spine curvature), review and manage patient measurement data, and generate and export printable reports.

The SpineUs™ system comprises the following:
Transducer / Scanner: Clarius Ultrasound Scanner, model C3 HD3 (K213436)
Software: SpineUs™ computer application
Tracking system: Motive Software, OptiTrack Cameras, SpineUs™ Active LED Markers, Power over Ethernet (PoE) switch
Accessories: USB-C charging cables, USB-C charging block, Wall mounted camera holders/covers, Tracker Reference (includes belt), Consumer PC

Here's a breakdown of the acceptance criteria and study details for the SpineUs™ System, based on the provided FDA 510(k) summary:

1. Table of Acceptance Criteria and Reported Device Performance (Segmentation AI)

2. Sample Size Used for the Test Set and Data Provenance

• Test Set Sample Size: 31 patients for both Non-Clinical and Clinical Performance Testing.
• Data Provenance: The data used in the Testing Datasets was obtained from clinical sites that are independent from those included in the Development dataset. While the specific countries are not mentioned, the gender, age, BMI, and ethnicity demographics suggest a diverse patient population, likely from multiple regions. The data is retrospective, as it involves recorded ultrasound sequences that were subsequently analyzed.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications

• Number of Experts: At least two clinical experts for the Segmentation AI outputs.
• Qualifications of Experts: Described as "trained clinical experts." No further specific qualifications (e.g., years of experience, specialty) are provided in the document for the test set ground truth.

4. Adjudication Method for the Test Set

• "At least two clinical experts" annotated the Segmentation AI outputs.
• "All annotations were reviewed by a separate annotator." This suggests a form of 2+1 or similar adjudication, where two experts make initial annotations, and a third (or a different "separate annotator") reviews them, potentially resolving disagreements or confirming consistency.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• No MRMC comparative effectiveness study was explicitly mentioned for AI-assisted versus without AI assistance.
• The clinical performance testing involved "three different observers measuring scoliosis angle on the SpineUs™ system images and X-ray images of the same patients." This was a comparison between the SpineUs™ system measurements and X-ray measurements, essentially using X-ray as a reference standard, not a comparison of human readers with and without AI assistance on the ultrasound images. Therefore, no effect size of human readers improving with AI vs. without AI assistance is provided.

6. Standalone Performance (Algorithm Only without Human-in-the-Loop Performance)

• Yes, standalone performance testing was done for the Segmentation AI.
• The section "Standalone Segmentation AI performance testing" explicitly states its purpose was "to assess the ability of the Segmentation AI to delineate between bone surfaces and background on ultrasound images from a recorded ultrasound sequence." The Non-Clinical Performance Testing summary directly reports the AI's performance on its own outputs against the established ground truth.

7. Type of Ground Truth Used

• Expert Consensus: For the Segmentation AI in both development and testing, image-level annotations were performed by trained clinical experts to label bone surface structures. These annotations, reviewed by a separate annotator, served as the ground truth for pixel-based metrics.
• X-ray Measurements: For the clinical performance testing assessing scoliosis angle, X-ray images of the same patients were used as the reference standard for comparison with SpineUs™ system measurements.

8. Sample Size for the Training Set

• Training Set Sample Size (Development Data): 81 ultrasound image sequences from 45 patients, totaling 17,684 images.

9. How the Ground Truth for the Training Set Was Established

• Expert Consensus with CT Confirmation: Image-level annotations were performed on a per-frame basis by a team of trained clinical experts, who labeled bone surface structures.
• Radiological Confirmation: "When available, corresponding thoracic CT imaging served as a ground truth to assist in the annotation process." This indicates that CT scans were used as a definitive reference to guide and confirm the expert annotations where possible.
• Adjudication: "All annotations were reviewed by a separate annotator." This ensures consistency and quality of the ground truth labels.

Ask a specific question about this device