Search Results

AI-Rad Companion (Musculoskeletal) is an image processing software that provides quantitative and qualitative analysis from previously acquired Computed Tomography DICOM images to support radiologists and physicians from emergency medicine, specialty care, urgent care, and general practice in the evaluation and assessment of musculoskeletal disease. It provides the following functionality:

• Segmentation of vertebras
• Labelling of vertebras
• Measurements of heights in each vertebra and indication if they are critically different
• Measurement of mean Hounsfield value in volume of interest within vertebra.
  Only DICOM images of adult patients are considered to be valid input.

Al-Rad Companion (Musculoskeletal) is software-only image post-processing application that uses deep learning algorithms to post-process CT data of the thorax. Al-Rad Companion (Musculoskeletal) supports workflows for visualization and various measurements of musculoskeletal disease, including:

• Segmentation of vertebras ●
• Labelling of vertebras
• Measurements of heights in each vertebra and indication if they are critically ● different
• . Measurement of mean Hounsfield value in volume of interest within vertebra

Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided text:

Acceptance Criteria and Device Performance

Note: The document explicitly states that the device's performance was "consistent for all critical subgroups, such as vendors or reconstruction parameters and patient age."

Study Details

2. Sample size used for the test set and the data provenance:

• Sample Size: N=140
• Data Provenance: Retrospective performance study on chest CT data from multiple clinical sites across the United States and Europe.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

• Number of Experts: Four radiologists.
• Qualifications: Not explicitly stated beyond "radiologists."

4. Adjudication method for the test set:

• Adjudication Method: Two readers per case, plus a third reader for adjudications (effectively a 2+1 method for cases with disagreement).

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, if so, what was the effect size of how much human readers improve with AI vs without AI assistance:

• MRMC Study: No, a comparative effectiveness study with human readers (MRMC) was not explicitly described. The study focused on the device's standalone performance compared to human ground truth.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

• Standalone Performance: Yes, the described study evaluated the "performance of the Al-Rad Companion (Musculoskeletal) device," which is an algorithm-only image processing software. The reported performance metrics (ratio of measurements within LoA) are for the device itself against the human-established ground truth.

7. The type of ground truth used:

• Type of Ground Truth: Expert consensus, established using manual vertebra height and density measurements performed by four radiologists with adjudication.

8. The sample size for the training set:

• Sample Size for Training Set: Not specified in the provided text. The document mentions that the device "uses the same deep learning technology as in the previously cleared reference device Siemens Al-Rad Companion (Cardiovascular) (K183268)," implying a pre-existing training process, but details of that training set are not in this document.

9. How the ground truth for the training set was established:

• Ground Truth for Training Set: Not specified in the provided text. Since the device leverages deep learning, it would have required a large, annotated dataset for training, but the specifics of how that training ground truth was established are not detailed in this document.

Ask a specific question about this device