Search Results

The qXR-BT device is intended to generate a secondary digital chest X-ray image that facilitates confirmation of the position of a breathing tube and an anatomical landmark on adult chest X-rays. This device is intended for use by licensed physicians who are trained in the evaluation of breathing tube placement on chest X-rays. The qXR-BT image provides adjunctive information and is not a substitute for the original PA/AP image.

qXR-BT is a standalone image analysis software used during the review of digital chest radiographic images, intended to facilitate determining the position of the breathing tube relative to the carina. Standard of care medical imaging workflows are well established, and include pre-existing software components such as a PACS, DICOM viewer and imaging worklist; qXR-BT is designed to integrate with these components.

X-rays are sent to qXR-BT by means of transmission functions within the user's PACS system. Upon completion of processing, the qXR-BT device returns results to the user's PACS or other userspecified radiology software system or database.

The input to the qXR-BT device is a chest X-ray (AP and PA, referred to as frontal) in digital imaging and communications in medicine (DICOM) format.

The qXR-BT device produces PDF and DICOM format outputs that enable users to view the position of a breathing tube and an anatomical landmark (carina).

The PDF format output contains preview images that show segmented structures outlined with a textual report describing the structures detected. The text report is restricted to the presence or absence of the breathing tubes and the carina as detected by the software device.

The DICOM format output consists of a single complete additional DICOM series for each input scan. This DICOM output contains labeled overlays indicating the location and extent of the segmentable structures, suitable for viewing in the PACS or radiology viewer.

The qXR-BT analysis module consists of a set of pre-trained convolutional neural networks (CNNs), that form the core processing component shown in Figure 1. This core processing component is coupled with a pre-processing module to prepare input DICOMs for processing by the CNNs and a post-processing module to convert the output into visual and tabular format for users.

Here's a breakdown of the acceptance criteria and the study that demonstrates the qXR-BT device meets them, based on the provided text:

1. A table of acceptance criteria and the reported device performance:

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

• Sample size: 162 Chest X-ray images.
• Data Provenance: Not explicitly stated regarding country of origin or whether it was retrospective or prospective.

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

• Number of experts: Three radiologists.
• Qualifications of experts: From the United States; no specific experience level (e.g., years of experience) is mentioned beyond "radiologists."

4. Adjudication method for the test set:

• Not explicitly stated. The text mentions "manual annotation of three radiologists," which implies an expert consensus method, but the specific adjudication rules (e.g., majority vote, independent review followed by consensus) are not detailed.

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:

• No, a multi-reader multi-case (MRMC) comparative effectiveness study with human readers was not explicitly mentioned or detailed in this summary. The performance testing described is a standalone evaluation of the algorithm's accuracy against ground truth.

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

• Yes, a standalone performance study was done. The text explicitly states, "Qure.ai performed standalone performance testing to test the accuracy of qXR-BT's analysis."

7. The type of ground truth used:

• Expert consensus. The ground truth was "based on manual annotation of three radiologists from United States."

8. The sample size for the training set:

• The sample size for the training set is not provided in the given document. The document only mentions the test set size.

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

• How the ground truth for the training set was established is not provided in the given document. The document only describes how the ground truth for the test set was established.

Ask a specific question about this device