Search Results

Brainomix 360 e-CTA is an image processing software package to be used by trained professionals, including, but not limited to physicians and medical technicians. The software runs on standard "off the-shelf" hardware (physical or virtualized) and can be used to perform image viewing, processing, and analysis of images. Data and images are acquired through DICOM compliant imaging devices.

Brainomix 360 e-CTA provides viewing and analysis capabilities for imaging datasets acquired with CTA (CT Angiography).

Brainomix 360 e-CTA is not intended for mobile diagnostic use.

Brainomix 360 e-CTA vessel density asymmetry ratio applies only to the MCA region.

Brainomix 360 e-CTA is a medical image visualization and processing software package compliant with the DICOM standard and running on an off-the-shelf physical or virtual server.

Brainomix 360 e-CTA allows for the visualization, analysis and post-processing of DICOM compliant CTA images which, when interpreted by a trained physician or medical technician, may yield information useful in clinical decision making.

Brainomix 360 e-CTA provides a wide range of basic image viewing, processing and manipulation functions, through multiple output formats. Functionality includes image registration and visualization of large cerebral vessels to provide an analysis of hemispheric difference via contralateral comparison (displayed as a relative percentage).

Brainomix 360 e-CTA processes the images using Al/ML algorithms where the input channels will help the software distinguish bone from vessels and reduce image grain.

Brainomix 360 e-CTA automatically provides a colored overlay to provide a visual reference of the MCA hemisphere of the brain with lower vessel density, and corresponding contrast intensity measurements and estimated phase.

Brainomix 360 e-CTA can connect with other DICOM-compliant devices, for example to transfer CTA scans from a Picture Archiving and Communication System (PACS) to Brainomix 360 e-CTA software for processing. Results and images can be sent to a PACS via DICOM transfer and can be viewed on a PACS workstation or via a web user interface on any machine and accessed within a hospital network and firewall and with a connection to the Brainomix 360 e-CTA software (e.g. a LAN connection).

Brainomix 360 e-CTA notification capabilities enable clinicians to preview images via e-mail notification with result image attachments. Images that are previewed via e-mail are compressed, are for informational purposes only, and not intended for diagnostic use beyond notification.

Brainomix 360 e-CTA is not intended for mobile diagnostic use. Notified clinicians are responsible for viewing non-compressed images on a diagnostic viewer and engaging in appropriate patient evaluation and relevant discussion with a treating physician before making care-related decisions or requests.

Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided FDA 510(k) submission document for Brainomix 360 e-CTA.

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

The document provides performance metrics, primarily focusing on Dice Similarity Coefficient (DSC) for vessel and parenchyma delineation, and Mean Absolute Error (MAE) for vessel density ratio. The "acceptance criteria" are implied by the "Summary performance metrics from full sample" and comparison to a previous version of the device.

Note on "Acceptance Criteria": The document explicitly states acceptance criteria for the digital phantom validation of vessel density ratio. For the AI/ML comparison, the criterion is implied as an improvement over the previous version of the device. For the standalone performance study, the document states "reaching for the vessel delineation and 0.999 for the parenchyma mask as the desired requirement," indicating these are the target performance levels.

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

• Test Set Sample Size: 308 Computed Tomography (CTA) brain scans (studies).
• Data Provenance:
  • Country of Origin: U.S.
  • Clinical Sites: Majority from Boston Medical Centre (BMC) or referring hospitals in the Massachusetts area (N=179). The remaining from Mayo Clinic Rochester (MCR; N=129).
  • Retrospective or Prospective: Retrospective study.

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

The document does not explicitly state the number of experts or their specific qualifications (e.g., "radiologist with 10 years of experience") used to establish the ground truth for the standalone performance study. It mentions the "truthers" in Table 9 in the context of stenosis.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

The document does not explicitly describe an adjudication method for the ground truth establishment in the standalone performance study.

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

A Multi-Reader Multi-Case (MRMC) comparative effectiveness study involving human readers assisting with AI vs. without AI assistance was not conducted or described in this document. The study presented is a standalone performance study of the algorithm and a comparison to the predicate device's algorithm.

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

Yes, a standalone performance study (algorithm only) was conducted to assess the performance of the vessel delineation and parenchyma mask generation. This is described in "4.3 Summary of Standalone Performance Study."

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)

The document implies the ground truth for the standalone performance study was established by human experts, referred to as "truthers" (e.g., "truthed masks" or "stenosis as noted by the truthers"). However, the precise method (e.g., manual segmentation by expert, consensus of multiple experts) is not explicitly detailed. Given the assessment of segmentation performance (Dice Similarity Coefficient), it's highly likely that the ground truth involved expert-annotated segmentations.

8. The sample size for the training set

The document does not provide the sample size for the training set. The study focuses on evaluating the performance of the device's AI/ML algorithm on a separate test set.

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

The document does not provide information on how the ground truth for the training set was established. It only mentions that the device uses "AI/ML algorithms" to "distinguish bone from vessels" and "increase the quality of the vessel mask."

Ask a specific question about this device