Search Results

The Viz Subdural+ (Subdural Plus) device is intended for automatic labeling, visualization and quantification of collections in the subdural space from a set of Non-Contrast Head CT (NCCT) images. The software is intended to automate the current manual process of identifying, labeling and quantifying the volume of collections in the subdural space identified on NCCT images. Viz Subdural + provides volumes from NCCT images acquired at a single time point.

The Viz Subdural+ software is intended for labeling subdural collections and reporting the grayscale value of the collection, widest width of the subdural collection, and midline shift. The device output should be reviewed along with the patient's original images by a physician qualified to interpret brain CT images.

Viz Subdural+ is a software-only device that uses a locked artificial intelligence machine learning (AI/ML) algorithm to process and analyze non-contrast CT (NCCT) scans of the head to automatically measure the collections in the subdural region in the brain and midline shift.

The device output provides visual overlays of automatically measured subdural collections where the overlay opacity (intensity) corresponds to the grayscale value of the collection within the native NCCT, and reports the total volume and widest width of the subdural collections. The device also automates and reports the measure of midline shift.

The results of the automated measurement are provided in a summary series and segmentation series in DICOM format. The summary series consists of a summary table of subdural collections, snapshot of each collection and a midline shift measurement. The first slice of the Subdural+ summary series summarizes the measurement results of each subdural collection (volume and widest width), total volume and midline shift in tabular format. The summary series also contains a snapshot of each subdural collection and a snapshot of the midline shift measurement. The segmentation series shows an RGB overlay where a subdural collection is identified by a colored overlay with the color intensity corresponding to the HU values of the original image on each slice of the input series of the segmented region. On slices with an overlay representing a measured subdural collection, the volume of the subdural collection is provided. The midline shift is overlaid and provided on the slice where the midline shift is measured.

Images are automatically forwarded from the Healthcare Facility and sent to Viz.ai's Backend Server after acquisition at the CT scanner. Viz Subdural+ is hosted on Viz.ai's Backend Server and automatically analyzes applicable NCCT scans that are acquired on CT scanners and are forwarded to Viz.ai's Backend Server. The results of the analysis are exported in DICOM format and are sent to a DICOM destination (e.g., PACS) where they are available for review by radiologists, neurologists, neuro-surgeons, interventional neuroradiologists, or other appropriately trained professionals to assist in the measurement of subdural collection volume, widest subdural collection width and midline shift.

Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided FDA 510(k) clearance letter for Viz Subdural+:

Acceptance Criteria and Reported Device Performance

Note: The document states the device "passed the primary endpoints for the study in terms of mean absolute error (MAE)," but it does not explicitly state the numerical acceptance thresholds for subdural collection volume or thickness MAE/DICE. The 2mm MAE for Midline Shift is inferred from the statement that the Subdural+ algorithm can measure midline shift "within the same performance limits (MAE < 2mm) as the predicate device."

Study Information

1. Sample Size Used for the Test Set and Data Provenance:

   • Subdural Collection Volume and Thickness Assessment: 203 cases
   • Midline Shift Assessment: 151 cases
   • Data Provenance: Retrospective study. Cases were obtained from two clinical sites. Imaging was from patients who received NCCT imaging assessment after presenting to one of the participating sites. The country of origin is not explicitly stated.

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

   • Number of Experts: Not explicitly stated, but established by "trained neuroradiologists."
   • Qualifications: "Trained neuroradiologists" – specific experience levels (e.g., 10 years) are not provided.

3. Adjudication Method for the Test Set:

   • Not explicitly stated. The ground truth was "established by trained neuroradiologists," which could imply consensus or sequential review, but the specific method (e.g., 2+1, 3+1) is not detailed.

4. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:

   • No MRMC comparative effectiveness study involving human readers improving with AI vs. without AI assistance was mentioned. The study focused on the standalone performance of the algorithm against a human-established ground truth.

5. Standalone (Algorithm Only) Performance Study:

   • Yes, a retrospective study was conducted to assess the "standalone performance of the image analysis algorithm for Viz Subdural+ as compared to a ground truth established by trained neuroradiologists."

6. Type of Ground Truth Used:

   • Expert Consensus: The ground truth was "established by trained neuroradiologists" in segmenting, labeling, and quantifying subdural collections, maximal subdural collection width (thickness), and midline shift. This implies expert consensus or adjudicated expert readings. It is not pathology or outcomes data.

7. Sample Size for the Training Set:

   • Not explicitly stated in the provided text.

8. How the Ground Truth for the Training Set Was Established:

   • Not explicitly stated in the provided text. The document focuses on the performance of the locked AI/ML algorithm (implying training was already completed) and its validation against a test set.

Ask a specific question about this device