Search Results

The Butterfly Auto 3D Bladder Volume Tool is a software application package. It is designed to view, quantify and report results acquired on Butterfly Network ultrasound systems for noninvasive volume measurements of the bladder, to support physician diagnosis. Indicated for use in adult populations.

The Butterfly Auto 3D Bladder Volume Tool is a software application used on Butterfly iQ Ultrasound Systems to provide a non-invasive measurement of bladder volume. The system calculates the bladder volume using proprietary artificial intelligence automatic segmentation and volume measurement algorithms on Butterfly Network ultrasound systems.

The Auto 3D Bladder Volume Tool allows the clinician to calculate bladder volume when using the Bladder preset in B-mode. The tool is used to acquire 25, 2D images of the bladder. Once acquired, a volume estimate is calculated and presented back to the clinician. The clinician can then exit, restart the tool or save the acquisition to the study roll. The information presented is intended as additional input to standard diagnostic pathways and is only to be used by qualified clinicians.

The Auto 3D Bladder Volume Tool is based on the image segmentation method, U-Net', and the volume calculation is computed using the process of integration over binary images.

Here's a breakdown of the acceptance criteria and study information for the Butterfly Network Auto 3D Bladder Volume Tool, based on the provided FDA 510(k) summary:

1. Acceptance Criteria and Reported Device Performance

Note: The document states that the "primary endpoint was met" but does not explicitly provide the specific numerical results of the device performance against the acceptance criteria within this summary section. It only lists the target performance (which matches the predicate's stated performance).

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

The document states, "A non-interventional validation study was conducted, where bladder volume was calculated." It mentions that "The patient dataset was constructed to provide a representative range of volume values, in a patient population with a balanced gender proportion and clinically typical age."

• Sample Size: The exact sample size for the test set is not explicitly stated in the provided text.
• Data Provenance: The document does not specify the country of origin of the data. It indicates the study was "non-interventional" and used a "patient dataset," suggesting it was retrospective data, but this is not explicitly confirmed.

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

Not explicitly stated. The document mentions that the primary endpoint was met and that inter and intra-operator variability was assessed, implying the involvement of operators/experts, but provides no details on their number or qualifications, nor how they established ground truth for the test set.

4. Adjudication Method for the Test Set

Not explicitly stated. No information is provided regarding an adjudication method (e.g., 2+1, 3+1, none) for the test set.

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

No. The document does not mention a multi-reader multi-case (MRMC) comparative effectiveness study comparing human readers with AI assistance versus without AI assistance. The study focuses on the performance of the algorithm itself.

6. Standalone (Algorithm Only) Performance Study

Yes. The validation study described appears to be a standalone performance study. The document states, "A non-interventional validation study was conducted, where bladder volume was calculated." It also mentions "Inter and intra-operator variability was assessed between operators processing the same images," which suggests the algorithm's output was part of the assessment, but the primary focus is on the device's ability to calculate bladder volume using its AI algorithm. The statement "Test datasets were strictly segregated from algorithm training datasets" further supports this.

7. Type of Ground Truth Used

The document does not explicitly state the method used to establish the ground truth volume for the test set. Given the context of bladder volume measurement, common methods for ground truth could include:

• Catheterization (direct measurement): This is often considered the gold standard for bladder volume.
• Manual ultrasound tracing by experts: Expert consensus on manual tracing of the bladder in 2D or 3D ultrasound could also be used as a reference.
• Phantom studies: Controlled experiments with known volumes.

However, the provided text does not specify which type of ground truth was used.

8. Sample Size for the Training Set

Not explicitly stated. The document mentions "Test datasets were strictly segregated from algorithm training datasets," confirming that a training set was used, but its size is not provided.

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

Not explicitly stated. The document mentions the use of "proprietary artificial intelligence automatic segmentation and volume measurement algorithms" and references the U-Net convolutional network for biomedical image segmentation, which implies that the training set would have included images with corresponding ground truth segmentations. However, the exact method or the qualifications of those who established this ground truth for the training data are not detailed.

Ask a specific question about this device