(88 days)
The 3D Auto LAA is a software application designed to view and quantify 3D image data acquired by Philips Ultrasound Systems for use in measuring the area, circumference, and diameter of a Left Atrial Appendage (LAA) orifice.
The purpose of this Traditional 510(k) Pre-market Notification is to introduce the new 3D Auto LAA cardiac quantification application for use on the Philips EPIQ and Affiniti Diagnostic Ultrasound systems, which were most recently cleared under K201012. The 3D Auto LAA application is compatible with 3D images generated via Philips Transesophageal Echocardiogram (TEE) transducers such as the X8-2t and X7-2t. The Philips 3D Auto LAA cardiac quantification application is a semi-automated application intended to provide measurements of the Left Atrial Appendage. The 3D Auto LAA application is designed to provide automatic and editable area, circumference, and diameter measurements of the Left Atrial Appendage (LAA) orifice. When the 3D Auto LAA application is launched, going through the workflow provides the clinician with a semi-automated preliminary border of the LAA in three planes based on greyscale intensity differentiation with some shape regularization.
Here's a breakdown of the acceptance criteria and the study information for the Philips 3D Auto LAA device, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
The provided text does not explicitly list specific acceptance criteria with numerical targets (e.g., accuracy > 90%) or directly reported performance metrics tied to such criteria. Instead, it states that the device was tested to "meet the defined requirements and performance claims." The "performance claims" are implicitly about the functionality of providing semi-automated measurements of LAA area, circumference, and diameter.
Here's an interpretation based on the document's content, focusing on the functionality described:
| Acceptance Criterion (Inferred from functionality) | Reported Device Performance (Inferred from "successful V&V testing" and description) |
|---|---|
| Ability to view 3D image data | Device successfully views 3D image data. |
| Ability to quantify LAA orifice measurements (area, circumference, diameter) | Device provides semi-automated and editable measurements of LAA area, circumference, and diameter. |
| Semi-automated border detection | Device provides a semi-automated preliminary border of the LAA in three planes. |
| Measurable LAA Area | Device generates LAA Area (mm²). |
| Measurable LAA Circumference | Device generates LAA Circumference (mm). |
| Measurable LAA Max Diameter | Device generates LAA Max Diameter (mm). |
| Measurable LAA Minimum Diameter | Device generates LAA Minimum Diameter (mm). |
| Editability of generated borders | User can modify the entire contour or individual points. |
| Compatibility with Philips Ultrasound Systems | Compatible with Philips EPIQ and Affiniti Diagnostic Ultrasound systems and Philips Transesophageal Echocardiogram (TEE) transducers. |
Important Note: The document focuses on demonstrating substantial equivalence to a predicate device by comparing intended use and technological characteristics, and by conducting internal V&V testing. It does not provide a detailed performance study with quantitative results against specific, pre-defined acceptance metrics.
2. Sample Size Used for the Test Set and Data Provenance
- Test Set Sample Size: The document does not specify a numerical sample size for the "Performance Validation Study" or any other non-clinical V&V testing. It only mentions that testing was performed.
- Data Provenance: The document does not specify the country of origin of the data or whether it was retrospective or prospective. Given it's a non-clinical performance validation study and not a clinical trial, it's likely internal engineering data or synthetic data, but this is not explicitly stated.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
The document does not provide any information regarding the number or qualifications of experts used to establish ground truth for the non-clinical test set. As this was a "Performance Validation Study" for a software application for quantification, it's more likely that the "ground truth" was derived from predefined technical specifications, comparison to manual measurements by engineers, or comparison to the predicate device's output, rather than expert clinical consensus on images.
4. Adjudication Method for the Test Set
The document does not specify any adjudication method for the test set.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and The Effect Size of How Much Human Readers Improve with AI vs. Without AI Assistance
A Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not performed or reported in this document. The document explicitly states: "The subject Philips 3D Auto LAA cardiac quantification did not require clinical data in order to make a determination for substantial equivalence when compared to the predicate device(s)." This indicates no human-in-the-loop performance study for regulatory submission purposes.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done
Yes, a standalone performance assessment was done implicitly. The "Performance Validation Study" and "Software Verification and Validation testing" address the algorithm's performance in generating semi-automated borders and measurements. However, it's important to note the device is described as "semi-automated," implying a human-in-the-loop is part of the intended use (to refine the borders). The testing reported here focuses on the algorithm's capability to generate these preliminary borders and measurements.
7. The Type of Ground Truth Used
The document does not explicitly state the type of ground truth used for the non-clinical V&V testing. Given the nature of a software quantification tool, it's highly probable the ground truth involved:
- Comparison against measurements obtained manually by trained individuals (engineers or potentially clinicians) using existing validated methods.
- Comparison against the performance of the predicate device (QLAB System's 3DQ Q-App) manual tracing options, to ensure equivalence.
- Internal gold standards derived from expert-generated manual segmentations on a subset of images used for development and testing.
8. The Sample Size for the Training Set
The document does not provide any information regarding the sample size for the training set. This information is typically not included in a 510(k) summary focused on substantial equivalence and non-clinical testing.
9. How the Ground Truth for the Training Set Was Established
The document does not provide any information on how the ground truth for the training set was established.
§ 892.2050 Medical image management and processing system.
(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).