(51 days)
QLAB Advanced Quantification Software is a software application package. It is designed to view and quantify image data acquired on Philips ultrasound systems.
The Philips QLAB Advanced Quantification Software System (QLAB) is designed to view and quantify image data acquired on Philips ultrasound systems. QLAB is available either as a stand-alone product that can function on a standard PC, a dedicated workstation, and on-board Philips' ultrasound systems.
The purpose of this Traditional 510(K) Pre-market Notification is to introduce a new to introduce the new 3D Auto MV cardiac quantification application to the Philips QLAB Advanced Quantification Software, which was most recently cleared under K191647. The latest QLAB software version (launching at version 15.0) will include the new Q-App 3D Auto MV, which integrates the segmentation engine of the cleared QLAB HeartModel Q-App (K181264) and the TomTec-Arena 4D MV Assessment application (K150122) thereby providing a dynamic Mitral Valve clinical quantification tool.
The document describes the QLAB Advanced Quantification Software System and its new 3D Auto MV cardiac quantification application.
Here's an analysis of the acceptance criteria and study information:
1. Table of Acceptance Criteria and Reported Device Performance:
The document does not explicitly state acceptance criteria in a quantitative table format (e.g., "accuracy must be > 90%"). Instead, it states that the device was tested to "meet the defined requirements and performance claims." The performance is demonstrated by the non-clinical verification and validation testing, and the 3D Auto MV Algorithm Training and Validation Study.
The document provides a comparison table (Table 1 on page 6-7) that highlights the features and a technical comparison to predicate devices, but this table does not present quantitative performance against specific acceptance criteria for the new 3D Auto MV feature. It lists parameters that the new application will measure, such as:
- Saddle Shaped Annulus Area (cm²)
- Saddle Shaped Annulus Perimeter (cm)
- Total Open Coaptation Area (cm²)
- Anterior Closure Line Length (cm)
- Posterior Closure Line Length (cm)
However, it does not provide reported performance values for these parameters from the validation study against any predefined acceptance criteria. The statement is that "All other measurements are identical to the predicate 4D MV-Assessment application," implying a level of equivalence, but without specific data.
2. Sample Size Used for the Test Set and Data Provenance:
The document mentions that Non-clinical V&V testing also included the 3D Auto MV Algorithm Training and the subsequent Validation Study performed for the proposed 3D Auto MV clinical application. However, it does not specify the sample size used for this validation study (i.e., the test set). The data provenance (e.g., country of origin, retrospective or prospective) is also not specified.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Their Qualifications:
This information is not provided in the document.
4. Adjudication Method for the Test Set:
This information is not provided in the document.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
The document does not indicate that a MRMC comparative effectiveness study was done. It focuses on the software's performance and substantial equivalence to predicate devices, not on how human readers' performance might improve with its assistance.
6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study:
The document describes the 3D Auto MV Q-App as a "semi-automatic tool" and states that the "User is able to edit, accept, or reject the initial landmark proposals of the mitral valve anatomical locations." This suggests that a purely standalone (algorithm-only) performance study, without any human-in-the-loop interaction, would not be fully representative of its intended use. The validation study presumably evaluates its performance within this semi-automatic workflow, but specific details are lacking.
7. Type of Ground Truth Used:
The document describes the 3D Auto MV application integrating the machine-learning derived segmentation engine of the QLAB HeartModel and the TOMTEC-Arena TTA2 4D MV-Assessment application. The ground truth for the training of the HeartModel (and subsequently the 3D Auto MV) would typically involve expert annotations of anatomical structures. However, the specific type of ground truth used for the validation study mentioned ("3D Auto MV Algorithm Training and the subsequent Validation Study") is not explicitly stated. Given the context of cardiac quantification, it would most likely be based on expert consensus or expert-derived measurements from the imaging data itself.
8. Sample Size for the Training Set:
The document mentions "3D Auto MV Algorithm Training" but does not specify the sample size used for the training set.
9. How the Ground Truth for the Training Set Was Established:
The document states that the 3D Auto MV Q-App "integrates the segmentation engine of the cleared QLAB HeartModel Q-App (K181264)". For HeartModel, it says: "The HeartModel Q-App provides a semi-automatic 3D anatomical border detection and identification of the heart chambers for the end-diastole (ED) and end-systole (ES) cardiac phases." And for its contour generation: "3D surface model is created semi-automatically without user interaction. User is required to edit, accept, or reject the contours before proceeding with the workflow."
This implies that the training of the HeartModel's segmentation engine (and inherited by 3D Auto MV) was likely based on expert-derived or expert-validated anatomical annotations/contours, which would have been used to establish the "ground truth" for the machine learning algorithm. However, explicit details on how this ground truth was established for the training data (e.g., number of annotators, their qualifications, adjudication methods) are not provided for this specific submission (K200974). It simply references the cleared HeartModel Q-App (K181264).
§ 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).