Search Results

QLAB Advanced Quantification Software is a software application package. It is designed to view and quantify image data acquired on Philips ultrasound systems.

Philips QLAB Advanced Quantification software (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. It can be used for the off-line review and quantification of ultrasound studies.

QLAB software provides basic and advanced quantification capabilities across a family of PC and cart based platforms. QLAB software functions through Q-App modules, each of which provides specific capabilities.

QLAB builds upon a simple and thoroughly modular design to provide smaller and more easily leveraged products.

Philips Ultrasound is submitting this 510(k) to address QLAB 11.0 modifications which include:

• Dynamic Heart Model (DHM) an enhancement to the Heart Model Quantification ● application that provides tracking of the entire cardiac cycle
• QLAB functionality upgraded to the HSDP Platform 2 from the HSDP Platform 1 ●
• O-Store Shared central database supporting multiple clients. .

The document provided is a 510(k) premarket notification for the Philips QLAB Advanced Quantification Software. It states that the submission is for modifications to an existing device (QLAB 10.8 K171314) and does not introduce new indications, modes, features, or technologies that require clinical testing. Therefore, there is no detailed study described that definitively calculates specific acceptance criteria and device performance metrics in the traditional sense of a clinical trial for a novel device.

However, based on the information provided, we can infer the approach to acceptance criteria and "performance" from the perspective of software verification and validation for modifications to an already cleared device.

1. Table of Acceptance Criteria and Reported Device Performance

Since this is a submission for modifications to an existing cleared device, the "acceptance criteria" revolve around ensuring the modified software functions as intended and does not negatively impact the safety and effectiveness of the previously cleared predicate device. Performance is demonstrated through software verification and validation against internal requirements.

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

The document does not specify a "test set" in the context of patient data or clinical images for evaluating the diagnostic performance of the algorithms. Instead, the testing described is focused on software verification and validation. This typically involves:

• Test Cases: Software testing would involve a suite of test cases designed to cover all functionalities, new and existing, and boundary conditions. The number of these test cases is not specified.
• Data Provenance: The document does not mention the use of patient data for performance evaluation in terms of diagnostic accuracy. The testing is focused on the software's functional and technical aspects. Since this is an upgrade to an existing quantification software, it is likely that existing image data (possibly de-identified, potentially from various sources including internal datasets or public datasets for software testing purposes) would have been used to validate the functions of the application, but this is not explicitly stated. The document strongly emphasizes that no new indications or technologies requiring clinical testing are introduced.

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

Given that no clinical testing requiring a "ground truth" established by external experts is detailed, this information is not provided. The "ground truth" for software verification and validation is defined by the product's functional and technical requirements.

4. Adjudication Method for the Test Set

Not applicable, as no external expert adjudication for a "test set" (in the clinical sense) is described.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

No. The document explicitly states: "QLAB 11.0 introduces no new indications for use, modes, features, or technologies relative to the predicate device (QLAB 10.8 K171314) that require clinical testing." Therefore, an MRMC study comparing human readers with and without AI assistance was not performed.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

The QLAB Advanced Quantification Software is described as a "software application package" designed to "view and quantify image data." It functions as an "off-line review and quantification" tool. While its primary function is quantification, the context implies it's a tool used by a human to assist in diagnosis or assessment. The mention of "tracking of the entire cardiac cycle" and "expanding the measurements" for the Dynamic Heart Model suggests algorithmic quantification, but it is not presented as a standalone diagnostic AI system that operates without human review or interaction. The performance data focuses on the software fulfilling its functional requirements within the existing framework of the predicate device.

7. The Type of Ground Truth Used

The "ground truth" for the software verification and validation activities is based on the defined software requirements and specifications. This is a functional "ground truth" rather than a clinical ground truth (like pathology, expert consensus on patient outcomes). The goal was to demonstrate that the software modifications (Dynamic Heart Model, HSDP Platform 2, Q-Store) work as designed.

8. The Sample Size for the Training Set

No training set is mentioned. This submission is for modifications to quantification software, not a de novo AI model that requires training on a dataset. The "Dynamic Heart Model" is described as an "enhancement" to an existing application providing "tracking" and "expanding measurements," suggesting algorithmic improvements rather than a new discriminative AI model requiring a separate training set.

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

Not applicable, as no training set for a de novo AI model is mentioned.

Ask a specific question about this device