(28 days)
QLAB Quantification Software is a software application package. It is designed to view and quantify image data acquired on Philips Healthcare ultrasound products.
QLAB Quantification software is available either as a stand-alone product that can function on a standard PC, on board a dedicated workstation, or on-board Philips' ultrasound systems. It can be used by trained healthcare professionals for the on-line and off-line review and quantification of ultrasound studies in healthcare facilities/hospitals. The QLAB Quantification software application package is designed to view and quantify image data acquired on Philips ultrasound products. The four modified plug-ins, a2DO, aCMQ , MVN, and Heart Model are applications within Philips QLAB Quantification software.
The provided document (K132165) describes modifications to existing QLAB Quantification software Q-Apps (a2DQ, aCMQ, MVN, and Heart Model). The submission is a special 510(k) and focuses on demonstrating that the modified software maintains the same level of safety and effectiveness as the predicate (unmodified) versions. It does not present a de novo study to establish new acceptance criteria or full device performance metrics beyond confirming equivalence to the predicate.
Therefore, direct responses to some of your questions, particularly those asking for the reported device performance against acceptance criteria or details of a stand-alone study with specific metrics, are not explicitly provided in this type of submission. The document emphasizes verification and validation against the predicate's established performance, rather than setting and meeting entirely new benchmarks.
Here's an attempt to answer your questions based on the provided text, indicating where information is not explicitly stated for this type of submission:
1. A table of acceptance criteria and the reported device performance
The document states: "Verification and Validation testing concluded that the modified QLAB Q-Apps are safe and effective and introduced no new risks." and "Testing performed demonstrated that the QLAB Quantification software with modified Q-Apps meets all defined reliability requirements and performance claims."
This indicates that the acceptance criteria for this special 510(k) were based on demonstrating equivalence in safety, effectiveness, reliability, and performance to the legally marketed predicate devices. Specific quantitative acceptance criteria (e.g., "EF measurement must be within X% of ground truth") and corresponding reported performance values are not detailed in this summary.
| Acceptance Criteria (Implied) | Reported Device Performance (Implied) |
|---|---|
| Maintain safety profile of predicate device | No new risks introduced. |
| Maintain effectiveness profile of predicate device | Safe and effective. |
| Meet established reliability requirements of predicate device | Meets all defined reliability requirements. |
| Meet established performance claims of predicate device | Meets all defined performance claims. |
| Support intended use | Does not alter the intended use. |
| Not introduce new technological characteristics | Has the same technological characteristics as the legally marketed device. |
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
The document does not specify the sample size for the test set used in verification and validation activities, nor does it provide details on the data provenance (country of origin, retrospective/prospective). This level of detail is typically found in the full test reports, not a 510(k) summary for modifications.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)
The document does not specify the number or qualifications of experts used to establish ground truth for the test set.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
The document does not specify the adjudication method used for the test set.
5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance
The document does not mention a multi-reader multi-case (MRMC) comparative effectiveness study. The focus is on software modifications to existing Q-Apps for improved workflow and semi-automation, not necessarily on a comparative effectiveness study of human readers with vs. without AI assistance. The modifications, particularly for MVN and a2DQ, aim to improve user efficiency and ease of use, which would imply an improvement in human reader efficiency but this is not quantified as an effect size from an MRMC study in this summary.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
The document repeatedly mentions "semi-automated border detection" (a2DQ), "automatically draw a region of interest" (aCMQ), and "semi-automation for greater efficiency and ease of use" (MVN), with an explicit mention that "The modified Heart Model application allows users to override border placement. The user may edit the border by clicking and dragging the border to the desired location." This strongly suggests that these are human-in-the-loop applications where the software provides automated assistance but the user retains control and the ability to edit. Therefore, a purely standalone (algorithm-only) performance evaluation independent of human interaction is not implied or described by the context of these modifications.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
The document refers to "Verification and Validation testing" demonstrating that the modified software meets "all defined reliability requirements and performance claims" relative to the "predicate." It does not explicitly state the type of ground truth used. For quantification software in medical imaging, ground truth often involves:
- Manual tracings/measurements by expert cardiologists.
- Correlation with other imaging modalities (e.g., Cardiac MR for Heart Model as mentioned, "Measurements are closely correlated to cardiac MR").
- Possibly phantoms or simulated data for certain aspects.
However, the specific methods are not detailed in this summary.
8. The sample size for the training set
The document does not provide any information regarding the sample size for a training set. As this is a special 510(k) for modifications, it's possible that the modifications primarily involved refinement of existing algorithms and workflows, rather than a complete retraining of an AI model requiring a new, distinct training set.
9. How the ground truth for the training set was established
The document does not provide information on how ground truth for any potential 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).